Power distribution network fault positioning method and device based on double-end positioning, equipment and medium

Abstract

The invention discloses a power distribution network fault positioning method and device based on double-end positioning, equipment and a medium, and the method comprises the steps: carrying out the relative zero-moment alignment of wave recording files of positioning devices at two ends, so as to obtain first voltage traveling wave line mode components at two ends of a fault line; according to the first voltage traveling wave line mode components, first wave head time sequences at the two ends of the fault line are obtained respectively; calculating a relation characteristic value of the first overlapped wave head and the second overlapped wave head according to the first wave head time sequence at the two ends of the fault line; and inputting the relation characteristic value and the upstream and downstream time difference of the fault point into a preset neural network model, outputting a fault point distance, and carrying out power distribution network fault positioning according to the fault point distance. According to the invention, the relation characteristic value and the upstream and downstream time difference of the fault point are taken as the input values of the model, so that the problem that the traditional double-end distance measurement method needs time synchronization and wave velocity normalization is avoided, and the accuracy of power distribution network fault positioning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault monitoring, and in particular to a distribution network fault locating method, device, equipment and medium based on double-end positioning. Background Art

[0002] Traditional distribution networks usually rely on manual troubleshooting section by section, which is time-consuming and labor-intensive. In order to significantly reduce the power outage time caused by fault repair time, it is of great significance to conduct precise fault detection of distribution networks.

[0003] Currently, the main method for locating faults in distribution networks uses the traveling wave method, which is divided into single-ended and double-ended traveling wave methods. The former uses the time difference between the zero-mode and line-mode wave heads for location, and in practice, the theoretical wave velocity is often used. However, the propagation speed of traveling waves is affected by line parameters (such as conductor type, insulation medium, and aging), resulting in unstable wave velocity and large error fluctuations. Furthermore, distribution networks typically contain a large number of branch lines and short-distance feeders. Traveling waves undergo refraction and reflection at multiple nodes, causing severe waveform distortion. The overlapping zero-mode and line-mode wave heads are difficult to distinguish. The double-ended method only extracts the first wave head, but the data at both ends must be strictly synchronized, and the error must be controlled to within the microsecond level, or even within 50 nanoseconds. Both traveling wave location methods require accurate wave head extraction, but the high-frequency components of the traveling wave signal are easily attenuated during propagation. This is especially true in mixed cable and overhead line lines or complex branch networks. Due to high-frequency attenuation and noise interference, the signal is weak, prone to misjudgment, and affects the accuracy of the time difference calculation, resulting in large positioning errors. Traveling wave positioning requires high-frequency sampling devices (MHz level) and needs to be widely installed at key nodes, resulting in high hardware costs and difficulty in large-scale promotion in distribution networks. Summary of the Invention

[0004] The present invention provides a distribution network fault locating method, device, equipment and medium based on double-end positioning, which can improve the accuracy of distribution network fault locating.

[0005] In a first aspect, an embodiment of the present invention provides a distribution network fault location method based on double-end positioning, comprising:

[0006] Obtain the recording files of the double-end positioning devices at both ends of the fault line, and extract the start time stamps of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line;

[0007] Aligning the relative zero time, and respectively extracting first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data;

[0008] Performing wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtaining first wave head time series at both ends of the fault line respectively based on the first time domain waveforms;

[0009] Obtaining a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculating a relationship characteristic value between the first overlapping wave head and the second overlapping wave head;

[0010] The relationship characteristic value and the time difference between the upstream and downstream of the fault point are input into a preset neural network model, the fault point distance is output, and the distribution network fault is located based on the fault point distance; wherein, the time difference between the upstream and downstream of the fault point is obtained based on the recording file.

[0011] The embodiment of the present invention aligns the fault recording data at both ends of the fault line by using the relative zero time, thereby providing data preparation for the subsequent acquisition of the first voltage traveling wave line mode component at both ends, and avoids the problem of strict synchronization of the time at both ends in the traditional two-end traveling wave method; by obtaining the first wave head time series at both ends of the fault line based on the first voltage traveling wave line mode component, data preparation is provided for the subsequent acquisition of the first overlapping wave head and the second overlapping wave head; by calculating the relationship eigenvalue between the first overlapping wave head and the second overlapping wave head, data support is provided for the subsequent fault location through a preset neural network model, and the relationship eigenvalue is used as the input value of the neural network model to avoid the traditional The problem of wave velocity normalization required in the two-terminal traveling wave method; the distance to the fault point is obtained by the neural network model based on the relationship characteristic value and the upstream and downstream time difference of the fault point. In the traditional two-terminal traveling wave method, strict time synchronization and wave velocity normalization are required, but the traveling wave propagation speed is affected by the actual physical parameters of the line (such as conductor type, insulation medium, and aging degree), and there is a problem of unstable wave velocity, making time synchronization and wave velocity normalization difficult to fully achieve, so that the error of the final fault location result is relatively large. The present invention uses the relationship characteristic and the upstream and downstream time difference of the fault point as the input value of the neural network model, avoiding the problem of needing time synchronization and wave velocity normalization. Therefore, compared with the existing technology, the present invention can improve the accuracy of distribution network fault location.

[0012] Furthermore, the first voltage traveling wave line mode components at both ends of the fault line are obtained respectively according to the first voltage traveling wave data, specifically:

[0013] Karenbauer transformation is performed on the first voltage traveling wave data respectively to obtain first voltage traveling wave line mode components corresponding to both ends of the fault line.

[0014] In the embodiment of the present invention, the first voltage traveling wave line mode components at both ends of the fault line are respectively obtained according to the first voltage traveling wave data, thereby providing data support for the subsequent acquisition of the first wave head time series.

[0015] Furthermore, the wavelet transform is performed on the line mode components of the first voltage traveling wave to obtain time domain waveforms of different layers, specifically:

[0016] The first voltage traveling wave line mode components are respectively subjected to wavelet transformation to obtain high frequency coefficients of different frequency bands, and the corresponding first voltage traveling wave line mode components are reconstructed according to the high frequency coefficients to obtain time domain waveforms of different layers at both ends of the fault line.

[0017] In the embodiment of the present invention, wavelet transform is performed on the first voltage traveling wave line mode components respectively to obtain time domain waveforms of different layers, thereby providing data preparation for subsequent acquisition of the first wave head time series at both ends of the fault line.

[0018] Furthermore, the first wave head time series at both ends of the fault line are obtained respectively according to the time domain waveform diagram, specifically:

[0019] Taking the maximum modulus value of each layer in the time domain waveform respectively, and setting the modulus value that is less than a preset percentage of the maximum modulus value to 0;

[0020] The points with non-zero modulus values ​​and their corresponding time coordinates are extracted to construct the first wave head time series at both ends of the fault line.

[0021] In the embodiment of the present invention, by setting the modulus values ​​that are less than a preset percentage of the maximum modulus value to 0, the first wave head time series at both ends of the fault line are constructed respectively, thereby avoiding noise interference and improving the accuracy of subsequent fault location.

[0022] Furthermore, the first overlapping wave head and the second overlapping wave head are obtained according to the time series of the first wave heads at both ends of the fault line, specifically:

[0023] extracting the first wave head in the first wave head time series at both ends of the fault line respectively, aligning the first wave heads by time shifting to obtain a first overlapping wave head;

[0024] Continue searching backward according to the time coordinate, extract the wave head that is aligned again, and obtain the second overlapping wave head.

[0025] The embodiment of the present invention provides data preparation for subsequent relationship eigenvalue calculation by obtaining the first overlapping wave head and the second overlapping wave head.

[0026] Furthermore, the relationship characteristic values ​​between the first overlapping wave head and the second overlapping wave head include the modulus ratio between the first wave heads at both ends of the fault line, the modulus ratio between the re-aligned wave heads, and the time difference between the time coordinates corresponding to the first overlapping wave head and the time coordinates corresponding to the second overlapping wave head.

[0027] The embodiment of the present invention uses rich and multi-dimensional relationship feature values ​​as input values ​​of the neural network model to improve the accuracy of the fault location result.

[0028] Furthermore, the upstream and downstream time difference of the fault point is obtained according to the recording file, specifically:

[0029] respectively obtaining the initial recording moments of the recording files, and performing absolute zero time alignment on the recording data in the respective recording files according to the initial recording moments;

[0030] extracting second voltage traveling wave data at both ends of the fault line within a preset time period before and after the absolute zero moment, respectively, to obtain second voltage traveling wave line mode components at both ends of the fault line according to the second voltage traveling wave data;

[0031] Performing wavelet transform on the second voltage traveling wave line mode components respectively to obtain second time domain waveforms of different layers, and obtaining second wave head time series at both ends of the fault line respectively based on the second time domain waveforms;

[0032] Find the initial wave head of the second wave head time series respectively, and calculate the time from the corresponding moment of the initial wave head to the respective initial recording moments to obtain the upstream initial wave head time and the downstream initial wave head time;

[0033] The absolute value of the difference between the upstream initial wave front time and the downstream initial wave front time is taken, and the absolute value is used as the upstream and downstream time difference of the fault point.

[0034] The embodiment of the present invention calculates the upstream and downstream time difference of the fault point and inputs the upstream and downstream time difference of the fault point into the neural network model, thereby further improving the accuracy of the fault distance output by the neural network model.

[0035] In a second aspect, an embodiment of the present invention provides a distribution network fault location device based on double-end positioning, comprising a relative zero time acquisition module, a first voltage traveling wave line mode component module, a first wave head time series module, a relationship characteristic value module, an upstream and downstream time difference module, and a fault point distance acquisition module, wherein:

[0036] The relative zero time acquisition module is used to obtain the recording files of the double-end positioning devices at both ends of the fault line, and extract the starting time marks of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line;

[0037] The first voltage traveling wave line mode component module is used to align the relative zero time and respectively extract the first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data;

[0038] The first wave head time series module is used to perform wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtain first wave head time series at both ends of the fault line respectively according to the first time domain waveforms;

[0039] The relationship characteristic value module is used to obtain a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculate the relationship characteristic value between the first overlapping wave head and the second overlapping wave head;

[0040] The fault point distance acquisition module is used to input the relationship characteristic value and the upstream and downstream time difference of the fault point into a preset neural network model, output the fault point distance, and locate the distribution network fault based on the fault point distance; wherein the upstream and downstream time difference of the fault point is obtained based on the recording file.

[0041] In the embodiment of the present invention, the relative zero time of the fault recording data in the recording file is obtained through the relative zero time acquisition module, providing data support for the subsequent relative zero time alignment; the first voltage traveling wave line mode component module is used to respectively obtain the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data, providing data support for the subsequent search for overlapping wave heads; the first wave head time series module is used to respectively obtain the first wave head time series at both ends of the fault line, providing data preparation for the subsequent calculation of the relationship eigenvalue; the relationship eigenvalue between the first overlapping wave head and the second overlapping wave head is calculated through the relationship eigenvalue module, providing rich and comprehensive input values ​​for the subsequent neural network model to improve the model output results. Accuracy; through the fault point distance acquisition module, the relationship characteristic value and the upstream and downstream time difference of the fault point are input into a preset neural network model to locate the distribution network fault. In the traditional two-terminal traveling wave method, strict time synchronization and wave velocity normalization are required to obtain wave velocity parameters and calculate the time difference. However, due to the influence of irresistible external factors such as line aging on actual transmission lines, it is difficult to accurately obtain wave velocity parameters, which affects the accuracy of the final fault location result. The present invention uses the relationship characteristic value obtained by relative zero time alignment and the upstream and downstream time difference of the fault point as model input data, thereby avoiding the problem of difficulty in accurately obtaining wave velocity parameters in the existing technology, thereby improving the accuracy of distribution network fault location.

[0042] In a third aspect, an embodiment of the present invention provides a terminal device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0043] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the distribution network fault location method based on double-terminal positioning as described in any one of the above.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device / apparatus where the computer-readable storage medium is located is controlled to execute the distribution network fault location method based on double-end positioning as described in any one of the above.

[0045] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to more clearly understand the technical means of the embodiments of the present invention, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a distribution network fault location method based on double-end positioning provided by an embodiment of the present invention;

[0047] Figure 2 A 10kV single-ended radial distribution network simulation model for verifying the embodiments of the present invention;

[0048] Figure 3 A structural diagram of a distribution network fault location device based on double-end positioning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] Example 1:

[0051] like Figure 1 As shown, a distribution network fault location method based on double-end positioning provided by an embodiment of the present invention includes the following steps:

[0052] S11, obtaining the recording files of the dual-end positioning devices at both ends of the fault line, and extracting the start time stamps of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line;

[0053] S12, aligning the relative zero time, and respectively extracting first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data;

[0054] S13, performing wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtaining first wave head time series at both ends of the fault line respectively based on the first time domain waveforms;

[0055] S14, obtaining a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculating a relationship characteristic value between the first overlapping wave head and the second overlapping wave head;

[0056] S15, input the relationship characteristic value and the upstream and downstream time difference of the fault point into a preset neural network model, output the fault point distance, and locate the distribution network fault based on the fault point distance; wherein, the upstream and downstream time difference of the fault point is obtained based on the recording file.

[0057] In the specific implementation, the time when the two ends of the traveling wave emitted from the fault point arrive at the monitoring point is defined as time 0. However, after the actual fault occurs, the double-end positioning device starts the fault recording at an inconsistent time because the fault current at both ends is inconsistent. It is necessary to combine the start time stamp of the recording file to align the relative zero time at both ends.

[0058] Preferably, the extracting of the first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time is, in this embodiment, specifically: intercepting a voltage traveling wave data window within 5ms near the zero point of the fault.

[0059] In this embodiment, the first voltage traveling wave line mode components at both ends of the fault line are obtained respectively according to the first voltage traveling wave data, specifically: the first voltage traveling wave data are subjected to Karenbauer transformation respectively to obtain the first voltage traveling wave line mode components corresponding to both ends of the fault line.

[0060] In this embodiment, the first voltage traveling wave line mode components are respectively subjected to wavelet transform to obtain time domain waveform diagrams of different layers. Specifically, the first voltage traveling wave line mode components are respectively subjected to wavelet transform to obtain high frequency coefficients of different frequency bands, and the corresponding first voltage traveling wave line mode components are reconstructed according to the high frequency coefficients to obtain time domain waveform diagrams of different layers at both ends of the fault line.

[0061] In the specific implementation, the collected voltage traveling wave line mode components are decomposed by 8 layers through Haar wavelet transform (Haar wavelet transform) to obtain high frequency coefficients of different frequency bands, and then reconstructed to obtain time domain waveforms of different layers.

[0062] In this embodiment, the first wave head time series at both ends of the fault line are obtained based on the time domain waveform diagram. Specifically, the maximum modulus value of each layer in the time domain waveform diagram is obtained, and the modulus values ​​that are less than a preset percentage of the maximum modulus value are set to 0; and the points with non-zero modulus values ​​and the corresponding time coordinates are extracted to respectively construct the first wave head time series at both ends of the fault line.

[0063] In a specific implementation, in order to reduce the communication volume of the dual-end positioning device, the maximum modulus of each layer is calculated for the waveform of the layer, and the data below 10% of the maximum value is set to 0. Then, the points that are not 0 and their corresponding time coordinates are transmitted to the other end as a two-dimensional matrix sequence; wherein, the two-dimensional matrix sequence is the first wave head time sequence.

[0064] It should be noted that the core of fault location lies in finding the fault wave head. The amplitude of the wave head at both ends of the fault is affected by the fault angle, fault resistance, and branch nodes. Sometimes it is impossible to find a clear wave head in the first layer of the wavelet transform, so it is necessary to continue searching in the lower frequency bands. Secondly, the noise of the recording device is relatively large. In order to prevent misjudgment of the wave head, less than 10% of the modulus maximum value of each layer is considered to be noise. Two processing measures can ensure accurate locating of the fault wave head.

[0065] In this embodiment, the first overlapping wave head and the second overlapping wave head are obtained based on the first wave head time series at both ends of the fault line. Specifically, the first wave head in the first wave head time series at both ends of the fault line is extracted respectively, and the first wave heads are aligned by time shift to obtain the first overlapping wave head; and the search is continued backward according to the time coordinate to extract the wave heads that are aligned again to obtain the second overlapping wave head.

[0066] In the specific implementation, the first wave head time series of the line mode voltage at both ends of the fault section after reconstruction by high-frequency coefficients has an amplitude close to 0 before the fault occurs. After the fault occurs, an amplitude greater than 0 appears, which is called a wave head; the wave head that first appears in the sequences at both ends (i.e., the initial arrival time of the fault wave head) is aligned by time shifting, which is called the first overlapping wave head; after the time series at both ends are aligned to obtain the first overlapping wave head, the subsequent wave heads will automatically appear at the moment of re-alignment, among which the aligned head that appears again after the first overlapping wave head is called the second overlapping wave head.

[0067] In this embodiment, the relationship characteristic values ​​between the first overlapping wave head and the second overlapping wave head include the modulus ratio between the first wave heads at both ends of the fault line, the modulus ratio between the re-aligned wave heads, and the time difference between the time coordinates corresponding to the first overlapping wave head and the time coordinates corresponding to the second overlapping wave head.

[0068] It should be noted that the modulus ratio between the first wave heads at both ends of the fault line and the modulus ratio between the re-aligned wave heads are related to the distance from the fault point to the two ends, reflecting the attenuation relationship between the wave head amplitude and distance; the time difference between the time coordinate corresponding to the first overlapping wave head and the time coordinate corresponding to the second overlapping wave head is related to the distance from the fault point to the near measurement end and the wave velocity. The above relationship characteristic values ​​can reflect the fault distance information from different angles.

[0069] In this embodiment, the upstream and downstream time difference of the fault point is obtained according to the recording file, specifically: the initial recording moment of the recording file is obtained respectively, and the recording data in each recording file is aligned to the absolute zero moment according to the initial recording moment; the second voltage traveling wave data at both ends of the fault line in the preset time period before and after the absolute zero moment are extracted respectively, so as to obtain the second voltage traveling wave line mode components at both ends of the fault line according to the second voltage traveling wave data; the second voltage traveling wave line mode components are respectively subjected to wavelet transformation to obtain second time domain waveforms of different layers, and the second wave head time series at both ends of the fault line are respectively obtained according to the second time domain waveform; the initial wave head of the second wave head time series is respectively found, and the time from the corresponding moment of the initial wave head to the respective initial recording moments is respectively calculated to obtain the upstream initial wave head time and the downstream initial wave head time; the absolute value of the difference between the upstream initial wave head time and the downstream initial wave head time is taken, and the absolute value is used as the upstream and downstream time difference of the fault point.

[0070] It should be noted that the upstream and downstream time difference of the fault point is related to the distance from the fault point to the two ends and the wave velocity. The wave velocity parameter is replaced by the upstream and downstream time difference of the fault point, thereby avoiding the problem in the traditional two-end ranging method that the traveling wave propagation speed is affected by the line parameters (such as conductor type, insulation medium, and aging degree), resulting in unstable wave velocity, and ultimately making the fault location result obtained based on wave velocity calculation inaccurate.

[0071] In a specific implementation, the relationship characteristic value and the upstream and downstream time difference of the fault point are finally input into a preset neural network model to obtain the distance of the fault point.

[0072] Preferably, the embodiment of the present invention selects a PSO-BP neural network model (a back propagation neural network model optimized by a particle swarm algorithm) as the neural network model for outputting fault distances.

[0073] Preferably, the PSO-BP neural network model is constructed as follows: construct a PSO-BP neural network positioning model; initialize the weights and bias parameters of the particle swarm optimization algorithm in the PSO-BP model; set the maximum number of iterations to 50 and the learning rate to 0.99; input the compiled training set into the PSO-BP neural network model; and verify the positioning effect of the method proposed in this chapter using a test set of the PSO-BP neural network fault location model. If the positioning accuracy does not reach the expected threshold, modify the parameter settings and re-train until the positioning accuracy meets the requirements; wherein the preset threshold is 100m.

[0074] Preferably, the process for obtaining the organized training and test sets is as follows: a fault location model is constructed based on the actual distribution network system in simulation software; fault distance, fault type, fault location, and different fault lines are simulated as variables to obtain fault recording data; the calculated data is labeled with the actual fault distance as the corresponding sample; the fault voltage waveform within 5ms before and after the fault is extracted using a sampling frequency of 1MHz, and the extracted voltage traveling wave data is subjected to a Karenbauer transform to obtain its line-mode voltage traveling wave component, forming a sample set of the relationship characteristic value and the upstream and downstream time difference of the fault point that is easy to update and reuse. Finally, the sample set is divided into a training set and a test set in a ratio of 8:3.

[0075] The embodiment of the present invention aligns the fault recording data at both ends of the fault line by using the relative zero time, thereby providing data preparation for the subsequent acquisition of the first voltage traveling wave line mode component at both ends, and avoids the problem of strict synchronization of the time at both ends in the traditional two-end traveling wave method; by obtaining the first wave head time series at both ends of the fault line based on the first voltage traveling wave line mode component, data preparation is provided for the subsequent acquisition of the first overlapping wave head and the second overlapping wave head; by calculating the relationship eigenvalue between the first overlapping wave head and the second overlapping wave head, data support is provided for the subsequent fault location through a preset neural network model, and the relationship eigenvalue is used as the input value of the neural network model to avoid the traditional The problem of wave velocity normalization required in the two-terminal traveling wave method; the distance to the fault point is obtained by the neural network model based on the relationship characteristic value and the upstream and downstream time difference of the fault point. In the traditional two-terminal traveling wave method, strict time synchronization and wave velocity normalization are required, but the traveling wave propagation speed is affected by the actual physical parameters of the line (such as conductor type, insulation medium, and aging degree), and there is a problem of unstable wave velocity, making time synchronization and wave velocity normalization difficult to fully achieve, so that the error of the final fault location result is relatively large. The present invention uses the relationship characteristic and the upstream and downstream time difference of the fault point as the input value of the neural network model, avoiding the problem of needing time synchronization and wave velocity normalization. Therefore, compared with the existing technology, the present invention can improve the accuracy of distribution network fault location.

[0076] It should be noted that, in order to demonstrate the beneficial effects of the embodiments of the present invention, the present invention will provide some simulation experimental data as a reference. The specific simulation verification process is as follows:

[0077] like Figure 2 As shown in FIG, a 10 kV single-ended radial distribution network simulation model is used to verify the embodiment of the present invention.

[0078] In the specific implementation, some physical parameters set by the distribution network simulation model include: the bus voltage level is 10kV, the fault occurrence time is 0.098s; the sampling frequency is 1MHz, the line parameters are positive-sequence impedance: 0.482 (Ω / km); positive-sequence reactance 0.846 (Ω / km); positive-sequence admittance to ground 1.24e-5 (S / km); zero-sequence impedance: 0.923 (Ω / km); zero-sequence reactance: 4.74 (Ω / km); zero-sequence admittance to ground: 5.03e-6 (S / km), and the system simulation time is 0.1s.

[0079] Furthermore, a PSO-BP artificial neural network was constructed. Using wavelet transform, the modulus maximum ratios of the first overlapping voltage wave head (FCW) and the second overlapping voltage wave head (SCW) (i.e., the modulus ratio between the first wave head at both ends of the fault line and the modulus ratio between the re-aligned wave heads) were extracted, k1 and k2, respectively. The time difference t1 (the time difference between the time coordinates corresponding to the first overlapping wave head and the second overlapping wave head) and the time difference t2 (the time difference between the upstream and downstream time points of the fault point) between the first overlapping wave heads at both ends of the fault point were also extracted. These characteristics [k1, k2, t1, t2] were then used as the input features of the PSO artificial neural network. Eleven fault points were randomly located from 1 km from the busbar-side fault location device to the end of the line section. The fault type was a phase-to-ground fault, and the fault resistance was 10Ω.

[0080] In order to prove the applicability of the artificial neural network fault location model based on the particle swarm optimization algorithm, training and testing were carried out under different fault initial phase angles, different transition resistances and different fault locations. Figure 2 A single-phase grounding fault is set on line L6, with a transition resistance of 10Ω and initial fault phase angles of 10°, 30°, 45°, 70°, and 90°. The location results are shown in Table 1. The proposed method achieves accurate location under different initial fault phase angles, and the impact of different initial fault phase angles on fault location is minimal.

[0081] Table 1. Positioning results of different initial fault phase angles during interphase faults

[0082]

[0083] exist Figure 2In the example shown, a single-phase ground fault occurs on feeder L6, 4.6 km from terminal A. The initial fault phase angle is 30°, and the fault transition resistances are 0.01Ω, 1Ω, 10Ω, 100Ω, 300Ω, and 1000Ω, respectively. Simulation results show that the proposed method achieves high positioning accuracy for various transition resistances and is unaffected by the transition resistance, as shown in Table 2.

[0084] Table 2 Results of locating different fault resistances during single-phase faults

[0085]

[0086] exist Figure 1 As shown in the figure, training tests are conducted on different fault types, different fault sections, different fault feeder lengths, and different fault lines. The fault resistance is 10Ω, the initial fault phase angle is 30°, and the fault location results at different fault positions for single-phase grounding fault and interphase fault are shown in Table 3 and Table 4 respectively.

[0087] Table 3. Location results of different fault locations for single-phase grounding fault

[0088]

[0089] As shown in Table 3, the fault location error of this method is within 150m under different fault distances, different feeder lengths, and different fault lines. The simulation results show that for single-phase grounding faults, different fault locations have little effect on the proposed fault location method.

[0090] Table 4. Results of different fault location locations for phase-to-phase faults

[0091]

[0092] According to the data in Table 4, for phase-to-phase faults, the fault location errors are mostly below 150 m under different fault lines, different fault sections, and different fault distances, which shows a relatively satisfactory location result.

[0093] Example 2:

[0094] like Figure 3 As shown, this embodiment provides a distribution network fault location device based on double-end positioning, including a relative zero time acquisition module 001, a first voltage traveling wave line mode component module 002, a first wave head time series module 003, a relationship characteristic value module 004 and a fault point distance acquisition module 005, wherein,

[0095] The relative zero time acquisition module 001 is used to obtain the recording files of the double-end positioning devices at both ends of the fault line, and extract the start time stamps of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line;

[0096] The first voltage traveling wave line mode component module 002 is used to align the relative zero time and respectively extract the first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data;

[0097] The first wave head time series module 003 is used to perform wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtain first wave head time series at both ends of the fault line respectively according to the first time domain waveforms;

[0098] The relationship characteristic value module 004 is used to obtain a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculate the relationship characteristic value between the first overlapping wave head and the second overlapping wave head;

[0099] The fault point distance acquisition module 005 is used to input the relationship characteristic value and the upstream and downstream time difference of the fault point into a preset neural network model, output the fault point distance, and locate the distribution network fault based on the fault point distance; wherein the upstream and downstream time difference of the fault point is obtained based on the recording file.

[0100] In this embodiment, the first voltage traveling wave line mode component module 002 obtains the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data. Specifically, the first voltage traveling wave line mode component module 002 performs Karenbauer transformation on the first voltage traveling wave data to obtain the first voltage traveling wave line mode components corresponding to each end of the fault line.

[0101] In this embodiment, the first wave header time series module 003 performs wavelet transform on the first voltage traveling wave line mode components respectively to obtain time domain waveforms of different layers. Specifically, the first wave header time series module 003 performs wavelet transform on the first voltage traveling wave line mode components respectively to obtain high-frequency coefficients of different frequency bands, and reconstructs the corresponding first voltage traveling wave line mode components according to the high-frequency coefficients to obtain time domain waveforms of different layers at both ends of the fault line.

[0102] Furthermore, the first wave header time series module 003 obtains the first wave header time series at both ends of the fault line according to the time domain waveform diagram, specifically: the first wave header time series module 003 respectively obtains the maximum modulus value of each layer in the time domain waveform diagram, and sets the modulus value that is less than a preset percentage of the maximum modulus value to 0; extracts the points whose modulus value is not 0 and the corresponding time coordinates to respectively construct the first wave header time series at both ends of the fault line.

[0103] In this embodiment, the relationship feature value module 004 obtains the first overlapping wave head and the second overlapping wave head based on the first wave head time series at both ends of the fault line. Specifically, the relationship feature value module 004 extracts the first wave head in the first wave head time series at both ends of the fault line, aligns the first wave head by time shifting, and obtains the first overlapping wave head; and continues to search backward according to the time coordinate to extract the wave head that is aligned again to obtain the second overlapping wave head.

[0104] The more detailed working principle and process flow of this embodiment can be referred to, but not limited to, the relevant records of the first embodiment.

[0105] In the embodiment of the present invention, the relative zero time of the fault recording data in the recording file is obtained through the relative zero time acquisition module 001, so as to provide data support for the subsequent relative zero time alignment; the first voltage traveling wave line mode component module 002 is used to respectively obtain the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data, so as to provide data support for the subsequent search for overlapping wave heads; the first wave head time series module 003 is used to respectively obtain the first wave head time series at both ends of the fault line, so as to provide data preparation for the subsequent calculation of the relationship eigenvalue; the relationship eigenvalue between the first overlapping wave head and the second overlapping wave head is calculated through the relationship eigenvalue module 004, so as to provide rich and comprehensive input values ​​for the subsequent neural network model to improve the model. The accuracy of the output result of the model is improved; through the fault point distance acquisition module 005, the relationship characteristic value and the upstream and downstream time difference of the fault point are input into the preset neural network model to locate the distribution network fault. In the traditional two-terminal traveling wave method, strict time synchronization and wave velocity normalization are required to obtain wave velocity parameters and calculate the time difference. However, due to the influence of irresistible external factors such as line aging on actual transmission lines, it is difficult to accurately obtain wave velocity parameters, thereby affecting the accuracy of the final fault location result. The present invention uses the relationship characteristic value obtained by relative zero time alignment and the upstream and downstream time difference of the fault point as model input data, thereby avoiding the problem of difficulty in accurately obtaining wave velocity parameters in the existing technology, thereby improving the accuracy of distribution network fault location.

[0106] Example 3:

[0107] This embodiment provides a terminal device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0108] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the distribution network fault location method based on double-terminal positioning as described in any one of the above.

[0109] Example 4:

[0110] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the computer program is running, the device / apparatus where the computer-readable storage medium is located is controlled to execute the distribution network fault location method based on double-end positioning as described in any one of the above.

[0111] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-monitorable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0112] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A distribution network fault location method based on double-end positioning, characterized in that: include: Obtain the recording files of the double-end positioning devices at both ends of the fault line, and extract the start time stamps of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line; Aligning the relative zero time, and respectively extracting first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data; Performing wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtaining first wave head time series at both ends of the fault line respectively based on the first time domain waveforms; Obtaining a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculating a relationship characteristic value between the first overlapping wave head and the second overlapping wave head; The relationship characteristic value and the time difference between the upstream and downstream of the fault point are input into a preset neural network model, the fault point distance is output, and the distribution network fault is located based on the fault point distance; wherein, the time difference between the upstream and downstream of the fault point is obtained based on the recording file.

2. A distribution network fault location method based on double-end positioning according to claim 1, characterized in that: The obtaining of the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data is specifically as follows: Karenbauer transformation is performed on the first voltage traveling wave data respectively to obtain first voltage traveling wave line mode components corresponding to both ends of the fault line.

3. A distribution network fault location method based on double-end positioning according to claim 1, characterized in that: The wavelet transform is performed on the first voltage traveling wave line mode components respectively to obtain time domain waveforms of different layers, specifically: The first voltage traveling wave line mode components are respectively subjected to wavelet transformation to obtain high frequency coefficients of different frequency bands, and the corresponding first voltage traveling wave line mode components are reconstructed according to the high frequency coefficients to obtain time domain waveforms of different layers at both ends of the fault line.

4. A distribution network fault location method based on double-end positioning according to claim 1, characterized in that: The first wave head time series at both ends of the fault line are obtained according to the time domain waveform diagram, specifically: Taking the maximum modulus value of each layer in the time domain waveform respectively, and setting the modulus value that is less than a preset percentage of the maximum modulus value to 0; The points with non-zero modulus values ​​and their corresponding time coordinates are extracted to construct the first wave head time series at both ends of the fault line.

5. A distribution network fault location method based on double-end positioning according to claim 4, characterized in that: The step of obtaining the first overlapping wave head and the second overlapping wave head according to the first wave head time series at both ends of the fault line is specifically as follows: extracting the first wave head in the first wave head time series at both ends of the fault line respectively, aligning the first wave heads by time shifting to obtain a first overlapping wave head; Continue searching backward according to the time coordinate, extract the wave head that is aligned again, and obtain the second overlapping wave head.

6. A distribution network fault location method based on double-end positioning according to claim 5, characterized in that: The relationship characteristic values ​​between the first overlapping wave head and the second overlapping wave head include the modulus ratio between the first wave heads at both ends of the fault line, the modulus ratio between the re-aligned wave heads, and the time difference between the time coordinates corresponding to the first overlapping wave head and the time coordinates corresponding to the second overlapping wave head.

7. A distribution network fault location method based on double-end positioning according to claim 1, characterized in that: The time difference between upstream and downstream of the fault point is obtained according to the recording file, specifically: respectively obtaining the initial recording moments of the recording files, and performing absolute zero time alignment on the recording data in the respective recording files according to the initial recording moments; extracting second voltage traveling wave data at both ends of the fault line within a preset time period before and after the absolute zero moment, respectively, to obtain second voltage traveling wave line mode components at both ends of the fault line according to the second voltage traveling wave data; Performing wavelet transform on the second voltage traveling wave line mode components respectively to obtain second time domain waveforms of different layers, and obtaining second wave head time series at both ends of the fault line respectively based on the second time domain waveforms; Find the initial wave head of the second wave head time series respectively, and calculate the time from the corresponding moment of the initial wave head to the respective initial recording moments to obtain the upstream initial wave head time and the downstream initial wave head time; The absolute value of the difference between the upstream initial wave front time and the downstream initial wave front time is taken, and the absolute value is used as the upstream and downstream time difference of the fault point.

8. A distribution network fault location device based on double-end positioning, characterized in that: It includes a relative zero time acquisition module, a first voltage traveling wave line mode component module, a first wave head time series module, a relationship characteristic value module and a fault point distance acquisition module, wherein, The relative zero time acquisition module is used to obtain the recording files of the double-end positioning devices at both ends of the fault line, and extract the starting time marks of the two recording files respectively to obtain the relative zero time when the fault recording is started at both ends of the fault line; The first voltage traveling wave line mode component module is used to align the relative zero time and respectively extract the first voltage traveling wave data at both ends of the fault line within a preset time period before and after the relative zero time, so as to respectively obtain the first voltage traveling wave line mode components at both ends of the fault line according to the first voltage traveling wave data; The first wave head time series module is used to perform wavelet transform on the first voltage traveling wave line mode components respectively to obtain first time domain waveforms of different layers, and obtain first wave head time series at both ends of the fault line respectively according to the first time domain waveforms; The relationship characteristic value module is used to obtain a first overlapping wave head and a second overlapping wave head according to the first wave head time series at both ends of the fault line, and calculate the relationship characteristic value between the first overlapping wave head and the second overlapping wave head; The fault point distance acquisition module is used to input the relationship characteristic value and the upstream and downstream time difference of the fault point into a preset neural network model, output the fault point distance, and locate the distribution network fault based on the fault point distance; wherein the upstream and downstream time difference of the fault point is obtained based on the recording file.

9. A terminal device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the distribution network fault location method based on double-terminal positioning according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device / apparatus where the computer-readable storage medium is located is controlled to execute the distribution network fault location method based on double-end location according to any one of claims 1 to 7.

Images