Method for discriminating fault area of power transmission line containing T area and related equipment

Abstract

The embodiment of the invention discloses a T-region-containing power transmission line fault region discrimination method and related equipment, and the method comprises the steps: obtaining a first power break variable at the left side of a T region and a first power break variable at the right side of the T region, and obtaining a fault region of a DC power transmission line according to the first power break variable, a second power break variable and a preset discrimination method; the fault area comprises a left side fault outside the T area, a right side fault outside the T area and a fault inside the T area. The fault area is obtained according to the first power break variable and the second power break variable, identification of the fault area can be completed only by obtaining the power break variable and conducting simple judgment, transient traveling waves on the two sides of the T area can be prevented from being obtained, and therefore the requirement of the multi-end hybrid direct current transmission line is met.

Description

Technical field

[0001] The present invention relates to the field of transmission circuit fault identification, and in particular to a method for identifying a fault area of ​​a transmission line containing a T zone and related equipment. [Background Technology]

[0002] The rectifier side of a multi-terminal hybrid DC transmission line is bounded by smoothing reactors and DC filters, while the inverter side at the end of the line is bounded by smoothing reactors. These asymmetric line boundaries are also evident due to the presence of a special T-zone busbar structure between parallel multi-terminal DC lines. This leads to significant differences in transient characteristics compared to flexible DC grids. Furthermore, the T-zone lacks the current-limiting reactor boundaries common to DC grids. This makes it difficult to identify transient traveling waves on both sides of the T-zone, making existing protection methods unsuitable for the requirements of multi-terminal hybrid DC transmission lines. [Summary of the invention]

[0003] In view of this, the present invention provides a method for determining a fault area of ​​a power transmission line including a T zone and related equipment.

[0004] The specific technical solution of the first embodiment of the present invention is: a method for determining the fault area of ​​a transmission line containing a T zone, applied to a DC transmission line, the method comprising: obtaining a first power mutation amount on the left side of the T zone and a first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar; the fault area of ​​the DC transmission line is obtained based on the first power mutation amount, the second power mutation amount and a preset determination method; the fault area includes a fault on the left side outside the T zone, a fault on the right side outside the T zone, and a fault within the T zone.

[0005] Preferably, obtaining the fault area of ​​the DC transmission line according to the first power mutation amount, the second power mutation amount and a preset judgment method includes: obtaining the fault area of ​​the DC transmission line according to the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount.

[0006] Preferably, the obtaining of the fault area of ​​the DC transmission line according to the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount includes: when the first power mutation amount is positive and the second power mutation amount is positive, the fault area is a left fault outside the T zone; when the first power mutation amount is negative and the second power mutation amount is negative, the fault area is a right fault outside the T zone; when the first power mutation amount is negative and the second power mutation amount is positive, the fault area is a fault inside the T zone.

[0007] Preferably, obtaining the first power mutation amount on the left side of the T zone and the first power mutation amount on the right side of the T zone includes: obtaining a first voltage mutation amount and a first current mutation amount on the left side of the T zone, and obtaining a second voltage mutation amount and a second current mutation amount on the right side of the T zone; obtaining the first power mutation amount according to the first voltage mutation amount and the first current mutation amount; and obtaining the second power mutation amount according to the second voltage mutation amount and the second current mutation amount.

[0008] Preferably, after obtaining the fault area of ​​the DC transmission line, the method further includes: inputting the first power mutation amount and the second power mutation amount into a preset model to obtain a fault result of the fault area; the fault result includes the distance from the fault point to the T zone.

[0009] Preferably, the preset model is trained in the following manner: obtaining the distances from different preset fault points to the T zone, and the power mutation amounts corresponding to different preset fault points; using the distances from the different preset fault points to the T zone and the power mutation amounts corresponding to the different preset fault points to train the preset model; obtaining the prediction result of the preset model; judging whether the accuracy of the prediction result is greater than a preset threshold; if the accuracy is not greater than the preset threshold, obtaining the distances from untrained preset fault points to the T zone, and the power mutation amounts corresponding to untrained preset fault points to train the preset model, until the prediction result is greater than the preset threshold, the training of the preset model is completed.

[0010] Preferably, the first power mutation amount and the second power mutation amount are input into a preset model to obtain the fault result of the fault area, including: performing data preprocessing, feature extraction and fusion, and weighting the first mutation amount and the second mutation amount with an attention mechanism, and then inputting them into the preset model to obtain the fault result.

[0011] The specific technical solution of the second embodiment of the present invention is: a transmission line fault area determination system containing a T zone, the system comprising: a power mutation amount acquisition module and a fault output module; the power mutation amount acquisition module is used to obtain a first power mutation amount on the left side of the T zone and a first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar; the fault output module is used to obtain the fault area of ​​the DC transmission line according to the first power mutation amount, the second power mutation amount and a preset determination method; the fault area includes a left-side fault outside the T zone, a right-side fault outside the T zone and a fault within the T zone.

[0012] The specific technical solution of the third embodiment of the present invention is: a transmission line fault area determination device containing a T zone, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method as described in any one of the first embodiments of the present application.

[0013] The specific technical solution of the fourth embodiment of the present invention is: a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the method described in any one of the first embodiments of the present application.

[0014] The implementation of the present invention will have the following beneficial effects:

[0015] The present invention obtains a first power mutation on the left side of the T zone and a first power mutation on the right side of the T zone. Based on the first and second power mutations and a preset identification method, the fault area of ​​the DC transmission line is determined. The fault area includes faults outside the left side of the T zone, faults outside the right side of the T zone, and faults within the T zone. By determining the fault area based on the first and second power mutations, fault identification can be completed by simply obtaining the power mutations and performing a simple determination. This avoids obtaining transient traveling waves on both sides of the T zone, thus meeting the requirements of multi-terminal hybrid DC transmission lines.

Brief Description of the Drawings

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A flow chart of the steps of a method for determining a fault area of ​​a transmission line including a T zone;

[0018] Figure 2 This is the topological structure diagram of the UHV three-section hybrid DC system;

[0019] Figure 3 is the equivalent circuit of the DC line fault on the left side outside the T area;

[0020] Figure 4 is the equivalent circuit of the DC line fault on the right side outside the T area;

[0021] Figure 5 is the equivalent circuit of the fault in the T area;

[0022] Figure 6aSchematic diagram of the change curve of the training set loss value;

[0023] Figure 6b Schematic diagram of the training set accuracy change curve;

[0024] Figure 7 This is a structural diagram of the model in this application;

[0025] Figure 8 This is a schematic diagram of the structure of a transmission line fault area identification system including a T zone;

[0026] Among them, 201 is a power mutation amount acquisition module; 202 is a fault output module. [Specific implementation method]

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The terms "first," "second," and the like in the specification, claims, and drawings of this application are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules is not limited to the listed steps or modules but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or apparatus.

[0029] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] See also Figure 1 , is a flowchart of the steps of a method for determining a fault area of ​​a transmission line including a T zone in the first embodiment of the present application. This method can avoid obtaining transient traveling waves on both sides of the T zone, thereby meeting the requirements of a multi-terminal hybrid DC transmission line. The method includes:

[0031] Step 101: Obtain a first power mutation amount on the left side of a T zone and a first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar;

[0032] Step 102: Obtain a fault area of ​​the DC transmission line according to the first power mutation amount, the second power mutation amount, and a preset judgment method; the fault area includes a left fault outside the T zone, a right fault outside the T zone, and a fault inside the T zone.

[0033] For details, please refer to Figure 2 Figure 2 shows the topology of a UHV three-section hybrid DC system. Unlike two-terminal DC transmission lines, parallel three-terminal hybrid DC transmission lines have a T-zone. The fault current change information at the three terminals of the T-connected busbar after a fault can provide a basis for formulating protection strategies. This paper uses the power mutation as a direction criterion. Taking the positive pole of a UHV three-terminal hybrid DC transmission system as an example, it is defined that the current direction during normal operation is positive. The current mutation is positive when the fault current is in the same direction as the normal operating current and the increment is positive. It is negative when the fault current is in the same direction as the normal operating current and the increment is negative. It is negative when the fault current is in the opposite direction to the normal operating current and the increment is positive. The voltage positive direction is defined as the positive line-to-ground voltage direction. The voltage mutation is positive when the voltage increment is positive and negative when the voltage increment is negative. The power mutation amount is the product of the voltage mutation amount and the current mutation amount. If the product of the voltage mutation amount and the current mutation amount is positive, the power mutation amount is positive. If the product of the voltage mutation amount and the current mutation amount is negative, the power mutation amount is negative. The fault area of ​​the DC transmission line is obtained according to the first power mutation amount, the second power mutation amount and the preset judgment method.

[0034] The method in this embodiment obtains a first power mutation amount on the left side of the T zone and a first power mutation amount on the right side of the T zone. Based on the first and second power mutation amounts and a preset identification method, the fault area of ​​the DC transmission line is determined. The fault area includes faults outside the left side of the T zone, faults outside the right side of the T zone, and faults within the T zone. By determining the fault area based on the first and second power mutation amounts, fault identification can be completed by simply obtaining the power mutation amounts and performing a simple determination. This avoids obtaining transient traveling waves on both sides of the T zone, thus meeting the requirements of multi-terminal hybrid DC transmission lines.

[0035] In a specific embodiment, determining the fault area of ​​the DC transmission line based on the first power mutation amount, the second power mutation amount, and a preset identification method includes determining the fault area of ​​the DC transmission line based on the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount. Specifically, the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount are associated with different fault points, and thus the fault area can be determined based on the positive and negative values ​​of the mutation amounts.

[0036] In a specific embodiment, the obtaining of the fault area of ​​the DC transmission line according to the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount includes: when the first power mutation amount is positive and the second power mutation amount is positive, the fault area is a left fault outside the T zone; when the first power mutation amount is negative and the second power mutation amount is negative, the fault area is a right fault outside the T zone; when the first power mutation amount is negative and the second power mutation amount is positive, the fault area is a fault inside the T zone.

[0037] Specifically, when a metallic ground fault occurs in the left line outside the T zone, the right line outside the T zone, or inside the T zone, the fault equivalent circuits are as follows: Figure 3 、 Figure 4 、 Figure 5 As shown. f is the equivalent fault voltage source, L1 and L2 represent the lines, L d is the smoothing reactor, Z1 and Z2 are the equivalent impedance of the line, and Z conv is the equivalent impedance of the converter in the T zone.

[0038] Specifically, when a metal grounding fault occurs on the left DC line L1 outside the T zone, the equivalent circuit of the DC line fault is as follows: Figure 3 As shown. Figure 3 Available in U f Under the action of , the flow direction of the current mutation ΔI1 is opposite to the specified positive direction and the increment is positive, so ΔI1<0; similarly, ΔI2<0; since the fault is a ground fault, the voltage increment is negative, so ΔU1<0, ΔU2<0. Therefore, the power mutation on the left and right sides of the T zone are both positive, that is, ΔP L1 >0,ΔP L2 >0.

[0039] Specifically, when a metal grounding fault occurs on the right DC line L2 outside the T zone, the equivalent circuit of the DC line fault is as follows: Figure 4 As shown. Figure 4It can be seen that the direction of the current mutation ΔI1 is the same as the specified positive direction and the increment is positive, so ΔI1>0; similarly, ΔI2>0; since the fault is a ground fault, the voltage increment is negative, so the voltage mutation ΔU1<0, ΔU2<0. Therefore, the power mutation on the left and right sides of the T zone are both negative, that is, ΔP L1 <0, ΔP L2 <0.

[0040] Specifically, when a metal ground fault occurs in the T zone, the equivalent circuit of the DC line fault is as follows: Figure 5 As shown. Figure 5 It can be seen that the direction of the current mutation ΔI1 is the same as the specified positive direction and the increment is positive, so ΔI1>0; the current mutation ΔI2 flowing through the right side of the T area is opposite to the specified positive direction and the increment is positive, so ΔI2<0; the increments of ΔU1 and ΔU2 are both negative, so ΔU1<0 and ΔU2<0. Therefore, the power mutations on the left and right sides of the T area are one negative and one positive, that is

[0041] In summary, the fault direction criterion in the T zone is as follows: ΔP i =ΔU m ×ΔI m (i=L1,L2;m=1,2)(1)

[0042] when and When the fault occurs on the left side outside the T zone, and When the fault occurs on the right side outside the T zone, and There is a fault in the T zone.

[0043] Analysis of fault area characteristics inside and outside the DC line area on the LCC side:

[0044] For line L1, after determining that the fault is located outside the left side of the T zone according to the above direction criterion, it is also necessary to determine whether the fault is located outside or inside the rectifier side zone. Figure 3 It can be seen that for the fault outside the rectifier side and the fault inside the rectifier side, the flow direction of the current mutation ΔI1 is opposite to the specified positive direction and the increment is positive, ΔI1<0. Since the fault is a ground fault, the voltage increment is negative, so the power mutation ΔP L1 >0, it can be seen that the faults inside and outside the DC line area on the LCC side cannot be distinguished based on the positive and negative values ​​of the power mutation amount alone.

[0045] like Figure 2As shown in the figure, the presence of a DC filter and smoothing reactor between the headend of DC line L1 and the outside zone together form the boundary element between the inside and outside zones of line L1. This boundary strongly attenuates the high-frequency components of both the transient voltage and current of the fault. Consequently, there are significant differences in the magnitude of voltage and current mutations inside and outside the zone, leading to significant differences in the magnitude of power mutations inside and outside the zone. This difference in power mutations detected by M1 can be used to distinguish between faults inside and outside the DC line zone on the LCC side.

[0046] Analysis of fault area characteristics inside and outside the DC line area on the MMC2 side:

[0047] For line L2, after determining that the fault is located outside the right side of the T zone according to the above-mentioned direction criterion, it is also necessary to determine whether the fault is located outside or inside the MMC2 side zone. Figure 4 It can be seen that for the fault outside the zone and the fault inside the zone on the MMC2 side, the flow direction of the current mutation ΔI2 is the same as the specified positive direction and the increment is positive, ΔI2>0. Since the fault is a ground fault, the voltage increment is negative, so the power mutation It can be seen that it is impossible to distinguish between internal and external faults in the DC line area on the MMC2 side based only on the positive and negative values ​​of the power mutation.

[0048] like Figure 2 As shown in the figure, the presence of a smoothing reactor between the end zone of DC line L2 and the outside zone forms the boundary element between the inside and outside zones of line L2. This boundary strongly attenuates the high-frequency components of both the transient voltage and current of the fault. Consequently, there are significant differences in the magnitude of voltage and current surges inside and outside the zone, leading to significant differences in the magnitude of power surges inside and outside the zone. This difference in power surges detected by M2 can be used to distinguish between faults inside and outside the DC line zone on the MMC2 side.

[0049] In a specific embodiment, the obtaining of the first power mutation amount on the left side of the T zone and the first power mutation amount on the right side of the T zone includes: obtaining a first voltage mutation amount and a first current mutation amount on the left side of the T zone, and obtaining a second voltage mutation amount and a second current mutation amount on the right side of the T zone; obtaining the first power mutation amount according to the first voltage mutation amount and the first current mutation amount; obtaining the second power mutation amount according to the second voltage mutation amount and the second current mutation amount. Specifically, ΔU m (m=1,2) is the voltage mutation amount at the measurement point, ΔI m (m=1,2,3) is the current mutation amount. The power mutation amount is the product of the voltage mutation amount and the current mutation amount.

[0050] Right now

[0051] ΔP i =ΔU m ×ΔI m(i=L1,L2;m=1,2) (2)

[0052] In a specific embodiment, after obtaining the fault area of ​​the DC transmission line, the method further includes: inputting the first power mutation amount and the second power mutation amount into a preset model to obtain a fault result of the fault area; the fault result includes the distance from the fault point to the T zone.

[0053] Specifically, after determining the fault area, the obtained power mutation amount can be input into a preset model to identify the exact fault point.

[0054] In a specific embodiment, the preset model is trained in the following manner: obtaining the distances from different preset fault points to the T zone and the power mutation amounts corresponding to the different preset fault points; training the preset model using the distances from the different preset fault points to the T zone and the power mutation amounts corresponding to the different preset fault points; obtaining the prediction results of the preset model; determining whether the accuracy of the prediction results is greater than a preset threshold; if the accuracy is not greater than the preset threshold, obtaining the distances from untrained preset fault points to the T zone and the power mutation amounts corresponding to the untrained preset fault points to train the preset model until the prediction results are greater than the preset threshold, completing the training of the preset model. Specifically, by iteratively training the preset model using multiple sets of different power mutation amounts and distances from the fault point to the T zone, the accuracy of the model prediction results is ensured.

[0055] In a specific embodiment, the first power mutation amount and the second power mutation amount are input into a preset model to obtain the fault result of the fault area, including: performing data preprocessing, feature extraction and fusion, and weighting the first mutation amount and the second mutation amount with an attention mechanism, and then inputting them into the preset model to obtain the fault result.

[0056] Specifically, a UHV three-terminal hybrid DC transmission model was established in PSCAD. Transient current and voltage data from the protection devices on the left and right sides of the T-zone were collected. To maximize the differences in fault characteristics and improve network training accuracy, the data was denoised and standardized. The standardization process used was as follows:

[0057]

[0058] Where: P i is the sample data after standardization; is the original sample data.

[0059] Current and voltage data were converted into power mutation data and used as input for the hybrid deep learning model for simulation, i.e., X = [P1, P2, P3, P4]. Fault sections were classified and their locations were labeled. The simulation data comprehensively considered faults in different areas (faults inside and outside the LCC line area, faults at the busbar in the T area, and faults inside and outside the MMC line area), different transition resistances (0.01 to 300 Ω), and different fault distances (0 to 908.4 km). A total of 254 data sets were collected, 224 of which were training sets and 30 were test sets. These data were then input into the CNN-BiLSTM-Attention hybrid deep learning model.

[0060] CNN and BiLSTM are used to extract both vertical and horizontal features of fault data. Based on these vertical features (Feature 1), BiLSTM is used to extract horizontal historical features (Feature 2) of the fault transient power mutation data. These two modules are cascaded to mine data from both vertical time points and horizontal time series perspectives, generating richer features.

[0061] 1) Use a CNN layer to extract features from the preprocessed power mutation data. Multiple convolution kernels are applied to the data to capture linear features, followed by activation functions to extract nonlinear features. The convolution kernels slide across the input sequence, capturing structural features of local patterns, such as sudden changes, peaks, or troughs. Pooling layers are then used to reduce the size of the feature map while retaining the most important information and reducing computational effort. These features are then superimposed to produce Feature 1.

[0062] The input signal is: X = [P1, P2, P3, P4], and the convolution kernel is used to perform convolution operation on the input signal.

[0063] a. Convolutional layer:

[0064]

[0065] In formula (4): * is the convolution operation; l is the number of convolution layers; j is the number of convolution kernels; is the jth eigenface eigenvector output by convolution; is the transient power mutation signal of the input characteristic surface; is the weight of the convolution kernel; is the weight bias; f r (z) is the activation function, and the sigmoid function is used here for activation.

[0066] b. Pooling layer: This layer is also called the downsampling layer. It further compresses and extracts the output of the previous layer (convolutional layer). Here, the maximum pooling extraction is used, as shown in formula (5):

[0067]

[0068] In formula (5): D j is the jth pooling area; is the output of the pooling layer; is the kth output using the maximum pooling method, that is, output feature 1.

[0069] 2) Use the BiLSTM layer to further process the features extracted by CNN. BiLSTM processes sequence data through two LSTM layers, forward and backward. The forward layer extracts the forward historical features of the fault in the time series, and the backward layer traces back the fault historical features from the reverse direction to learn the relationship between different time steps of the fault signal. After fusing the two features, feature 2 of the data is obtained.

[0070] For the BiLSTM network, the calculation process is as follows:

[0071]

[0072] In formula (6), the LSTM unit is the traditional LSTM network calculation process, x t is the input at time t, that is, the CNN layer extracts feature 1, is the forward hidden layer state, is the backward hidden layer state, W y 、b y are weight matrices and bias terms, y t is the hidden layer output at time t, that is, output feature 2.

[0073] The attention mechanism is introduced to perform weighted processing on the fused features. The weights are dynamically adjusted according to the importance of the features to select the features that are more critical for fault area identification. The weighted features are obtained using the Softmax function. The weighted sum is calculated based on the weights and the corresponding value vectors to achieve the final fault area classification output s t .

[0074] The input sequence is y = [y1, y2, ..., yt], and the process of calculating the weight is as follows:

[0075]

[0076] In formula (7): e t is the probability distribution; W h is the weight of Attention; b h is the deviation of Attention; v is the attention value; a t is the weight coefficient; s t is the output of the Attention layer at time t.

[0077] The feature extraction and fusion are combined with the weighted attention mechanism to form the CNN-BiLSTM-Attention model. By continuously comparing the set parameters with the model output effect, the optimal parameters of the CNN-BiLSTM-Attention model are obtained. The model is trained with 224 sets of collected data. The training results are as follows: Figure 6a and Figure 6b The deep learning model structure constructed in MATLAB is shown as follows. Figure 7 As shown. It mainly includes 1 input layer, 4 convolutional layers, 4 pooling layers, 2 BiLSTM layers, 1 attention layer and 1 output layer. Figure 6a and Figure 6b The data in the figure shows that after 150 iterations, the loss value of the model training set is about 0.1, and the accuracy of the training set is as high as 98.218%, showing good fault area discrimination performance.

[0078] In order to further prove that the constructed model has strong generalization ability, 30 sets of data (test sets) are used to simulate the actual fault identification scenario test. These 30 sets of data are input into the trained CNN-BiLSTM-Attention model to identify the fault area. The test results are shown in Table 1. 10 output results are designed, corresponding to the fault areas f1~f2 respectively. 10 , in order to identify the fault area.

[0079]

[0080] Table 1: Comparison table of model fault area identification results

[0081] In the specific embodiment, see Figure 8 , is a structural schematic diagram of a transmission line fault area determination system containing a T zone in the second embodiment of the present application, characterized in that the system includes: a power mutation amount acquisition module 201 and a fault output module 202; the power mutation amount acquisition module 201 is used to obtain a first power mutation amount on the left side of the T zone and a first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar; the fault output module 202 is used to obtain the fault area of ​​the DC transmission line according to the first power mutation amount, the second power mutation amount and a preset determination method; the fault area includes a left-side fault outside the T zone, a right-side fault outside the T zone, and a fault within the T zone.

[0082] The system in this embodiment obtains a first power mutation on the left side of the T zone and a first power mutation on the right side of the T zone. Based on the first and second power mutations and a preset identification method, the system determines the fault area of ​​the DC transmission line. Fault areas include faults outside the left side of the T zone, faults outside the right side of the T zone, and faults within the T zone. By determining the fault area based on the first and second power mutations, fault identification is completed by simply obtaining the power mutations and performing a simple determination. This avoids the need to obtain transient traveling waves on both sides of the T zone, thus meeting the requirements of multi-terminal hybrid DC transmission lines.

[0083] In a specific embodiment, the third embodiment of the present application provides a transmission line fault area determination device containing a T zone, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method as described in any one of the first embodiments of the present application.

[0084] In a specific embodiment, the fourth embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor performs the steps of the method described in any one of the first embodiments of the present application.

[0085] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0086] The above description is merely a preferred embodiment of the present invention and does not constitute any other form of limitation to the present invention. Any person skilled in the art may utilize the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes for application in other fields. However, any simple modification, equivalent change, and modification of the above embodiments made in accordance with the technical essence of the present invention without departing from the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for identifying fault areas of a power transmission line containing a T zone, applied to a DC transmission line, characterized in that: The method comprises: Obtaining a first power mutation amount on the left side of the T zone and a first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar; The fault area of ​​the DC transmission line is obtained according to the first power mutation amount, the second power mutation amount and a preset judgment method; the fault area includes a left fault outside the T zone, a right fault outside the T zone and a fault inside the T zone.

2. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 1, characterized in that: The method of obtaining the fault area of ​​the new DC power transmission line according to the first power mutation amount, the second power mutation amount and a preset determination method includes: The fault area of ​​the DC transmission line is obtained according to the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount.

3. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 2, characterized in that: The obtaining of the fault area of ​​the DC transmission line according to the positive and negative values ​​of the first power mutation amount and the positive and negative values ​​of the second power mutation amount includes: When the first power mutation amount is a positive value and the second power mutation amount is a positive value, the fault area is a left fault outside the T area; When the first power mutation amount is a negative value and the second power mutation amount is a negative value, the fault area is a right side fault outside the T area; When the first power mutation amount is a negative value and the second power mutation amount is a positive value, the fault area is a fault within the T area.

4. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 1, characterized in that: The obtaining of the first power mutation amount on the left side of the T zone and the first power mutation amount on the right side of the T zone includes: Acquire a first voltage mutation amount and a first current mutation amount on the left side of the T zone, and acquire a second voltage mutation amount and a second current mutation amount on the right side of the T zone; Obtaining the first power mutation amount according to the first voltage mutation amount and the first current mutation amount; The second power mutation amount is obtained according to the second voltage mutation amount and the second current mutation amount.

5. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 1, characterized in that: After the fault area of ​​the DC transmission line is obtained, the method further includes: The first power mutation amount and the second power mutation amount are input into a preset model to obtain a fault result of the fault area; the fault result includes a distance from the fault point to the T zone.

6. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 5, characterized in that: The preset model is trained in the following way: Obtain the distances from different preset fault points to the T zone, and the power mutation amounts corresponding to different preset fault points; The preset model is trained using the distances from the different preset fault points to the T zone and the power mutation amounts corresponding to the different preset fault points; Obtaining the prediction result of the preset model; Determining whether the accuracy of the prediction result is greater than a preset threshold; If the accuracy is not greater than the preset threshold, the distance from the untrained preset fault point to the T zone and the power mutation amount corresponding to the untrained preset fault point are obtained to train the preset model until the prediction result is greater than the preset threshold, and the preset model training is completed.

7. The method for determining the fault area of ​​a power transmission line containing a T zone according to claim 5, characterized in that: The step of inputting the first power mutation amount and the second power mutation amount into a preset model to obtain a fault result of the fault area includes: The first mutation amount and the second mutation amount are subjected to data preprocessing, feature extraction and fusion, and weighted by an attention mechanism, and then input into the preset model to obtain the fault result.

8. A transmission line fault area identification system including T zone, characterized in that: The system comprises: a power mutation amount acquisition module and a fault output module; The power mutation amount acquisition module is used to acquire the first power mutation amount on the left side of the T zone and the first power mutation amount on the right side of the T zone; the left side of the T zone is the area between the sending-end rectifier-side converter station and the busbar; the right side of the T zone is the area between the receiving-end converter station and the busbar; The fault output module is used to obtain the fault area of ​​the DC transmission line according to the first power mutation amount, the second power mutation amount and a preset judgment method; the fault area includes a left side fault outside the T zone, a right side fault outside the T zone and a fault inside the T zone.

9. A device for determining a fault area of ​​a power transmission line including a T zone, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images