Fault determination method and device for power transmission line

Abstract

The invention discloses a power transmission line fault determination method and device, and relates to the technical field of power systems. The method comprises the following steps: acquiring self-admittance matrixes and mutual admittance matrixes of a plurality of nodes in a power transmission line system; based on the self-admittance matrix and the mutual admittance matrix, complex domain voltage information and complex domain current information of a fault node in the power transmission line system are determined; converting the complex domain voltage information and the complex domain current information to obtain time domain waveform information of the fault node; and calling a neural network model to analyze the time domain waveform information to obtain the position information of the fault node. According to the invention, the technical problem of low accuracy of fault positioning of the power transmission line is solved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method and device for determining a fault of a power transmission line. Background Art

[0002] At present, transmission lines are an important part of the power system. When a transmission line fails, it will cause a large-scale power outage. Therefore, it is very important to quickly and accurately find the fault point on the transmission line.

[0003] In the related art, the fault point on the transmission line is determined by adopting the single-ended traveling wave fault ranging method. There are two main single-ended traveling wave fault ranging methods. One is active detection type, but this method is only applicable to permanent short circuits; the other is to calculate the fault distance based on the time difference between the traveling wave head arriving at the measuring point twice in succession, but this method requires accurate identification of the traveling wave head and a very high sampling rate, so there is a technical problem of low accuracy in fault locating of the transmission line.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method and device for determining a fault of a power transmission line, so as to at least solve the technical problem of low accuracy in locating faults of the power transmission line.

[0006] According to one aspect of an embodiment of the present application, a method for determining a fault of a transmission line is provided. The method may include: obtaining a self-admittance matrix and a mutual-admittance matrix of multiple nodes in a transmission line system, wherein the node includes at least a connection point and an end point of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the node, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, determining the complex domain voltage information and complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; converting the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and current waveform of the fault node; calling a neural network model to analyze the time domain waveform information to obtain the location information of the fault node, wherein the neural network model is obtained by training based on the time domain waveform information sample, and the location information is used to represent the location where the fault occurs in the transmission line.

[0007] Optionally, the method also includes: obtaining the parallel admittance and series impedance of the transmission line, wherein the parallel admittance is used to represent the admittance characteristics of the transmission line per unit length, and the series impedance is used to represent the impedance characteristics of the transmission line per unit length; obtaining the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, including: determining the self-admittance matrix and the mutual-admittance matrix based on the parallel admittance and the series impedance.

[0008] Optionally, obtaining the parallel admittance and series impedance of the transmission line includes: using a frequency-variant parameter model of the transmission line system to perform polynomial vector fitting on the frequency-variant parameters of the transmission line to obtain the parallel admittance and series impedance, wherein the frequency-variant parameters are used to represent line parameters that vary with frequency.

[0009] Optionally, determining the self-admittance matrix and the mutual-admittance matrix based on the parallel admittance and the series impedance includes: determining the self-admittance matrix and the mutual-admittance matrix based on the parallel admittance, the series impedance, and the length information of the transmission line, wherein the length information is used to represent the actual length of the transmission line.

[0010] Optionally, based on the auto-admittance matrix and the mutual-admittance matrix, the complex domain voltage information and the complex domain current information of the fault node in the transmission line system are determined, including: based on the auto-admittance matrix and the mutual-admittance matrix, the impedance matrix of the transmission line system is determined, wherein the impedance matrix is ​​used to represent the impedance characteristics of the transmission line system; based on the impedance matrix, the complex domain voltage information and the complex domain current information are determined.

[0011] Optionally, determining the impedance matrix of the transmission line system based on the self-admittance matrix and the mutual-admittance matrix includes: determining the admittance matrix of the transmission line system based on the self-admittance matrix and the mutual-admittance matrix, wherein the admittance matrix is ​​used to represent the admittance characteristics of the transmission line system; and converting the admittance matrix to obtain the impedance matrix.

[0012] Optionally, based on the impedance matrix, complex domain voltage information and complex domain current information are determined, including: based on the impedance matrix, adding a fault excitation current at the fault node to obtain a fault excitation voltage, wherein the fault excitation current is used to represent the current fluctuation occurring at the fault node, and the fault excitation voltage is used to represent the voltage fluctuation occurring at the fault node; converting the fault excitation voltage to obtain complex domain short-circuit current information, wherein the complex domain short-circuit current information is used to represent the short-circuit current of the fault node in the complex frequency domain; based on the impedance matrix and the complex domain short-circuit current information, complex domain voltage information and complex domain current information are determined.

[0013] Optionally, the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the fault node, including: performing a numerical inverse Laplace transform on the complex domain voltage information and the complex domain current information to obtain the time domain waveform information.

[0014] Optionally, the method also includes: establishing an initial neural network model based on a residual convolutional neural network and a multi-head self-attention mechanism; training the initial neural network model based on time domain waveform information samples to obtain a neural network model, wherein the time domain waveform information samples are generated based on the time domain waveform information.

[0015] According to another aspect of the embodiment of the present application, a transmission line fault determination device is also provided. The device may include: an acquisition unit, used to acquire the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the node includes at least the connection point and the end point of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the node, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; a first determination unit, used to determine the complex domain voltage information and complex domain current information of the fault node in the transmission line system based on the self-admittance matrix and the mutual-admittance matrix, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; a conversion unit, used to convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; a second determination unit, used to call a neural network model to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is obtained by training based on the time domain waveform information sample, and the position information is used to represent the position where the fault occurs in the transmission line.

[0016] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, including: the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the transmission line fault determination methods.

[0017] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program. When the program is run, the method for determining a fault of a power transmission line in an embodiment of the present invention is executed.

[0018] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement any one of the methods for determining a fault of a power transmission line.

[0019] According to another aspect of the embodiment of the present application, a computer program product is further provided. The computer program product may include a computer program, wherein the computer program is configured to execute any of the above-mentioned methods for determining a fault of a power transmission line when running.

[0020] According to another aspect of the embodiment of the present application, a computer program product is also provided. The computer program product may include a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and the computer program is configured to execute any of the above-mentioned transmission line fault determination methods when running.

[0021] According to another aspect of the embodiment of the present application, a computer program is further provided, wherein the computer program is configured to execute any one of the above-mentioned methods for determining a fault of a power transmission line when the program is run.

[0022] In an embodiment of the present application, a self-admittance matrix and a mutual-admittance matrix of multiple nodes in a transmission line system are obtained, wherein the nodes include at least connection points and end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, the complex domain voltage information and the complex domain current information of the faulty node in the transmission line system are determined, wherein the complex domain voltage information is used to represent the voltage of the faulty node in the complex frequency domain, and the complex domain current information is used to represent the current of the faulty node in the complex frequency domain; the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the faulty node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the faulty node; a neural network model is called to analyze the time domain waveform information to obtain the position information of the faulty node, wherein the neural network model is obtained based on the training of the time domain waveform information samples, and the position information is used to represent the position where the fault occurs in the transmission line, thereby achieving the technical effect of improving the accuracy of fault locating for the transmission line, thereby solving the technical problem of low accuracy of fault locating for the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 is a flow chart of a method for determining a fault of a power transmission line according to an embodiment of the present application;

[0025] Figure 2 is a schematic diagram of the structure of a residual convolutional neural network according to an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of a frequency-variable parameter model according to an embodiment of the present application;

[0027] Figure 4 is a structural schematic diagram of a transmission line fault determination device according to an embodiment of the present application;

[0028] Figure 5 is a schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] According to an embodiment of the present application, a method embodiment of a method for determining a fault of a transmission line is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1 is a flow chart of a method for determining a fault of a power transmission line according to an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps:

[0033] Step S102, obtaining the self-admittance matrix and the mutual-admittance matrix of a plurality of nodes in the transmission line system.

[0034] In the technical solution provided in step S102 above, the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system can be obtained. The transmission line system can be a T-connected hybrid transmission line system. The above nodes can at least include the connection points and end points of the transmission line. The self-admittance matrix can be used to represent the admittance characteristics of the node, which can be called a complex domain self-admittance submatrix, which can be expressed by y s(s) is used to represent the mutual admittance matrix. The mutual admittance matrix can be used to represent the admittance characteristics associated between multiple nodes. It can be called the line mutual admittance submatrix and can be expressed by y m (s) is indicated.

[0035] Optionally, the frequency-dependent parameters of the transmission line are fitted with a polynomial vector based on rational function approximation, and the shunt admittance and series impedance of different types of transmission lines in the T-connected hybrid transmission line at discrete frequencies can be obtained. Further, based on the obtained shunt admittance and series impedance, the complex domain self-admittance submatrix y of multiple nodes in the transmission line system can be determined s (s) and the line mutual admittance submatrix y m (s).

[0036] Step S104: determining complex domain voltage information and complex domain current information of a fault node in the power transmission line system based on the auto-admittance matrix and the mutual-admittance matrix.

[0037] In the technical solution provided in the above step S104, after obtaining the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, the complex domain voltage information and the complex domain current information of the fault node in the transmission line system can be determined based on the obtained self-admittance matrix and the mutual-admittance matrix. Among them, the complex domain voltage information can be used to represent the voltage of the fault node in the complex frequency domain, which can be called the complex frequency fault transient voltage. The complex domain current information can be used to represent the current of the fault node in the complex frequency domain, which can be called the complex frequency fault transient current. It should be noted that the above fault transient voltage and fault transient current are both fault component data.

[0038] Optionally, after obtaining the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, the admittance matrix of the transmission line system can be determined based on the obtained self-admittance matrix and the mutual-admittance matrix. Further converting the admittance matrix of the transmission line system can obtain the impedance matrix of the transmission line system. Based on the impedance matrix of the transmission line system, the complex domain expression of the fault transient voltage and the fault transient current at any point of the transmission system can be determined.

[0039] Step S106, converting the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node.

[0040] In the technical solution provided in the above step S106, after the complex domain voltage information and complex domain current information of the fault node in the transmission line system are determined, the determined complex domain voltage information and complex domain current information can be converted to obtain the time domain waveform information of the fault node. The time domain waveform information can be used to represent the voltage waveform and current waveform of the fault node.

[0041] Optionally, after determining the complex domain voltage information and complex domain current information of the fault node in the transmission line system, the complex domain expressions of the fault transient voltage and fault transient current can be quickly converted into time domain expressions using numerical inverse Laplace transform to accurately restore the morphological characteristics of the line surge.

[0042] Step S108, calling the neural network model to analyze the time domain waveform information to obtain the location information of the fault node.

[0043] In the technical solution provided in the above step S108, after the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the fault node, the neural network model can be called to analyze the time domain waveform information to obtain the location information of the fault node. The neural network model can be trained based on the time domain waveform information sample. The location information can be used to indicate the location where the fault occurs in the transmission line.

[0044] Optionally, by establishing a neural network model that combines a residual convolutional neural network with a multi-head self-attention mechanism, the training set is input into the residual convolutional neural network, and the network parameters are updated according to the loss function results. The trained residual convolutional neural network model is tested with the test set, the segmentation error is calculated, and the effectiveness of the model is verified. The above neural network model is called to analyze the time domain waveform information to obtain the location information of the fault node.

[0045] In an embodiment of the present application, a self-admittance matrix and a mutual-admittance matrix of multiple nodes in a transmission line system are obtained, wherein the nodes include at least connection points and end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, the complex domain voltage information and the complex domain current information of the faulty node in the transmission line system are determined, wherein the complex domain voltage information is used to represent the voltage of the faulty node in the complex frequency domain, and the complex domain current information is used to represent the current of the faulty node in the complex frequency domain; the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the faulty node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the faulty node; a neural network model is called to analyze the time domain waveform information to obtain the position information of the faulty node, wherein the neural network model is obtained based on the training of the time domain waveform information samples, and the position information is used to represent the position where the fault occurs in the transmission line, thereby achieving the technical effect of improving the accuracy of fault locating for the transmission line, thereby solving the technical problem of low accuracy of fault locating for the transmission line.

[0046] The above embodiments of the present application are further described below.

[0047] In some embodiments of the present application, the method further includes: obtaining the parallel admittance and series impedance of the transmission line, wherein the parallel admittance is used to represent the admittance characteristics of the transmission line per unit length, and the series impedance is used to represent the impedance characteristics of the transmission line per unit length; step S102, obtaining the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, including: determining the self-admittance matrix and the mutual-admittance matrix based on the parallel admittance and the series impedance.

[0048] In this embodiment, the parallel admittance and series impedance of the transmission line can be obtained, and further based on the obtained parallel admittance and series impedance, the self-admittance matrix and the mutual admittance matrix can be determined. Among them, the parallel admittance can be used to represent the admittance characteristics of the transmission line per unit length, which can be called the parallel admittance per unit length, and can be represented by y(s). The series impedance is used to represent the impedance characteristics of the transmission line per unit length, which can be called the series impedance per unit length, and can be represented by z(s).

[0049] Optionally, frequency-varying parameters of the transmission line are fitted with polynomial vectors based on rational function approximation, and the unit length shunt admittance y(s) and unit length series impedance z(s) of discrete frequencies of different types of transmission lines in the T-connected hybrid transmission line can be obtained. After the unit length shunt admittance y(s) and unit length series impedance z(s) of discrete frequencies of different types of transmission lines are obtained, the self-admittance matrix and mutual-admittance matrix of each node of the system can be obtained.

[0050] In some embodiments of the present application, the parallel admittance and series impedance of a transmission line are obtained, including: using a frequency-variant parameter model of the transmission line system to perform polynomial vector fitting on the frequency-variant parameters of the transmission line to obtain the parallel admittance and series impedance, wherein the frequency-variant parameters are used to represent line parameters that vary with frequency.

[0051] In this embodiment, the frequency-variable parameter model of the transmission line system can be used to perform polynomial vector fitting on the frequency-variable parameters of the transmission line to obtain the parallel admittance and series impedance. Optionally, a frequency-variable parameter model of a T-connected hybrid transmission line system is established in the electromagnetic transient simulation software to output the frequency-variable series impedance matrix and parallel admittance matrix of all transmission lines:

[0052] s=c+jω

[0053] Among them, s can be used to represent complex variables in the complex frequency domain, c can be used to represent the damping coefficient, j can be used to represent the imaginary unit in the complex domain, ω=(2m+1)π / (Ndt), N can be used to represent the total number of samples, N=T / dt, T can be used to represent the analytical calculation time length of this model, dt can be used to represent the analytical calculation step length, and m=0, 1, ... N-1. Further, the frequency-varying parameters of the transmission line are fitted with polynomial vectors based on rational function approximation, and the unit length shunt admittance y(s) and unit length series impedance z(s) of discrete frequencies of different types of transmission lines in the T-connected hybrid transmission line can be obtained.

[0054] In some embodiments of the present application, a self-admittance matrix and a mutual-admittance matrix are determined based on parallel admittance and series impedance, including: determining the self-admittance matrix and the mutual-admittance matrix based on parallel admittance, series impedance, and length information of the transmission line, wherein the length information is used to represent the actual length of the transmission line.

[0055] In this embodiment, after obtaining the parallel admittance and the series impedance, the self-admittance matrix and the mutual admittance matrix can be determined based on the parallel admittance, the series impedance, and the length information of the transmission line. The length information can be used to represent the actual length of the transmission line, which can be represented by l.

[0056] Optionally, after obtaining the unit length shunt admittance y(s) and unit length series impedance z(s) of different types of transmission lines at discrete frequencies, the complex domain self-admittance submatrix y of each node in the system can be calculated according to the actual line length: s (s) and the line mutual admittance submatrix y m (s), including the target transmission line, the transmission line of the back bus of the target transmission line measurement end, and the transmission line connected to the opposite bus of the target transmission line measurement end. Since the transmission line is a three-phase AC transmission line, the dimension of each sub-matrix is ​​3×3, and the complex domain self-admittance sub-matrix y s (s) and the line mutual admittance submatrix y m The calculation formula of (s) is:

[0057]

[0058] Among them, l can be used to represent the length of the transmission line, T can be used to represent the transformation matrix (for example, Clarke transformation matrix), γ(s) can be used to represent the propagation coefficient per unit length of the line in complex domain form, and the expression of γ(s) is:

[0059]

[0060] In some embodiments of the present application, step S104, based on the auto-admittance matrix and the mutual-admittance matrix, determines the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, including: based on the auto-admittance matrix and the mutual-admittance matrix, determining the impedance matrix of the transmission line system, wherein the impedance matrix is ​​used to represent the impedance characteristics of the transmission line system; based on the impedance matrix, determining the complex domain voltage information and the complex domain current information.

[0061] In this embodiment, based on the acquired autoadmittance matrix and mutual admittance matrix, the impedance matrix of the transmission line system can be determined. Further based on the determined impedance matrix, complex domain voltage information and complex domain current information can be determined. Among them, the impedance matrix can be used to represent the impedance characteristics of the transmission line system, which can be called a complex domain node impedance matrix.

[0062] Optionally, based on the acquired self-admittance matrix and mutual-admittance matrix, the admittance matrix of the transmission line system can be determined first, and the complex domain node impedance matrix of the system can be obtained by further inverting the admittance matrix.

[0063] In some embodiments of the present application, an impedance matrix of a transmission line system is determined based on a self-admittance matrix and a mutual-admittance matrix, including: determining an admittance matrix of the transmission line system based on the self-admittance matrix and the mutual-admittance matrix, wherein the admittance matrix is ​​used to represent the admittance characteristics of the transmission line system; and converting the admittance matrix to obtain an impedance matrix.

[0064] In this embodiment, based on the acquired self-admittance matrix and mutual-admittance matrix, the admittance matrix of the power transmission line system can be determined. The acquired admittance matrix is ​​further converted to obtain an impedance matrix. The admittance matrix can be used to represent the admittance characteristics of the power transmission line system.

[0065] Optionally, assuming that there are N nodes before the system fails, after the system fails, the fault point is used as a new node to construct a system admittance matrix of (N+1)×(N+1) sub-matrices. Further, according to the complex domain self-admittance sub-matrix y of each node determined s (s) and the line mutual admittance submatrix y m (s), if the system node has a power source or equivalent system impedance, or is connected to a load, construct the admittance matrix of the power source or equivalent system and the load, and sum it with the self-admittance submatrix of the corresponding node of the system admittance matrix to obtain the admittance matrix of the system after the fault. By inverting the admittance matrix of the system after the fault, the complex domain node impedance matrix of the system can be obtained.

[0066] In some embodiments of the present application, complex domain voltage information and complex domain current information are determined based on an impedance matrix, including: based on the impedance matrix, adding a fault excitation current at a fault node to obtain a fault excitation voltage, wherein the fault excitation current is used to represent current fluctuations occurring at the fault node, and the fault excitation voltage is used to represent voltage fluctuations occurring at the fault node; converting the fault excitation voltage to obtain complex domain short-circuit current information, wherein the complex domain short-circuit current information is used to represent the short-circuit current of the fault node in the complex frequency domain; and determining the complex domain voltage information and the complex domain current information based on the impedance matrix and the complex domain short-circuit current information.

[0067] In this embodiment, after determining the impedance matrix of the transmission line system, based on the determined impedance matrix, a fault excitation current can be added at the fault node to obtain a fault excitation voltage. After obtaining the fault excitation voltage, the fault excitation voltage is converted to obtain complex domain short-circuit current information. Further based on the determined impedance matrix and complex domain short-circuit current information, complex domain voltage information and complex domain current information can be determined. Among them, the fault excitation current can be used to represent the current fluctuation occurring at the fault node. The fault excitation voltage can be used to represent the voltage fluctuation occurring at the fault node. The complex domain short-circuit current information can be used to represent the short-circuit current of the fault node in the complex frequency domain, which can be called the complex domain short-circuit current at the fault port.

[0068] Optionally, after obtaining the impedance matrix, the fault excitation current is applied to the fault node, and the corresponding fault excitation voltage at each node can be determined. For the fault point, the time domain model of the excitation voltage source during the fault is:

[0069] Δu fΦ (t) = U f sin[α(t-t0)+θ fΦ ]ε(t-t0)

[0070] Among them, Δu fΦ (t) can be used to represent the time domain model of the excitation voltage source during a fault, U f It can be used to indicate the voltage amplitude at the fault point before the fault occurs, α can be used to indicate the grid angular frequency, t0 can be used to indicate the time when the fault occurs, and θ fΦ It can be used to represent the fault closing angle, and ε(t) can be used to represent the unit step signal.

[0071] Optionally, the above time domain expression is converted to the complex domain, and according to the boundary conditions of single-phase grounding fault, two-phase grounding fault, three-phase phase-to-phase fault and two-phase phase-to-phase fault, the complex domain composite sequence network under different fault types is constructed by using the symmetrical component transformation method, and the complex domain expression of the short-circuit current at the fault port is derived:

[0072]

[0073] in, It can be used to indicate the complex domain short-circuit current at the fault port. The superscript (type) can be used to indicate the fault type. ff(1) (s) can be used for the positive sequence complex domain self-impedance at the fault port, θ (type) They can be used to represent parameters related to the fault type, and their expressions are shown in Table 1:

[0074] Table 1 Fault type related parameters

[0075]

[0076] Among them, the value meaning of the fault type is: AG can be used to indicate that phase A is grounded, BG can be used to indicate that phase B is grounded, CG can be used to indicate that phase C is grounded, AB can be used to indicate that phase A and phase B are short-circuited, AC can be used to indicate that phase A and phase C are short-circuited, BC can be used to indicate that phase B and phase C are short-circuited, ABG can be used to indicate that phase A and phase B are short-circuited and grounded, ACG can be used to indicate that phase A and phase C are short-circuited and grounded, BCG can be used to indicate that phase B and phase C are short-circuited and grounded, and ABC can be used to indicate that phase A, phase B and phase C are short-circuited and grounded.

[0077] After obtaining the impedance matrix of the system after the fault and the complex domain expression of the short-circuit current at the fault port, the complex domain expressions of the fault transient voltage and fault transient current at any point in the transmission system can be determined by the following formula:

[0078]

[0079] in, The complex domain expression that can be used to represent the fault transient voltage at node J is: The complex domain expression that can be used to represent the fault transient voltage at node K is: It can be used to represent the complex domain expression of the fault transient current of node J. Node J and node K can be used to represent the nodes at both ends of line JK respectively. fJ (s) and Z fK (s) can be used to represent the mutual impedance between the faulty node f and node J, and between the faulty node f and node K in the complex domain node impedance matrix, y s (s) and y m (s) can be used to represent the self-admittance of node J and the mutual admittance between lines JK, respectively.

[0080] In some embodiments of the present application, step S106, converting the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, includes: performing a numerical inverse Laplace transform on the complex domain voltage information and the complex domain current information to obtain the time domain waveform information.

[0081] In this embodiment, after obtaining the complex domain voltage information and the complex domain current information, the complex domain voltage information and the complex domain current information can be numerically inverse Laplace transformed to obtain time domain waveform information. Optionally, after obtaining the complex domain expressions of the fault transient voltage and the fault transient current at the measuring point, the complex domain expressions of the fault transient voltage and the fault transient current can be quickly converted into time domain expressions by using numerical inverse Laplace transform, and the morphological characteristics of the line surge can be accurately restored. The complex domain value can be converted into the time domain value by the following formula:

[0082]

[0083] Among them, f(kΔt) and F(c+jω m ) can be used to represent time domain values ​​and complex domain values, s = c + jω m , c can be used to represent the damping coefficient, j can be used to represent the complex domain imaginary unit, w = (2m + 1) pi / (Ndt), N can be used to represent the number of samples, N = T / dt, T can be used to represent the analytical calculation time length of this model, dt can be used to represent the analytical calculation step length, m, k = 0, 1, ... N-1, σ m Can be used to represent the Hanning function, σ m The expression is as follows:

[0084]

[0085] In some embodiments of the present application, the method also includes: establishing an initial neural network model based on a residual convolutional neural network and a multi-head self-attention mechanism; training the initial neural network model based on time domain waveform information samples to obtain a neural network model, wherein the time domain waveform information samples are generated based on the time domain waveform information.

[0086] It should be noted that this embodiment can automatically generate time domain waveform information samples, that is, automatically generate waveform data samples, the fault distance is taken as points on the entire length of the fault line at intervals of 2 kilometers (km), the fault resistance (which can be expressed as R f The values ​​are 0, 50 ohms (Ω), 100 Ω, 150 Ω, and 200 Ω. The fault closing angle (which can be expressed as θ fΦThe values ​​of the angle (represented by angle 0, angle 30, angle 60, and angle 90) are 0 degrees (°), 30°, 60°, and 90°, and the values ​​of the fault types are AG, BG, CG, AB, BC, CA, ABG, BCG, CAG, and ABC. The above fault condition values ​​are traversed one by one through complex domain analytical calculation to generate the time domain waveforms of the three-phase fault transient voltage and current at the measuring point. The sampling frequency is 100 kilohertz (kHz), and the time window length is 5 milliseconds (ms) as the sample data.

[0087] In this embodiment, an initial neural network model combining a residual convolutional neural network and a multi-head self-attention mechanism is established, and three-phase fault transient voltage, transient current, zero-sequence voltage and zero-sequence current are selected as inputs of the initial neural network model. Due to the large differences in input data, in order to improve the accuracy of network training and fully learn the fault characteristics, it is necessary to first normalize the sample data (that is, the time domain waveform information sample):

[0088]

[0089] Among them, U abc Can be used to represent raw voltage data, U abc ' can be used to represent the normalized voltage sample data, I abc Can be used to represent raw current data, I abc 'Can be used to represent normalized current sample data, maxU abc 、maxI abc 、minU abc 、minI ab Can be used to represent custom values.

[0090] Optionally, different fault types have different input dimensions. When the fault type is a single-phase grounding fault, the fault phase voltage, fault phase current, zero-sequence voltage and zero-sequence current are taken as input, and the input dimension is 4; when the fault type is a two-phase phase-to-phase fault, the fault phase voltage and the fault phase current are both two-dimensional, and there is no zero sequence in the phase-to-phase short circuit, so the input dimension is 4; similarly, the input dimension of a two-phase phase-to-phase grounding fault is 6; the input dimension of a three-phase phase-to-phase short circuit is 6. Figure 2 is a schematic diagram of the structure of a residual convolutional neural network according to an embodiment of the present application, such as Figure 2As shown in the figure, the input sample data x is 500 in size and the input dimension is 4 or 6, that is, x(500×4 or 500×6). The input data is processed by normalization, multi-head self-attention mechanism, gated recurrent unit (GRU), dimension transformation, and deep residual network (Residual Network152, ResNet152). The data input to the gated recurrent unit is x(500×4 or 500×6), the data output by the gated recurrent unit is x(500×100), the data output by the dimension transformation is x(5×100×100), and the data output by the deep residual network is y(1000). After y(1000) is processed by three regularizations, linear layers, and activation layers (Relu), y(512), y(128), and y(16) are obtained respectively. Then, y(16) is processed by linear layers and activation layers (Sigmoid) to output y(1). Based on the above time domain waveform information samples, the initial neural network model is trained to obtain the neural network model, and the network parameters are updated according to the loss function results. The trained neural network model is tested using the test set, the segment error is calculated, and the model validity is verified.

[0091] In an embodiment of the present application, a self-admittance matrix and a mutual-admittance matrix of multiple nodes in a transmission line system are obtained, wherein the nodes include at least connection points and endpoints of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, the complex domain voltage information and the complex domain current information of the fault node in the transmission line system are determined, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; a neural network model is called to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is obtained based on the training of the time domain waveform information sample, and the position information is used to represent the position where the fault occurs in the transmission line, thereby achieving the technical effect of improving the accuracy of fault locating the transmission line, thereby solving the technical problem of low accuracy of fault locating the transmission line.

[0092] In order to facilitate those skilled in the art to better understand the technical solution of the present application, a specific embodiment is now described.

[0093] At present, as an important part of the power system, transmission lines are responsible for the important task of ensuring the stable supply of electricity. When a transmission line fails, it will cause a large-scale power outage, seriously affecting people's lives and social production. Therefore, it is extremely important to quickly and accurately find the fault point, reduce the difficulty of troubleshooting for line patrol workers, and shorten the fault repair time. When a short circuit occurs in the transmission line, its fault traveling wave reflects back and forth between the fault point and the line end point, forming multiple groups of traveling wave surges in a very short time, and the morphological characteristics of the fault traveling wave surge are closely related to the fault distance, fault transition resistance, fault type and fault line parameters. Therefore, it is of great significance to study the fault location method based on the recognition of fault traveling wave surge morphology, and the single-ended traveling wave location method does not require communication channels to transmit data, and has higher engineering implementation convenience.

[0094] In the related art, there are two main single-ended traveling wave fault distance measurement methods. One is active detection type, which is only applicable to permanent short circuits; the other is to calculate the fault distance based on the time difference between the traveling wave head arriving at the measuring point twice in succession. This method requires accurate identification of the traveling wave head and a very high sampling rate. However, when a short circuit occurs in the line, the fault traveling wave will reflect back and forth between the fault point of the line and the busbars at both ends of the line, and will continue to attenuate during the propagation process, thereby forming multiple surge characteristics with different shapes at the beginning of the fault. These surges have differences in time and amplitude characteristics. Due to the frequency-varying characteristics of the transmission line, surges of different names have different shapes. The above feature differences are closely related to the fault distance and fault transition resistance. The existing single-ended traveling wave distance measurement method only uses the arrival time characteristics of the first two surges, which not only misses the characteristics of the subsequent multiple traveling wave surges, but also misses the differences in amplitude and morphological characteristics of different traveling wave surges. In addition, similar fault location methods currently available that utilize the morphological characteristics of traveling wave surges mostly adopt methods based on electromagnetic transient simulation calculations. This method requires technicians to perform a large number of simulations to generate waveform samples, which is very time-consuming and labor-intensive, and thus has the technical problem of low accuracy in locating faults in transmission lines.

[0095] In order to solve the above problems, this application proposes a fault segmentation method for overhead hybrid cable transmission lines with branches based on a multi-head self-attention mechanism residual network with complex domain transient analytical calculation, and involves a single-ended fault location method based on fault wave surge morphology recognition of samples generated by complex domain analytical calculation. This embodiment makes full use of the differences in amplitude, time and morphological characteristics of wave surges of different orders to locate faults, enhance the anti-interference ability of fault location, and improve the accuracy.

[0096] This application adopts a complex domain analytical calculation method to establish a complex domain mathematical model of the transmission line, and then establishes a complex domain transfer function about the fault boundary and the measuring point, and uses different fault boundaries as input to obtain the fault phasor frequency function of the corresponding measuring point complex domain fault voltage or current, and obtains the corresponding fault transient time domain waveform data through numerical inverse Laplace transform. Since the computational efficiency of the method based on the analytical calculation is much higher than that of the electromagnetic transient simulation calculation, and the output waveform at the initial stage of the fault can accurately restore the morphological characteristics of the traveling wave surge, the method of generating traveling wave surge morphological samples based on complex domain analytical calculation can automatically form a large number of waveform data samples of different types, different positions, and different transition resistances in a very short time, which is conducive to the training and machine learning of the morphological characteristics of the waveform. Then, a neural network model combining a residual neural network with a multi-head self-attention mechanism is established, and a single-ended fault location method based on traveling wave surge morphological recognition is formed through the learning of a large amount of waveform data.

[0097] Figure 3 is a schematic diagram of a frequency-variable parameter model according to an embodiment of the present application, such as Figure 3 As shown in the figure, the frequency-variable parameter model of the T-connected hybrid transmission line system is established by electromagnetic transient simulation software, where Line 2, Line 3, and Line 4 are T-connected target lines, with a total length of 50km, 20km, and 10km, respectively. Line 5 is a transmission line connected to the busbar on the opposite side of the target transmission line measurement end, with a total length of 25km. Line 1 is a transmission line for the back busbar of the target transmission line measurement end, with a total length of 30km. Line 2 is 50km long, and the line types are 20km overhead line, 20km cable (indicated by the dotted line in the figure), and a mixed line of 10km overhead line. Line 3 and Line 4 are overhead lines of 20km and 10km, respectively. The outer radius of the overhead line combined conductor of line 4 is 0.0163454 meters (m), and the outer radius of the overhead line combined conductors of the other lines is 0.0203454m. The simulation outputs the frequency-dependent series impedance matrix and parallel admittance matrix of all transmission lines, and the frequency-dependent parameters of the transmission lines are fitted by polynomial vectors based on rational function approximation, and the unit length parallel admittance y(s) and unit length series impedance z(s) of discrete frequencies of different types of transmission lines in T-connected hybrid transmission lines are obtained. Among them, s=c+jw, c can be used to represent the damping coefficient, the expression of c is c=log10(N2) / T, j can be used to represent the complex domain imaginary unit, w=(2m+1)pi / (Ndt), N can be used to represent the total number of samples, N=T / dt, T can be used to represent the analytical calculation time length of this model, dt is the analytical calculation analytical step, m=0, 1, ...N-1.

[0098] After obtaining the unit length shunt admittance y(s) and unit length series impedance z(s) of different types of transmission lines at discrete frequencies, the complex domain self-admittance submatrix y of each node in the system can be calculated according to the actual line length: s (s) and the line mutual admittance submatrix y m (s), including the target transmission line, the transmission line of the back bus of the target transmission line measurement end, and the transmission line connected to the opposite bus of the target transmission line measurement end. Since it is a three-phase AC transmission line, the dimension of each sub-matrix is ​​3×3, which can be expressed by the following formula: s (s) and the line mutual admittance submatrix y m (s):

[0099]

[0100] Among them, l can be used to represent the length of the transmission line, T can be used to represent the Clarke transformation matrix, and γ(s) can be used to represent the propagation coefficient per unit length of the line in complex domain form, which is expressed as follows:

[0101]

[0102] Since there is a cable line in the middle of line 2, the overhead line is divided into three parts, so the line is considered to have 4 nodes. The system has 8 nodes before the failure. After the system failure, the fault point is used as the new node to construct a system admittance matrix of 9*9 sub-matrices. According to the complex domain self-admittance sub-matrix y of each node s (s) and the line mutual admittance submatrix y m (s), if the system node has the impedance of the power source or equivalent system, or is connected to the load, construct the admittance matrix of the power source or equivalent system and the load, and sum it with the self-admittance sub-matrix of the node corresponding to the system admittance matrix to obtain the admittance matrix of the system after the fault, and invert it to obtain the complex domain node impedance matrix of the system.

[0103] Using the impedance matrix obtained above, when the fault excitation current is applied to the fault node, the corresponding fault excitation voltage at each node can be calculated. For the fault point, the time domain model of the excitation voltage source during the fault is:

[0104] Δu fΦ (t) = U f sin[α(t-t0)+θ fΦ ]ε(t-t0)

[0105] Among them, Uf can be used to represent the voltage amplitude at the fault point before the fault occurs, α can be used to represent the grid angular frequency, t0 can be used to represent the time when the fault occurs, and θ fΦIt can be used to represent the fault closing angle, and ε(t) can be used to represent the unit step signal.

[0106] The above time domain expression is converted to the complex domain, and according to the boundary conditions of single-phase grounding fault, two-phase inter-phase grounding fault, three-phase phase-to-phase fault and two-phase phase-to-phase fault, the complex domain composite sequence network under different fault types is constructed by using the symmetrical component transformation method, and the complex domain expression of the short-circuit current at the fault port is derived:

[0107]

[0108] The superscript (type) can be used to indicate the fault type, Z ff(1) (s) can be used to represent the positive sequence complex domain self-impedance at the fault port, θ (type) They can be used to represent parameters related to the fault type, and their expressions are shown in Table 1.

[0109] Based on the impedance matrix of the post-fault system and the complex domain expression of the short-circuit current at the fault port obtained above, the complex domain expression of the fault transient voltage and current at any point in the transmission system can be calculated by the following formula:

[0110]

[0111] Wherein, node J and node K can be used to represent the nodes at both ends of line JK, respectively, ZfJ(s) and ZfK(s) can be used to represent the mutual impedance between fault node f and node J, fault node f and node K in the complex domain node impedance matrix, respectively, y s (s) and y m (s) can be used to represent the self-admittance of node J and the mutual admittance between lines JK. In this embodiment, 2 is an observation node. If the line fault occurs between lines 23, J is 2 and K is 9. If the line fault occurs in other line segments, the above formula needs to be used to calculate the fault transient voltage U3 at node 3. At this time, J is 2 and K is 3.

[0112] After obtaining the complex domain expressions of the fault transient voltage and current at the measuring point, the complex domain expressions of the fault transient voltage and current can be quickly converted into time domain expressions by using the numerical inverse Laplace transform, accurately restoring the morphological characteristics of the line surge. The complex domain values ​​can be converted into time domain values ​​by the following formula:

[0113]

[0114] Among them, f(kΔt) and F(c+jω m ) can be used to represent time domain values ​​and complex domain values, s = c + jω m, c can be used to represent the damping coefficient, j can be used to represent the complex domain imaginary unit, w = (2m + 1) pi / (Ndt), N can be used to represent the number of samples, N = T / dt, T can be used to represent the analytical calculation time length of this model, T is taken as 0.08 seconds (s), dt can be used to represent the analytical calculation step length, dt is taken as 10 microseconds (us), m, k = 0, 1, ... N-1, σ m Can be used to represent the Hanning function, σ m The expression is as follows:

[0115]

[0116] The waveform data samples are further automatically generated. The fault distance is taken as points along the entire length of the fault line at intervals of 2 km. The fault resistance R f The value is 0, 50Ω, 100Ω, 150Ω, 200Ω, fault closing angle θ fΦ The values ​​are 0°, 30°, 60°, and 90°, and the fault types are AG, BG, CG, AB, BC, CA, ABG, BCG, CAG, and ABC. The above fault condition values ​​are traversed one by one through complex domain analytical calculation to generate the three-phase fault transient voltage and current time domain waveforms at the measuring point. The sampling frequency is 100kHz, and the time window length is 5ms as the sample data.

[0117] This embodiment establishes a neural network model that combines a residual convolutional neural network with a multi-head self-attention mechanism, selects three-phase fault transient voltage, transient current, zero-sequence voltage and zero-sequence current as the input of the residual convolutional neural network, and adopts a multi-head self-attention mechanism to solve the problem of multi-dimensional input. The data samples are divided into training sets and test sets according to a certain ratio for machine learning. Due to the large differences in input data, in order to improve the accuracy of network training and fully learn the fault characteristics, the sample data is normalized:

[0118]

[0119] Among them, U abc Can be used to represent raw voltage data, U abc ' can be used to represent the normalized voltage sample data, I abc Can be used to represent raw current data, I abc ' can be used to represent the normalized current sample data. In this embodiment, the custom value minU abc =-maxU abc , minI ab =-maxI abc .

[0120] In this embodiment, different fault types have different input dimensions. When the fault type is a single-phase grounding fault, the fault phase voltage, fault phase current, zero-sequence voltage, and zero-sequence current are taken as inputs, and the input dimension is 4; when the fault type is a two-phase phase-to-phase fault, the fault phase voltage and the fault phase current are both 2-dimensional, and there is no zero sequence in the phase-to-phase short circuit, so the input dimension is 4; similarly, the input dimension of the two-phase phase-to-phase grounding fault is 6; the input dimension of the three-phase phase-to-phase short circuit is 6, and the specific structure of the residual convolutional neural network used is as follows: Figure 2 As shown. It should be noted that this embodiment performs model training according to different fault types, namely single-phase grounding fault, two-phase short circuit, two-phase short circuit to ground, and three-phase short circuit. The training set is further input into the residual convolutional neural network, and the network parameters are updated according to the loss function result. The trained residual convolutional neural network model is tested with the test set, and the segmentation error is calculated to verify the effectiveness of the model.

[0121] The electromagnetic transient simulation model is used to randomly generate 100 fault transient voltage and current waveform data, which are input into the trained model in sequence. The model's fixed-segment output value is compared with the actual fixed-segment number. The fault fixed-segment number on line 2 is set to 0, the fault fixed-segment number on line 3 is set to 1, and the fault fixed-segment number on line 4 is set to 2. The results are shown in the following table:

[0122] Table 2 Fault transient voltage and current waveform data

[0123]

[0124]

[0125]

[0126]

[0127]

[0128] From Table 2, we can see that except for the data results of 56, 66 and 79, which were misjudged, the above model can accurately judge the segmentation results of the remaining data, with an accuracy rate of 97%, which proves the effectiveness of the model.

[0129] In an embodiment of the present application, a self-admittance matrix and a mutual-admittance matrix of multiple nodes in a transmission line system are obtained, wherein the nodes include at least connection points and endpoints of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, the complex domain voltage information and the complex domain current information of the fault node in the transmission line system are determined, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; the complex domain voltage information and the complex domain current information are converted to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; a neural network model is called to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is obtained based on the training of the time domain waveform information sample, and the position information is used to represent the position where the fault occurs in the transmission line, thereby achieving the technical effect of improving the accuracy of fault locating the transmission line, thereby solving the technical problem of low accuracy of fault locating the transmission line.

[0130] The embodiment of the present application also provides a transmission line fault determination device. It should be noted that the transmission line fault determination device of this embodiment can be used to execute the transmission line fault determination method of the embodiment of the present invention.

[0131] Figure 4 is a schematic diagram of a structure of a transmission line fault determination device according to an embodiment of the present application, such as Figure 4 As shown, the transmission line fault determination device 400 may include: an acquisition unit 402 , a first determination unit 404 , a conversion unit 406 , and a second determination unit 408 .

[0132] The acquisition unit 402 is used to acquire the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the node includes at least the connection point and the end point of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the node, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes.

[0133] The first determination unit 404 is used to determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system based on the auto-admittance matrix and the mutual-admittance matrix, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain.

[0134] The conversion unit 406 is used to convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node.

[0135] The second determination unit 408 is used to call the neural network model to analyze the time domain waveform information to obtain the location information of the fault node, wherein the neural network model is trained based on the time domain waveform information samples, and the location information is used to indicate the location where the fault occurs in the transmission line.

[0136] Optionally, the method also includes: a first acquisition unit, used to acquire the parallel admittance and series impedance of the transmission line, wherein the parallel admittance is used to represent the admittance characteristics of the transmission line per unit length, and the series impedance is used to represent the impedance characteristics of the transmission line per unit length; the acquisition unit 402 includes: a first determination module, used to determine the self-admittance matrix and the mutual admittance matrix based on the parallel admittance and the series impedance.

[0137] Optionally, the first acquisition unit includes: utilizing a frequency-variant parameter model of a transmission line system, a fitting module for performing polynomial vector fitting on frequency-variant parameters of the transmission line to obtain parallel admittance and series impedance, wherein the frequency-variant parameters are used to represent line parameters that vary with frequency.

[0138] Optionally, the first determination module includes: a first determination submodule, used to determine the self-admittance matrix and the mutual-admittance matrix based on the parallel admittance, the series impedance, and the length information of the transmission line, wherein the length information is used to represent the actual length of the transmission line.

[0139] Optionally, the first determination unit 404 includes: a second determination module, used to determine the impedance matrix of the transmission line system based on the auto-admittance matrix and the mutual-admittance matrix, wherein the impedance matrix is ​​used to represent the impedance characteristics of the transmission line system; and a third determination module, used to determine complex domain voltage information and complex domain current information based on the impedance matrix.

[0140] Optionally, the second determination module includes: a second determination submodule, used to determine the admittance matrix of the transmission line system based on the self-admittance matrix and the mutual-admittance matrix, wherein the admittance matrix is ​​used to represent the admittance characteristics of the transmission line system; and convert the admittance matrix to obtain an impedance matrix.

[0141] Optionally, the third determination module includes: an adding submodule, used to add a fault excitation current at the fault node based on the impedance matrix to obtain a fault excitation voltage, wherein the fault excitation current is used to represent the current fluctuation occurring at the fault node, and the fault excitation voltage is used to represent the voltage fluctuation occurring at the fault node; a conversion submodule, used to convert the fault excitation voltage to obtain complex domain short-circuit current information, wherein the complex domain short-circuit current information is used to represent the short-circuit current of the fault node in the complex frequency domain; a third determination submodule, used to determine the complex domain voltage information and the complex domain current information based on the impedance matrix and the complex domain short-circuit current information.

[0142] Optionally, the conversion unit 406 includes: a conversion module, configured to perform a numerical inverse Laplace transform on the complex domain voltage information and the complex domain current information to obtain time domain waveform information.

[0143] Optionally, the method also includes: establishing a unit for establishing an initial neural network model based on a residual convolutional neural network and a multi-head self-attention mechanism; training the initial neural network model based on time domain waveform information samples to obtain a neural network model, wherein the time domain waveform information samples are generated based on the time domain waveform information.

[0144] In the device, the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system are obtained by the acquisition unit 402, wherein the nodes include at least the connection points and the end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes. The complex domain voltage information and the complex domain current information of the fault node in the transmission line system are determined by the first determination unit 404 based on the self-admittance matrix and the mutual-admittance matrix, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain. The complex domain voltage information and the complex domain current information are converted by the conversion unit 406 to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node. The second determination unit 408 calls a neural network model to analyze the time domain waveform information to obtain the location information of the fault node, wherein the neural network model is trained based on the time domain waveform information samples, and the location information is used to indicate the location where the fault occurs in the transmission line, thereby achieving the technical effect of improving the accuracy of fault locating the transmission line, thereby solving the technical problem of low accuracy of fault locating the transmission line.

[0145] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, the non-volatile storage medium including a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any one of the methods for determining a fault of a power transmission line.

[0146] Specifically, the above storage medium is used to store program instructions for the following functions to implement the following functions:

[0147] Obtain the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the nodes include at least the connection points and the end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; call the neural network model to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is trained based on the time domain waveform information sample, and the position information is used to represent the location where the fault occurs in the transmission line.

[0148] Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above-mentioned contents. More specific examples of the above-mentioned storage medium may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above-mentioned contents.

[0149] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program. When the program is run, the method for determining a fault of a power transmission line in an embodiment of the present invention is executed.

[0150] In an exemplary embodiment of the present application, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, it implements any of the above-mentioned methods for determining a fault of a power transmission line.

[0151] Optionally, the computer program may implement the following steps when executed by a processor:

[0152] Obtain the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the nodes include at least the connection points and the end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; call the neural network model to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is trained based on the time domain waveform information sample, and the position information is used to represent the location where the fault occurs in the transmission line.

[0153] In an exemplary embodiment of the present application, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and the computer program is configured to execute any of the above-mentioned transmission line fault determination methods when running.

[0154] Optionally, the computer program may implement the following steps when executed by a processor:

[0155] Obtain the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the nodes include at least the connection points and the end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; call the neural network model to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is trained based on the time domain waveform information sample, and the position information is used to represent the location where the fault occurs in the transmission line.

[0156] In an exemplary embodiment of the present application, a computer program is further provided. The computer program is configured to execute the steps in any of the above method embodiments when running.

[0157] Optionally, the computer program may implement the following steps when executed by a processor:

[0158] Obtain the self-admittance matrix and the mutual-admittance matrix of multiple nodes in the transmission line system, wherein the nodes include at least the connection points and the end points of the transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between multiple nodes; based on the self-admittance matrix and the mutual-admittance matrix, determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; convert the complex domain voltage information and the complex domain current information to obtain the time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; call the neural network model to analyze the time domain waveform information to obtain the position information of the fault node, wherein the neural network model is trained based on the time domain waveform information sample, and the position information is used to represent the location where the fault occurs in the transmission line.

[0159] According to an embodiment of the present application, an electronic device is provided, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned transmission line fault determination methods.

[0160] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0161] Figure 5 is a schematic block diagram of an electronic device according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0162] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0163] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0164] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a fault determination method for a power transmission line. For example, in some embodiments, the fault determination method for a power transmission line may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the fault determination method for the power transmission line described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the transmission line fault determination method in any other appropriate manner (for example, by means of firmware).

[0165] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0167] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0169] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0170] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0171] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0172] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0175] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0177] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a fault of a power transmission line, characterized in that: include: Obtaining a self-admittance matrix and a mutual-admittance matrix of a plurality of nodes in a power transmission line system, wherein the nodes include at least connection points and end points of a power transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between the plurality of nodes; Based on the autoadmittance matrix and the mutual admittance matrix, determine the complex domain voltage information and the complex domain current information of the fault node in the transmission line system, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; Converting the complex domain voltage information and the complex domain current information to obtain time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; A neural network model is called to analyze the time domain waveform information to obtain the location information of the fault node, wherein the neural network model is trained based on time domain waveform information samples, and the location information is used to indicate the location where the fault occurs in the transmission line.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a shunt admittance and a series impedance of the transmission line, wherein the shunt admittance is used to represent the admittance characteristic of the transmission line per unit length, and the series impedance is used to represent the impedance characteristic of the transmission line per unit length; Obtaining a self-admittance matrix and a mutual-admittance matrix of a plurality of nodes in a power transmission line system includes: determining the self-admittance matrix and the mutual-admittance matrix based on the shunt admittance and the series impedance.

3. The method according to claim 2, characterized in that Obtaining the parallel admittance and series impedance of the transmission line, including: The frequency-variant parameter model of the transmission line system is used to perform polynomial vector fitting on the frequency-variant parameters of the transmission line to obtain the shunt admittance and the series impedance, wherein the frequency-variant parameters are used to represent line parameters that vary with frequency.

4. The method according to claim 2, characterized in that: Determining the self-admittance matrix and the mutual-admittance matrix based on the shunt admittance and the series impedance includes: The self-admittance matrix and the mutual-admittance matrix are determined based on the shunt admittance, the series impedance, and the length information of the transmission line, wherein the length information is used to represent the actual length of the transmission line.

5. The method according to claim 1, characterized in that Determining complex domain voltage information and complex domain current information of a fault node in the power transmission line system based on the auto-admittance matrix and the mutual-admittance matrix includes: Determining an impedance matrix of the power transmission line system based on the auto-admittance matrix and the mutual-admittance matrix, wherein the impedance matrix is ​​used to represent the impedance characteristics of the power transmission line system; Based on the impedance matrix, the complex domain voltage information and the complex domain current information are determined.

6. The method according to claim 5, characterized in that Determining an impedance matrix of the power transmission line system based on the auto-admittance matrix and the mutual-admittance matrix includes: Determining an admittance matrix of the power transmission line system based on the self-admittance matrix and the mutual-admittance matrix, wherein the admittance matrix is ​​used to represent the admittance characteristics of the power transmission line system; The admittance matrix is ​​transformed to obtain the impedance matrix.

7. The method according to claim 5, characterized in that Determining the complex domain voltage information and the complex domain current information based on the impedance matrix includes: Based on the impedance matrix, a fault excitation current is added at the fault node to obtain a fault excitation voltage, wherein the fault excitation current is used to represent the current fluctuation occurring on the fault node, and the fault excitation voltage is used to represent the voltage fluctuation occurring on the fault node; Converting the fault excitation voltage to obtain complex domain short-circuit current information, wherein the complex domain short-circuit current information is used to represent the short-circuit current of the fault node in the complex frequency domain; The complex domain voltage information and the complex domain current information are determined based on the impedance matrix and the complex domain short-circuit current information.

8. The method according to any one of claims 1 to 7, characterized in that Converting the complex domain voltage information and the complex domain current information to obtain time domain waveform information of the fault node includes: Performing a numerical inverse Laplace transform on the complex domain voltage information and the complex domain current information to obtain the time domain waveform information.

9. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Based on the residual convolutional neural network and multi-head self-attention mechanism, an initial neural network model is established; Based on the time domain waveform information samples, the initial neural network model is trained to obtain the neural network model, wherein the time domain waveform information samples are generated based on the time domain waveform information.

10. A transmission line fault determination device, characterized in that: include: An acquisition unit, used to acquire a self-admittance matrix and a mutual-admittance matrix of a plurality of nodes in a transmission line system, wherein the nodes include at least a connection point and an end point of a transmission line, the self-admittance matrix is ​​used to represent the admittance characteristics of the nodes, and the mutual-admittance matrix is ​​used to represent the admittance characteristics associated between the plurality of nodes; A first determining unit, configured to determine complex domain voltage information and complex domain current information of a fault node in the power transmission line system based on the autoadmittance matrix and the mutual admittance matrix, wherein the complex domain voltage information is used to represent the voltage of the fault node in the complex frequency domain, and the complex domain current information is used to represent the current of the fault node in the complex frequency domain; A conversion unit, used to convert the complex domain voltage information and the complex domain current information to obtain time domain waveform information of the fault node, wherein the time domain waveform information is used to represent the voltage waveform and the current waveform of the fault node; The second determination unit is used to call a neural network model to analyze the time domain waveform information to obtain the location information of the fault node, wherein the neural network model is trained based on the time domain waveform information samples, and the location information is used to indicate the location where the fault occurs in the transmission line.

Images