Line detection method and device, computer device and storage medium

Abstract

The application relates to a line detection method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining fault characteristic data corresponding to two-end fault positive sequence currents of a target line when a fault event occurs; determining a data sampling interval of the two-end positive sequence currents of the target line according to the fault characteristic data; sampling the current two-end positive sequence currents of the target line according to the data sampling interval to obtain first operation data; inputting the first operation data into a fault detection model to obtain a first detection result, wherein the fault detection model is obtained by training operation data of the target line in normal operation; when the first detection result is normal operation, performing difference calculation on the current two-end positive sequence currents of the target line to obtain second operation data; inputting the second operation data into the fault detection model to obtain a second detection result; and determining a target line detection result based on the first detection result and the second detection result. The method can effectively improve the line detection efficiency.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a line detection method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the increasing penetration rate of distributed power sources in distribution networks, the traditional three-stage overcurrent protection has the defect of insufficient selectivity and is no longer suitable for the current distribution network. Solving the line protection problems caused by the high proportion of distributed power sources connected to the grid has become increasingly important research value.

[0003] The existing technology is to directly cut off the distributed power supply when a fault occurs, which can maintain the structure of the original distribution network and basically does not require any changes to the original protection. It is low in cost, but the line detection efficiency is low. Summary of the Invention

[0004] Based on this, it is necessary to provide a line detection method, device, computer equipment and storage medium to address the above technical problems, which can effectively improve the efficiency of line detection.

[0005] A line detection method, comprising:

[0006] Obtain fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs;

[0007] Determine the data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data;

[0008] Sampling the current positive sequence current at both ends of the target line according to the data sampling interval to obtain first operating data;

[0009] Inputting first operating data into a fault detection model to obtain a first detection result, wherein the fault detection model is trained based on operating data of the target line during normal operation;

[0010] When the first detection result indicates normal operation, the second operation data is obtained by performing a difference calculation on the current positive sequence currents at both ends of the target line;

[0011] inputting the second operating data into the fault detection model to obtain a second detection result;

[0012] A target line detection result is determined based on the first detection result and the second detection result.

[0013] In one embodiment, determining the data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data includes:

[0014] Determine the phase difference of the fault positive sequence current at both ends of the target line when the fault event occurs based on the phase angle characteristics of the fault characteristic data;

[0015] The data sampling interval of the positive sequence current at both ends of the target line is determined according to the phase difference.

[0016] In one embodiment, sampling the current positive sequence current at both ends of the target line according to the data sampling interval to obtain the first operating data includes:

[0017] Collecting the current positive sequence current at the current inflow end of the target line to obtain first characteristic data;

[0018] After the first characteristic data is collected and a data sampling interval has passed, the current positive sequence current is collected at the current outflow end of the target line to obtain the second characteristic data;

[0019] First operating data is obtained according to the first characteristic data and the second characteristic data.

[0020] In one embodiment, before inputting the first operating data into the fault detection model to obtain the first detection result, the method further includes:

[0021] Obtain historical operating data of the target line under normal operating conditions;

[0022] The support vector data description model is trained based on historical operation data to obtain a fault detection model.

[0023] In one embodiment, after inputting the first operating data into the fault detection model and obtaining the first detection result, the method further includes:

[0024] When the first detection result is an operation abnormality, it is determined that the target line detection result of the target line is a target line fault.

[0025] In one embodiment, when the first detection result indicates normal operation, the second operation data is obtained by performing a difference calculation on the current positive sequence currents at both ends of the target line, including:

[0026] When the first detection result is normal operation, obtaining the corresponding sine wave amplitude and phase angle characteristics of the current positive sequence current at both ends of the target line;

[0027] Amplitude characteristic data is obtained by performing difference calculation based on the current sine wave amplitude of the positive sequence current at both ends of the target line;

[0028] Phase angle characteristic data is obtained by performing difference calculation based on the phase angle characteristics of the current positive sequence current at both ends of the target line;

[0029] The second operation data is obtained according to the amplitude characteristic data and the phase angle characteristic data.

[0030] In one embodiment, determining a target line detection result based on the first detection result and the second detection result includes:

[0031] When the first detection result indicates that the target line is operating abnormally, determining that the target line detection result is an operation fault;

[0032] When the first detection result indicates that the target line is operating normally and the second detection result indicates that the target line is operating normally, determining that the detection result of the target line is operating normally;

[0033] When the first detection result indicates that the target line is operating normally and the second detection result indicates that the target line is operating abnormally, it is determined that the detection result of the target line is an operation fault.

[0034] A line detection device, comprising:

[0035] An acquisition module is used to acquire fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; and determine a data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data;

[0036] a first calculation module, configured to sample the current positive sequence current at both ends of the target line according to a data sampling interval to obtain first operating data; and input the first operating data into a fault detection model to obtain a first detection result, wherein the fault detection model is trained based on the operating data of the target line during normal operation;

[0037] A second calculation module is configured to, when the first detection result indicates normal operation, perform a difference calculation on the current positive sequence currents at both ends of the target line to obtain second operation data; and input the second operation data into a fault detection model to obtain a second detection result;

[0038] The judgment module is used to determine the target line detection result based on the first detection result and the second detection result.

[0039] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0040] Obtain fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs;

[0041] Determine the data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data;

[0042] Sampling the current positive sequence current at both ends of the target line according to the data sampling interval to obtain first operating data;

[0043] Inputting first operating data into a fault detection model to obtain a first detection result, wherein the fault detection model is trained based on operating data of the target line during normal operation;

[0044] When the first detection result is normal operation, the second operation data is obtained by difference calculation on the current positive sequence current at both ends of the target line;

[0045] The second operation data is input into the fault detection model to obtain the second detection result;

[0046] The target line detection result is determined based on the first detection result and the second detection result.

[0047] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0048] Obtain fault characteristic data corresponding to fault positive sequence current at both ends of the target line when a fault event occurs;

[0049] Determine the data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data;

[0050] Sample the current positive sequence current at both ends of the target line according to the data sampling interval to obtain the first operation data;

[0051] Input the first operation data into the fault detection model to obtain the first detection result, and the fault detection model is trained based on the operation data of the target line in normal operation;

[0052] When the first detection result is normal operation, the second operation data is obtained by difference calculation on the current positive sequence current at both ends of the target line;

[0053] The second operation data is input into the fault detection model to obtain the second detection result;

[0054] The target line detection result is determined based on the first detection result and the second detection result.

[0055] The above-mentioned line detection method, apparatus, computer equipment and storage medium obtain fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; determine the data sampling interval of the positive sequence current at both ends of the target line based on the fault characteristic data; sample the current positive sequence current at both ends of the target line based on the data sampling interval to obtain first operating data; input the first operating data into a fault detection model to obtain a first detection result, and the fault detection model is trained based on the operating data of the target line during normal operation; when the first detection result is normal operation, calculate the difference between the current positive sequence current at both ends of the target line to obtain second operating data; input the second operating data into the fault detection model to obtain a second detection result; and determine the target line detection result based on the first detection result and the second detection result. In this way, by determining the sampling interval of the positive sequence current at both ends of the target line, and then obtaining the first operating data based on the sampling interval, the positive sequence current at both ends of the target line is self-synchronized, and the model is then trained using the characteristic data of the synchronized positive sequence current. Finally, the detection result of the target line is obtained based on the trained model. This longitudinal protection method on the power grid line effectively ensures the rapid effectiveness of the relay protection of the current target line and effectively improves the line detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A diagram showing an application environment of a line detection method in one embodiment;

[0057] Figure 2 1 is a flow chart of a line detection method according to an embodiment;

[0058] Figure 3 A schematic diagram of a process for determining a data sampling interval in one embodiment;

[0059] Figure 4 A schematic diagram of a process for generating first operating data in one embodiment;

[0060] Figure 5 A schematic diagram of a process for generating a fault detection model in one embodiment;

[0061] Figure 6 A schematic diagram of a process for determining a target line fault in one embodiment;

[0062] Figure 7 A schematic diagram of a process for generating second operating data in one embodiment;

[0063] Figure 8 A schematic diagram of a process for determining a target line detection result in one embodiment;

[0064] Figure 9 is a structural block diagram of a line detection device in one embodiment;

[0065] Figure 10 is a diagram of the internal structure of a computer device in one embodiment;

[0066] Figure 11 FIG1 is a simulation model diagram of an active power distribution network in one embodiment;

[0067] Figure 12 Schematic diagram of detection results corresponding to a fault detection model in an embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0069] The line detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the computer device 102 obtains fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs, determines a data sampling interval for the positive sequence current at both ends of the target line based on the fault characteristic data, samples the current positive sequence current at both ends of the target line based on the data sampling interval to obtain first operating data, inputs the first operating data into a fault detection model, and obtains a first detection result. The fault detection model is trained based on the operating data of the target line during normal operation. When the first detection result is normal operation, the current positive sequence current at both ends of the target line is calculated to obtain second operating data, inputs the second operating data into the fault detection model, and obtains a second detection result. The target line detection result is determined based on the first detection result and the second detection result. The computer device 102 may specifically include, but is not limited to, various personal computers, laptops, servers, smart phones, tablets, smart cameras, and portable wearable devices.

[0070] In one embodiment, Figure 2 As shown, a line detection method is provided, which is applied to Figure 1 Taking the computer device 102 in the example as an example, the method includes the following steps:

[0071] Step S202 : Acquire fault characteristic data corresponding to the fault positive sequence currents at both ends of the target line when a fault event occurs.

[0072] The fault positive sequence current is the positive sequence current at both ends of the target line when a fault event occurs. The fault characteristic data may include the amplitude, phase difference, frequency, and other characteristic data of the fault positive sequence current used to characterize the characteristics of the fault positive sequence current.

[0073] Step S204, determining the data sampling interval of the positive sequence current at both ends of the target line according to the fault feature data.

[0074] Specifically, the computer device determines the data sampling interval of the positive sequence current at both ends of the target line by detecting the time interval required for the feature data corresponding to the fault positive sequence current to be transmitted from one end of the target line to the other end. For example, when a fault event occurs, the computer device collects the feature data of the positive sequence current at both ends of the target line in real time and records the collection time corresponding to each group of feature data. When the positive sequence current at one end of the target line first appears a fault waveform, the sampling time at this time is recorded as the first sampling time. When the positive sequence current at the other end of the target line first appears a fault waveform, the sampling time at this time is recorded as the second sampling time. The first sampling time and the second sampling time are calculated to obtain the data sampling interval of the positive sequence current at both ends of the target line.

[0075] Step S206, sampling the current positive sequence current at both ends of the target line according to the data sampling interval to obtain first running data.

[0076] Specifically, the computer device samples the positive sequence current at both ends of the target line according to the data sampling interval. Specifically, the current positive sequence current at one end of the target line is sampled, and after a time period corresponding to the data sampling interval, the positive sequence current at the other end is sampled, thereby realizing the synchronization of the positive sequence current at both ends of the target line.

[0077] Step S208, inputting the first running data into a fault detection model to obtain a first detection result, the fault detection model being trained based on the running data of the target line in normal operation.

[0078] The fault detection model can be a common deep learning model or various neural network models, such as wavelet neural network, generalized neural network, convolutional neural network, etc., and can also be a support vector machine model. The training sample data of the fault detection model is the running data of the target line in normal operation.

[0079] Specifically, the computer device inputs the first running data obtained in the above step S206 as input data into the fault detection model to obtain the first detection result corresponding to the first running data.

[0080] Step S210, when the first detection result is normal, calculating the difference between the current positive sequence currents at both ends of the target line to obtain second running data.

[0081] Specifically, the computer device analyzes the first detection result determined in the above step. If the first detection result is normal, the computer device calculates the difference between the feature data corresponding to the current positive sequence currents at both ends of the target line to obtain the second running data.

[0082] Step S212, input the second operation data into the fault detection model to obtain a second detection result.

[0083] Specifically, the computer device inputs the second operation data as input data into the fault detection model to obtain the second detection result corresponding to the second operation data.

[0084] Step S214, determine a target line detection result based on the first detection result and the second detection result.

[0085] Specifically, the computer device determines the first detection result and the second detection result according to the foregoing steps, wherein the priority of the first detection result is greater than the priority of the second detection result, when the first detection result is an operation fault, it is determined that the target line is in an operation fault state, when the first detection result is normal operation, the second detection result is analyzed, if the second detection result is also normal, it is determined that the operation of the target line is in a normal state, if the second detection result is an operation fault, it is determined that the operation of the target line is in a fault state.

[0086] In the embodiment, the fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when the fault event occurs is obtained; the data sampling interval of the positive sequence current at both ends of the target line is determined according to the fault characteristic data; the first operation data is obtained by sampling the current positive sequence current at both ends of the target line according to the data sampling interval; the first detection result is obtained by inputting the first operation data into the fault detection model, the fault detection model is trained based on the operation data of the target line in normal operation; when the first detection result is normal operation, the second operation data is obtained by difference calculation of the current positive sequence current at both ends of the target line; the second detection result is obtained by inputting the second operation data into the fault detection model; the target line detection result is determined based on the first detection result and the second detection result. In this way, the sampling interval of the positive sequence current at both ends of the target line is determined, and then the first operation data is obtained according to the sampling interval, so as to realize the self-synchronization of the positive sequence current at both ends of the target line, and then the model is trained by using the characteristic data of the synchronous positive sequence current, and finally the detection result of the target line is obtained according to the trained model. This longitudinal protection method on the power grid line greatly guarantees the speed effectiveness of the current relay protection of the target line, and effectively improves the line detection efficiency.

[0087] In one embodiment, as shown in Figure 3 determining the data sampling interval of the positive sequence current at both ends of the target line according to the fault characteristic data includes:

[0088] Step S302, according to the phase angle characteristics of the fault characteristic data, the phase difference of the fault positive sequence current at both ends of the target line when the fault event occurs is determined.

[0089] Specifically, the computer device collects the positive sequence currents at both ends of the target line respectively, analyzes the characteristic data corresponding to the positive sequence currents at both ends respectively, and compares the phase angle characteristics corresponding to the positive sequence currents at both ends, so as to determine the phase difference of the fault positive sequence currents at both ends of the target line when the fault event occurs.

[0090] In step S304, the data sampling interval of the positive sequence currents at both ends of the target line is determined according to the phase difference.

[0091] Specifically, the computer device compensates the phase of the positive sequence currents at both ends according to the phase difference of the positive sequence currents at both ends, and then determines the data sampling interval of the positive sequence currents at both ends.

[0092] In the embodiment, the phase difference of the fault positive sequence currents at both ends of the target line when the fault event occurs is determined according to the phase angle characteristics of the fault characteristic data, and the data sampling interval of the positive sequence currents at both ends of the target line is determined according to the phase difference, so as to determine the data sampling interval according to the currents at both ends of the target line, and effectively improve the accuracy of determining the data sampling interval.

[0093] In one embodiment, as shown in Figure 4 the first operating data is obtained by sampling the current positive sequence currents at both ends of the target line according to the data sampling interval, including:

[0094] In step S402, the first characteristic data is obtained by collecting the current positive sequence currents at the current inflow end of the target line.

[0095] The first characteristic data includes the phase angle characteristics, amplitude and other characteristic data of the positive sequence currents at both ends.

[0096] In step S404, the second characteristic data is obtained by collecting the current positive sequence currents at the current outflow end of the target line after the first characteristic data is collected and the data sampling interval is passed.

[0097] Specifically, the computer device samples the positive sequence currents at both ends of the target line according to the data sampling interval, specifically, the current positive sequence currents at one end of the target line are sampled, and after the time period corresponding to the data sampling interval is passed, the positive sequence currents at the other end are sampled, so as to realize the synchronization of the positive sequence currents at both ends of the target line.

[0098] In step S406, the first operating data is obtained according to the first characteristic data and the second characteristic data.

[0099] In the embodiment, the computer device collects the first feature data of the current positive sequence current of the inflow end of the target line current, collects the second feature data of the current positive sequence current of the outflow end of the target line current after the first feature data is collected and after a data sampling interval, and obtains the first operation data according to the first feature data and the second feature data, so that the positive sequence currents at both ends of the target line are sampled according to the data sampling interval, the transmission time delay of the fault positive sequence current in the target line is avoided, and the accuracy of the first operation data is improved.

[0100] In one embodiment, as shown in Figure 5 Before the first operation data is input into the fault detection model to obtain the first detection result, the method further includes:

[0101] In step S502, historical operation data of the target line in a normal operation condition is obtained.

[0102] In step S504, a support vector data description model is trained based on the historical operation data to obtain a fault detection model.

[0103] The support vector data description (SVDD) can describe a target data set in a hyper-spherical shape, and can be used for heterogeneous point detection or classification, usually contains multiple sample classes, and needs to simultaneously describe each sample class in a hyper-spherical shape.

[0104] In the embodiment, the historical operation data of the target line in the normal operation condition is obtained, the support vector data description model is trained based on the historical operation data to obtain the fault detection model, so that the fault detection model learned from the operation data features of the target line in the normal operation condition has strong data feature discrimination ability, and the reliability of the fault detection model is effectively improved.

[0105] In one embodiment, as shown in Figure 6 After the first operation data is input into the fault detection model to obtain the first detection result, the method further includes:

[0106] In step S602, when the first detection result is abnormal, it is determined that the target line detection result of the target line is a target line fault.

[0107] In the embodiment, when the first detection result is abnormal, it indicates that the current positive sequence current presents a fault waveform, so it is determined that the target line detection result of the target line is a target line fault, and the accuracy of the target line fault detection is improved.

[0108] In one embodiment, as shown in Figure 7As shown, when the first detection result is normal operation, the current positive sequence current at both ends of the target line is calculated to obtain the second operation data, including:

[0109] Step S702: When the first detection result indicates normal operation, the corresponding sinusoidal wave amplitude and phase angle characteristics of the current positive sequence current at both ends of the target line are obtained.

[0110] Specifically, when the computer device determines that the first detection result is a normal operating state according to the above steps, it then obtains the corresponding sinusoidal wave amplitude and phase angle characteristics of the current positive sequence current at both ends of the target line.

[0111] Step S704 , performing difference calculation based on the current sine wave amplitudes of the positive sequence currents at both ends of the target line to obtain amplitude characteristic data.

[0112] Specifically, the computer device subtracts the sine wave amplitudes of the current positive sequence currents at both ends of the target line to obtain amplitude characteristic data.

[0113] Step S706 , performing difference calculation based on the current phase angle characteristics of the positive sequence current at both ends of the target line to obtain phase angle characteristic data.

[0114] Specifically, the computer device subtracts the phase angle characteristic values ​​of the current positive sequence currents at both ends of the target line to obtain the phase angle characteristic data.

[0115] Step S708: Obtain second operating data according to the amplitude characteristic data and the phase angle characteristic data.

[0116] In this embodiment, when the first detection result is normal operation, the corresponding sinusoidal wave amplitude and phase angle characteristics of the current positive-sequence current at both ends of the target line are obtained, and the amplitude characteristic data is obtained by difference calculation based on the sinusoidal wave amplitude of the current positive-sequence current at both ends of the target line. The phase angle characteristic data is obtained by difference calculation based on the phase angle characteristic of the current positive-sequence current at both ends of the target line. The second operation data is obtained based on the amplitude characteristic data and the phase angle characteristic data, thereby achieving the second operation data based on the difference in the characteristic data corresponding to the positive-sequence current at both ends of the target, effectively improving the accuracy of the second operation data.

[0117] In one embodiment, Figure 8 As shown, determining the target line detection result based on the first detection result and the second detection result includes:

[0118] Step S802: When the first detection result indicates that the target line is operating abnormally, determine that the target line detection result is an operation fault.

[0119] Step S804: When the first detection result indicates that the target line is operating normally and the second detection result indicates that the target line is operating normally, it is determined that the detection result of the target line is operating normally.

[0120] Step S806, when the first detection result represents that the target line is running normally and the second detection result represents that the target line is running abnormally, determining that the detection result of the target line is running failure.

[0121] In the embodiment, the detection result of the target line is determined by analyzing the first detection result and the second detection result. When the first detection result represents that the target line is running abnormally, it is determined that the detection result of the target line is running failure. When the first detection result represents that the target line is running normally and the second detection result represents that the target line is running normally, it is determined that the detection result of the target line is running normally. When the first detection result represents that the target line is running normally and the second detection result represents that the target line is running abnormally, it is determined that the detection result of the target line is running failure. The target line is analyzed for failure by setting different priorities for the first detection result and the second detection result, thereby effectively improving the accuracy of the target line failure detection.

[0122] The application also provides an application scenario applying the line detection method. Specifically, the line detection method is applied in the application scenario as follows.

[0123] The extreme value normalization is performed on the feature vector formed by the positive sequence currents at both ends of the line, so that the out-of-zone failure and normal operation features are consistent, and then the massive data of normal operation is used to replace the out-of-zone failure data to reflect the failure features, thereby solving the problem that the machine algorithm cannot be successfully applied due to the need for a large amount of failure data. The feature vector of the positive sequence current is normalized according to the following formula 1:

[0124]

[0125] In the formula, I and I' are the positive sequence current feature vectors before and after normalization, i'1(k) and i'2(k) are the kth positive sequence current instantaneous values at the first section and the end of the line, and n is the number of sampling points in a period.

[0126] The self-synchronization of the positive sequence currents at both ends of the line is realized by using the self-synchronization technology based on the mutation variable features in the art. However, considering the self-synchronization error in actual application, the application considers an error of at most 15°, constructs a training sample set of the single classification algorithm, and specifically constructs the training sample set according to the following formula 2:

[0127]

[0128] In the formula, t f1 , t f2 are the fault occurrence times detected according to the current mutation variable features at both ends of the line. Considering a certain self-synchronization error, t f1 -t f2= 1, 2, …, m, where m is the maximum self-synchronization error corresponding to the number of sampling points, m x 360° / is not greater than 15°.

[0129] The single classification algorithm, support vector data description (SVDD), is trained by using the training sample set in the above step, and a classification hypersphere with a radius R is obtained in a high-dimensional space.

[0130] Considering the influence of measurement errors, non-periodic components, etc., the radius R in the above step is multiplied by a reliability coefficient K to define the protection criterion threshold value, as shown in the following formula 3:

[0131] d set = K x R, formula 3

[0132] In the formula, d set is the threshold value of the protection criterion; because the feature dispersion of normal operation and out-of-area faults is low, and the optimization goal of SVDD is to find the classification hypersphere with the smallest volume, the training samples in the high-dimensional space are relatively dense, therefore, the reliability coefficient K should take a small value, and K = 1.0-1.1 is taken in the present application. In the test and application of the present application, the positive sequence currents at both ends of the line are processed by using the maximum value normalization as the input of SVDD, the distance between the sample and the center of the hypersphere is calculated, if the distance is less than the threshold value, it is judged as an out-of-area fault or normal operation; otherwise, it is judged as an in-area fault.

[0133] The feature vector after the maximum value normalization is taken as the input of SVDD, the distance between the mapped feature quantity and the center of the hypersphere is calculated, if the distance is greater than the threshold value, it is judged as an in-area fault, otherwise, the following step is executed:

[0134] The feature vector formed by the positive sequence fault components at both ends of the line is normalized by using the maximum value, and then taken as the input of SVDD in step three. If the distance between the mapped feature quantity and the center of the hypersphere is less than the protection threshold value, it is judged as an out-of-area fault or normal operation; otherwise, it is an in-area fault.

[0135] A simulation model of an active power distribution network is built in PSCAD as shown in Figure 11 The training sample set and the test sample set are obtained by fully considering the load level, fault location, transition resistance (maximum 400 ohms), penetration rate of distributed power (maximum 50%), fault type (phase-to-phase short circuit), etc. Figure 12 The classification hypersphere obtained by training SVDD has a radius of 0.8717, and the reliability coefficient of the protection criterion is 1.02, so the protection criterion threshold value is 0.8891, which corresponds to Figure 12The dashed line in the figure shows the sample. When the distance between a sample and the center of the hypersphere is greater than 0.8891, it is judged to be an internal fault. Otherwise, the eigenvector of the positive sequence current fault component is calculated and used as the input of the SVDD to determine whether a distribution network fault has occurred. When the distance between the eigenvector and the center of the hypersphere is greater than 0.8891, it is judged to be an internal fault; otherwise, it is judged to be an external fault. Testing has shown that the accuracy for normal operation and external faults is 100%, and the accuracy for internal faults is 99.5%.

[0136] In this embodiment, the sampling interval of the positive-sequence current at both ends of the target line is determined, and the first operating data is obtained based on the sampling interval, so as to achieve self-synchronization of the positive-sequence current at both ends of the target line. The characteristic data of the synchronized positive-sequence current is then used to train the model, and finally the detection result of the target line is obtained based on the trained model. This longitudinal protection method on the power grid line greatly and effectively guarantees the rapid effectiveness of the relay protection of the current target line and effectively improves the line detection efficiency.

[0137] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0138] In one embodiment, Figure 9 As shown, a line detection device is provided. The device can be a software module or a hardware module, or a combination of the two to form a part of a computer device. The device specifically includes: an acquisition module 902, a first calculation module 904, a second calculation module 906, and a judgment module 908, wherein:

[0139] An acquisition module 902 is configured to acquire fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; and determine a data sampling interval for the positive sequence current at both ends of the target line based on the fault characteristic data;

[0140] A first calculation module 904 is configured to sample the current positive sequence current at both ends of the target line according to a data sampling interval to obtain first operating data; and input the first operating data into a fault detection model to obtain a first detection result. The fault detection model is trained based on the operating data of the target line during normal operation.

[0141] A second calculation module 906 is configured to, when the first detection result indicates normal operation, calculate the difference between the current positive sequence currents at both ends of the target line to obtain second operating data; and input the second operating data into the fault detection model to obtain a second detection result;

[0142] The judgment module 908 is configured to determine a target line detection result based on the first detection result and the second detection result.

[0143] The above-mentioned line detection device obtains fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; determines the data sampling interval of the positive sequence current at both ends of the target line based on the fault characteristic data; samples the current positive sequence current at both ends of the target line based on the data sampling interval to obtain first operating data; inputs the first operating data into a fault detection model to obtain a first detection result, and the fault detection model is trained based on the operating data of the target line during normal operation; when the first detection result is normal operation, calculates the difference between the current positive sequence current at both ends of the target line to obtain second operating data; inputs the second operating data into the fault detection model to obtain a second detection result; and determines the target line detection result based on the first detection result and the second detection result. In this way, by determining the sampling interval of the positive sequence current at both ends of the target line, and then obtaining the first operating data based on the sampling interval, the positive sequence current at both ends of the target line is self-synchronized, and the model is then trained using the characteristic data of the synchronized positive sequence current. Finally, the detection result of the target line is obtained based on the trained model. This longitudinal protection method on the power grid line effectively ensures the rapid effectiveness of the relay protection of the current target line and effectively improves the line detection efficiency.

[0144] The specific definition of the line detection device can be found in the definition of the line detection method above and will not be repeated here. Each module in the above-mentioned line detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0145] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a line detection method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0146] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0147] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0148] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0149] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of each of the above-described method embodiments.

[0150] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0151] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The above-described 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 application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A line detection method, characterized in that: The method comprises: Obtain fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; Determining a data sampling interval of positive sequence current at both ends of the target line according to the fault characteristic data; Sampling the current positive sequence current at both ends of the target line according to the data sampling interval to obtain first operating data; Inputting the first operating data into a fault detection model to obtain a first detection result, wherein the fault detection model is trained based on the operating data of the target line during normal operation; When the first detection result indicates normal operation, performing a difference calculation on the current positive sequence currents at both ends of the target line to obtain second operation data; inputting the second operating data into the fault detection model to obtain a second detection result; A target line detection result is determined based on the first detection result and the second detection result.

2. The method according to claim 1, characterized in that The determining, based on the fault characteristic data, a data sampling interval of the positive sequence current at both ends of the target line includes: determining, based on the phase angle characteristics of the fault characteristic data, a phase difference of the fault positive sequence currents at both ends of the target line when the fault event occurs; A data sampling interval of the positive sequence current at both ends of the target line is determined according to the phase difference.

3. The method according to claim 1, characterized in that The sampling of the current positive sequence current at both ends of the target line according to the data sampling interval to obtain the first operating data includes: Collecting a current positive sequence current at a current inflow end of the target line to obtain first characteristic data; After the first characteristic data is acquired and the data sampling interval has passed, the current positive sequence current is acquired from the current outflow end of the target line to acquire second characteristic data; First operating data is obtained according to the first characteristic data and the second characteristic data.

4. The method according to claim 1, wherein Before inputting the first operating data into the fault detection model to obtain the first detection result, the method further includes: Acquiring historical operating data of the target line under normal operating conditions; The fault detection model is obtained by training a support vector data description model based on the historical operation data.

5. The method according to claim 1, wherein After inputting the first operating data into the fault detection model to obtain a first detection result, the method further includes: When the first detection result is an operation abnormality, it is determined that the target line detection result of the target line is a target line fault.

6. The method according to claim 1, characterized in that When the first detection result indicates normal operation, performing a difference calculation on the current positive sequence currents at both ends of the target line to obtain second operation data includes: When the first detection result indicates normal operation, obtaining corresponding sinusoidal wave amplitude and phase angle characteristics of the current positive sequence current at both ends of the target line; Amplitude characteristic data is obtained by performing difference calculation based on the current sine wave amplitudes of the positive sequence current at both ends of the target line; Performing difference calculation based on the phase angle characteristics of the current positive sequence current at both ends of the target line to obtain phase angle characteristic data; Second operating data is obtained according to the amplitude characteristic data and the phase angle characteristic data.

7. The method according to claim 1, characterized in that The determining the target line detection result based on the first detection result and the second detection result includes: When the first detection result indicates that the target line is operating abnormally, determining that the target line detection result is an operation fault; When the first detection result indicates that the target line is operating normally and the second detection result indicates that the target line is operating normally, determining that the detection result of the target line is operating normally; When the first detection result indicates that the target line is operating normally and the second detection result indicates that the target line is operating abnormally, it is determined that the detection result of the target line is an operation fault.

8. A line detection device, characterized in that: The device comprises: An acquisition module is configured to acquire fault characteristic data corresponding to the fault positive sequence current at both ends of the target line when a fault event occurs; and determine a data sampling interval for the positive sequence current at both ends of the target line according to the fault characteristic data; a first calculation module, configured to sample the current positive sequence current at both ends of the target line according to the data sampling interval to obtain first operating data; and input the first operating data into a fault detection model to obtain a first detection result, wherein the fault detection model is trained based on the operating data of the target line during normal operation; a second calculation module, configured to, when the first detection result indicates normal operation, perform difference calculation on the current positive sequence currents at both ends of the target line to obtain second operation data; and input the second operation data into the fault detection model to obtain a second detection result; A judgment module is used to determine a target line detection result based on the first detection result and the second detection result.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images