Fault positioning method, device and equipment for power distribution network, medium and program

Abstract

The invention discloses a power distribution network fault positioning method, device and equipment, a medium and a program. The method comprises the following steps: when it is detected that a test line in a power distribution network satisfies a fault positioning trigger condition, determining zero-sequence current signals of each test point on the test line in a plurality of set power frequency periods; for each test point, determining an instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point in each set power frequency period; determining a fault probability vector of the test line according to the instantaneous energy density sequence of each test point; and determining a fault occurrence position of the test line according to a test point topological structure of the test line and the fault probability vector. According to the technical scheme, the problem that the positioning effect of the high-resistance fault of the power distribution network is poor in the prior art can be solved, and the high-resistance fault positioning efficiency and accuracy of the power distribution network are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technology, and in particular to a method, system, device and storage medium for locating a fault in a distribution network. Background Art

[0002] In power systems, distribution networks typically directly serve a vast number of users, characterized by wide coverage, complex operating environments, and widespread impact from faults. Therefore, rapid and accurate fault location after a distribution network fault can ensure power supply continuity, shorten outage duration, and improve user satisfaction.

[0003] Existing methods for locating distribution network faults mainly include the steady-state component method and the signal injection method. However, methods based on steady-state quantities (such as the zero-sequence current amplitude and phase ratio method and the active component method) rely on the steady-state characteristics of the power frequency, but are easily affected by the compensation degree of the arc suppression coil, the size of the transition resistance, unstable arcs, and the inherent imbalance of the system. They have low sensitivity, resulting in a high risk of misjudgment or refusal to operate under high-resistance faults and complex working conditions, and poor overall effect. The principle of the signal injection method is direct, and fault detection is achieved by injecting a dedicated signal. However, it requires the additional installation of a signal source and detection device, which greatly increases the system investment and maintenance costs. It is also limited in effect for high-resistance faults that are difficult to detect, such as transient faults or tree barriers.

[0004] Therefore, the existing technical solutions have poor effects on high-resistance fault location in complex distribution network environments, and there is an urgent need to provide a fast and reliable high-resistance fault location method. Summary of the Invention

[0005] The present invention provides a fault location method, device, equipment, medium and program for a distribution network. The method determines the fault probability vector of a test line based on the instantaneous energy density sequence of each test point, and determines the fault location of the test line in combination with the test point topology of the test line, so as to solve the problem of poor high-resistance fault location effect in the prior art and provide a fast and reliable high-resistance fault location method.

[0006] According to a first aspect of the present invention, a method for locating a fault in a distribution network is provided, characterized by comprising:

[0007] When it is detected that a test line in the distribution network meets a fault location trigger condition, the zero-sequence current signal of each test point on the test line under multiple set power frequency cycles is determined;

[0008] For each of the test points, determining the instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles;

[0009] Determining a fault probability vector of the test line according to the instantaneous energy density sequence of each of the test points;

[0010] A fault location of the test line is determined according to the test point topology of the test line and the fault probability vector.

[0011] According to a second aspect of the present invention, a fault location device for a distribution network is provided, characterized by comprising:

[0012] A signal acquisition module is used to determine the zero-sequence current signals of each test point on the test line under multiple set power frequency cycles when detecting that the test line in the distribution network meets the fault location trigger condition;

[0013] A first determining module is configured to determine, for each of the test points, an instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles;

[0014] A second determination module is configured to determine a fault probability vector of the test line according to the instantaneous energy density sequence of each test point;

[0015] A fault location module is used to determine a fault location of the test line according to the test point topology structure of the test line and the fault probability vector.

[0016] According to a third aspect of the present invention, there is provided an electronic device, comprising:

[0017] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network high-resistance fault locating method described in any embodiment of the present invention.

[0018] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution network high-resistance fault location method described in any embodiment of the present invention when executed.

[0019] According to a fifth aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for locating a high-resistance fault in a distribution network according to any embodiment of the present invention is implemented.

[0020] The technical solution of the embodiment of the present invention determines the zero-sequence current signals respectively possessed by each test point on the test line under multiple set power frequency cycles when detecting that the test line in the distribution network meets the fault location trigger condition. Then, for each test point, the instantaneous energy density sequence of the test point is determined according to the zero-sequence current signal of the test point under each set power frequency cycle. Furthermore, the fault probability vector of the test line is determined according to the instantaneous energy density sequence of each test point. Finally, the fault location of the test line is determined according to the test point topology structure of the test line and the fault probability vector. This can realize the determination of the fault location based on the fault probability vector of the test line determined based on the instantaneous energy density sequence of each test point and the test point topology structure of the test line, thereby solving the problem of poor high-resistance fault location effect in the prior art and improving the efficiency and accuracy of high-resistance fault location in the distribution network.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flow chart of a method for locating a fault in a distribution network according to a first embodiment of the present invention;

[0024] Figure 2 This is a flow chart of a method for locating a fault in a distribution network according to a second embodiment of the present invention;

[0025] Figure 3 This is a flow chart of a method for locating a fault in a distribution network according to a third embodiment of the present invention;

[0026] Figure 4 2 is a schematic structural diagram of a fault location device for a distribution network according to a fourth embodiment of the present invention;

[0027] Figure 5 The present invention is a schematic diagram of the structure of an electronic device for implementing the method for locating a fault in a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention 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 numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes 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.

[0030] Example 1

[0031] Figure 1 A flow chart of a method for locating a fault in a distribution network is provided for the first embodiment of the present invention. This embodiment is applicable to locating the location of a fault in a distribution network. The method can be performed by a fault locating device for the distribution network. The fault locating device for the distribution network can be implemented in the form of hardware and / or software. The fault locating device for the distribution network can be configured in a control platform of the distribution network. Figure 1 As shown, the method includes:

[0032] S101: When it is detected that a test line in a distribution network meets a fault location triggering condition, zero-sequence current signals respectively possessed by each test point on the test line under a plurality of set power frequency cycles are determined.

[0033] The test line can be any one or more transmission lines in a distribution network. Fault location triggering conditions can include detecting a fault in the test circuit or detecting a voltage change on the test line exceeding a set threshold. Test points can be pre-set test locations on the test line, such as multiple test locations evenly distributed along the transmission line or the installation locations of multiple pre-installed current sensors.

[0034] The set power frequency cycle can be a pre-set time period corresponding to the power frequency cycle for collecting the zero-sequence current signal. For example, the two power frequency cycles after the power frequency cycle in which the fault occurs can be used as the set power frequency cycle for collecting the zero-sequence current signal. It should be noted that the power frequency cycle generally refers to the period corresponding to the rated frequency of the alternating current power of the power system. For example, in China, the rated frequency of alternating current is 50 Hz, and the corresponding power frequency cycle is 0.02 seconds. The zero-sequence current signal can be obtained by a collection device installed at the test point.

[0035] For example, when a circuit fault is detected on a test line in the distribution network, or when a voltage change on the test line exceeds a set threshold, it can be determined that the test line in the distribution network meets the fault location triggering condition. Consequently, the zero-sequence current signal of each test point in the test line can be acquired during a time period corresponding to at least one preset power frequency cycle using acquisition devices at each pre-set test point.

[0036] Optionally, a method for detecting whether a test line in the distribution network meets a fault location triggering condition may specifically include:

[0037] Determine a current bus zero-sequence voltage value of the test line in a current power frequency cycle, and obtain a previous bus zero-sequence voltage value of the test line in a previous power frequency cycle;

[0038] Determine a voltage change between the current bus zero-sequence voltage value and the previous bus zero-sequence voltage value;

[0039] If the voltage change value exceeds a set threshold, it is determined that the test limit meets a fault location trigger condition, and the current power frequency cycle is determined as a fault occurrence cycle of the test line.

[0040] Among them, the current power frequency cycle may refer to the power frequency cycle in which the test circuit is detected. The current bus zero-sequence voltage value may be the zero-sequence voltage value of the bus corresponding to the test circuit under the current power frequency cycle. The previous power frequency cycle may refer to the previous power frequency cycle before the current power frequency cycle. The previous bus zero-sequence voltage value may be the zero-sequence voltage value of the bus corresponding to the test circuit under the previous power frequency cycle. The set threshold value may be pre-set by a technician based on experience, and is used to determine whether the voltage change value of the test circuit under two adjacent power frequency cycles exceeds the limit. If it exceeds the limit, it can be determined that the test circuit has failed.

[0041] For example, a voltage measuring device installed on the bus corresponding to the test circuit can be used to collect the bus zero-sequence voltage value of the test circuit in each power frequency cycle in real time and record it. Therefore, when collecting the current bus zero-sequence voltage value of the test circuit in the current power frequency cycle, the previous bus zero-sequence voltage value of the test circuit in the previous power frequency cycle can be obtained simultaneously.

[0042] Then, based on the overall change of the current bus zero-sequence voltage value and the previous bus zero-sequence voltage value in one power frequency cycle, the voltage change value between the current bus zero-sequence voltage value and the previous bus zero-sequence voltage value can be determined. For example, the voltage change can be defined as: △U0=u0(t)-u0(t-2T n ), where t is a time variable, u0(t) is the bus zero-sequence voltage at each moment, and T n It can be the power frequency period (the Chinese power grid takes 0.02s).

[0043] Finally, it can be determined whether the voltage change value exceeds the set threshold. If it exceeds, it means that the test circuit has a fault. It can be determined that the test limit meets the fault location trigger condition, and the current power frequency cycle is determined as the fault occurrence cycle of the test line. For example, set the bus zero sequence voltage U at the current moment N One tenth of the value is the preset threshold, then when △U0>0.1U N , it can be determined that the test limit meets the fault location triggering condition.

[0044] S102 : For each of the test points, determine the instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles.

[0045] Among them, the instantaneous energy density sequence can characterize the energy changes of zero-sequence current in the time domain and frequency domain, and can be used to analyze fault information in the distribution network.

[0046] For example, after determining the zero-sequence current signals of each test point on the test circuit under multiple set power frequency cycles, an energy density function of the test point can be constructed based on the signal analysis of each zero-sequence current signal of a certain test point under multiple set power frequency cycles, so that the instantaneous energy density of the test point at each moment and the instantaneous energy density sequence of the test point can be determined. It should be noted that the energy density function of the test point can be a correlation function of the time and energy density of the test point, which is used to calculate the instantaneous energy density of the test point at each moment. Furthermore, the instantaneous energy density sequence of the test point can be generated by arranging the instantaneous energy density of the test point at each moment based on the time sequence.

[0047] S103 : Determine a fault probability vector of the test circuit according to the instantaneous energy density sequence of each test point.

[0048] The fault probability vector may represent the probability of a fault occurring in each test segment in the test circuit, and each test segment may be determined based on the spatial position relationship of each test point on the test circuit and the electrical connection sequence of the test points in the circuit.

[0049] For example, the instantaneous energy density sequence of each test point can be input into a pre-trained convolutional neural network to determine the probability of failure in each test segment, thereby obtaining a failure probability vector for the test circuit. It should be noted that the convolutional neural network can be any network model in the prior art that can be used to generate a failure probability vector for a test circuit, and this embodiment does not limit the specific implementation and training method of the convolutional neural network.

[0050] S104 : Determine a fault location of the test line according to the test point topology of the test line and the fault probability vector.

[0051] The test point topology of the test circuit may be the spatial position relationship of each test point on the test circuit and the electrical connection sequence of the test points in the test circuit, and may be used to divide the test segments on the test circuit.

[0052] For example, the spatial position of each test segment in the test line in the distribution network can be determined based on the test point topology structure of the test line. Then, the maximum fault probability determined from the fault probability vector can be combined to determine the test segment corresponding to the maximum fault probability, and the spatial position of the test segment corresponding to the maximum fault probability can be determined as the fault occurrence location.

[0053] The above technical solution of this embodiment, when detecting that a test line in a distribution network meets a fault location trigger condition, determines the zero-sequence current signals respectively possessed by each test point on the test line under multiple set power frequency cycles, and then, for each test point, determines the instantaneous energy density sequence of the test point based on the zero-sequence current signal of the test point under each set power frequency cycle. Furthermore, based on the instantaneous energy density sequence of each test point, determines the fault probability vector of the test line. Finally, based on the test point topology structure of the test line and the fault probability vector, determines the fault location of the test line. This can achieve the determination of the fault location based on the fault probability vector of the test line determined by the instantaneous energy density sequence of each test point and the test point topology structure of the test line, thereby solving the problem of poor high-resistance fault location effect in the prior art and improving the efficiency and accuracy of high-resistance fault location in the distribution network.

[0054] Optionally, based on the above embodiment, this embodiment proposes an optional embodiment. This optional embodiment can further optimize step S101 in the above embodiment, when detecting that the test line in the distribution network meets the fault location trigger condition, determining the zero-sequence current signals respectively possessed by each test point on the test line under multiple set power frequency cycles, and can include:

[0055] The power frequency cycle before the fault occurrence cycle, the next power frequency cycle and the next next power frequency cycle after the fault occurrence cycle are respectively recorded as set power frequency cycles;

[0056] By providing a fault recording device corresponding to each test point on the test line, the zero-sequence current signal of each test point under each set power frequency cycle is obtained.

[0057] The fault occurrence cycle may refer to the power frequency cycle in which the test circuit fault is detected. The previous power frequency cycle may refer to the power frequency cycle immediately preceding the power frequency cycle in which the test circuit fault is detected. The next power frequency cycle may refer to the power frequency cycle immediately following the power frequency cycle in which the test circuit fault is detected. The next next power frequency cycle may refer to the power frequency cycle immediately following the power frequency cycle in which the test circuit fault is detected.

[0058] For example, the power frequency cycle before the fault occurrence cycle, the next power frequency cycle and the next lower power frequency cycle of the fault occurrence cycle can be pre-set as the set power frequency cycles for collecting zero-sequence current signals, and then the fault recording device installed at each test point in the distribution network can be started to collect the zero-sequence current signals of each test point 1 power frequency cycle before the fault occurs and 2 power frequency cycles after the fault occurs.

[0059] Optionally, based on the above embodiment, this embodiment proposes an optional embodiment. This optional embodiment can further optimize step S103 in the above embodiment, determining the fault probability vector of the test line based on the instantaneous energy density sequence of each test point, and can include:

[0060] Dividing each of the test points into an upstream test point and a downstream test point;

[0061] Inputting the upstream instantaneous energy density sequence of each upstream test point into the first channel network module in the network model, processing each upstream instantaneous energy density sequence through the convolution layer in the first channel network module, and obtaining the first test line local feature of each upstream test point;

[0062] Inputting the downstream instantaneous energy density sequence of each downstream test point into the second channel network module in the network model, processing each downstream instantaneous energy density sequence through the convolution layer in the second channel network module, and obtaining the second test line local feature of each downstream test point;

[0063] The first test line local feature and the second test line local feature are fused to generate a test line fusion feature, and the test line fusion feature is processed through a fully connected layer in the network model to generate a fault probability vector of the test line.

[0064] The upstream test point may be a test point located upstream of the distribution network that is pre-classified based on the actual location of the test point or the power transmission sequence. The downstream test point may be a test point located downstream of the distribution network that is pre-classified based on the actual location of the test point or the power transmission sequence.

[0065] It should be noted that the network model can be a pre-built two-channel convolutional neural network, and the structural parameters for constructing the two-channel convolutional neural network can include: the number of channels of the convolution layer, the activation function, the maximum pooling of the pooling layer, the number of neurons in the fully connected layer, and the activation function of the output layer.

[0066] Furthermore, the dual-channel convolutional neural network can perform convolution processing on data separately through two convolution channels, and further process the result of the fusion of the convolution results of the two convolution channels through a fully connected layer. The first channel network module and the second channel network module can be two convolution channels in the dual-channel convolutional neural network. The first test line local feature of the upstream test point and the second test line local feature of the downstream test point can be the result of convolution processing of the upstream instantaneous energy density sequence and the downstream instantaneous energy density sequence.

[0067] For example, the test points located upstream and downstream of the distribution network are divided in advance based on the actual location of the test points or the transmission sequence, and then the instantaneous energy density sequence of the test points can be divided into the upstream instantaneous energy density sequence E up (t) and the downstream instantaneous energy density sequence E down (t). Then, the upstream instantaneous energy density sequence E up (t) and the downstream instantaneous energy density sequence E down (t) The two channel network modules of the network model are inputted respectively, and the convolution layer is used for convolution processing to obtain the corresponding two test line local features, and the two test line local features are fused to obtain the test line fusion feature, which can be processed by the fully connected layer in the network model to generate the test line fault probability vector P = [p1, p2, ..., p S ], where s is the total number of test segments.

[0068] Example 2

[0069] Figure 2 This is a flow chart of a fault location method for a distribution network provided in the second embodiment of the present invention. This embodiment can further improve step S102 of the first embodiment above, and determine the instantaneous energy density sequence of each test point according to the zero-sequence current signal of the test point under each set power frequency cycle. Figure 2 As shown, the method includes:

[0070] S201: When it is detected that a test line in a distribution network meets a fault location triggering condition, the zero-sequence current signals respectively possessed by each test point on the test line under a plurality of set power frequency cycles are determined.

[0071] S202 : performing signal analysis on the zero-sequence current signal of the test point in each set power frequency cycle in the frequency domain to obtain a transient characteristic sub-band component corresponding to each zero-sequence current signal.

[0072] The transient characteristic sub-band component may be a local frequency component related to the fault separated from the zero-sequence current signal in the frequency domain.

[0073] For example, after obtaining the zero-sequence current signals of each test point under multiple set power frequency cycles, the transient characteristic sub-band components related to the fault can be separated from the zero-sequence current signal through frequency domain segmentation technology based on each zero-sequence current signal, or the zero-sequence current signal can be decomposed using dynamic spectrum segmentation adaptive decomposition (DSSD) to obtain a series of transient characteristic sub-band components.

[0074] Optionally, performing signal analysis on the zero-sequence current signal of the test point in each set power frequency cycle in the frequency domain to obtain the transient characteristic sub-band component corresponding to each zero-sequence current signal may include:

[0075] Performing Fourier transformation on each of the zero-sequence current signals to obtain a corresponding Fourier spectrum;

[0076] For each of the Fourier spectrums, extracting a set of spectrum maximum point positions and a set of spectrum minimum point positions of the Fourier spectrum according to a set number of modes;

[0077] Determine the frequency band splitting points according to the set objective function and the set of frequency spectrum maximum point positions and the set of frequency spectrum minimum point positions;

[0078] Generating frequency band intervals having the same number of modes according to the frequency band division points;

[0079] An inverse Fourier transform is performed on the Fourier spectrum in each of the frequency band intervals to generate transient characteristic sub-band components corresponding to the zero-sequence current signal, the number of which is the same as the frequency band intervals.

[0080] The modal number can be used to control the number of frequency band divisions. A spectrum maximum point location set can refer to points in the extracted spectrum where energy is significantly higher than the surrounding frequencies. A spectrum minimum point location set can refer to points in the extracted spectrum where energy is significantly lower than the surrounding frequencies. Frequency band division points can refer to points used to divide the frequency bands, determined based on the spectrum maximum point location set and the spectrum minimum point location set.

[0081] For example, the measured zero-sequence current signal can be subjected to a fast Fourier transform to obtain the Fourier spectrum I k (f):I k (f) = F{i k (t)}, where F is the Fourier transform operator and f is the frequency.

[0082] For each Fourier spectrum I k (f) The set of spectral maximum point positions and the set of spectral minimum point positions of the Fourier spectrum can be extracted according to the set number of modes.

[0083] For example, the modal number N can be initialized to 2, then the extreme point search range N∈[2,N max ](N max =10).

[0084] Assume that the set of spectrum maximum point positions P is extracted max and the minimum point set P min It can be:

[0085]

[0086] Where: M and L are the number of extreme points respectively.

[0087] The envelope spectrum entropy can be minimized by continuous iteration. When L>5N, the maximum value points are connected to generate the envelope curve and P is updated. min and L. Until L≤5N, the minimum envelope spectrum entropy value can be obtained. At this time, the first N minimum points with the largest amplitude can be extracted from the minimum point set Then calculate the midpoint position of adjacent points

[0088] can be minimized by mid -f cut ‖ is the set objective function, determine the split point f cut .

[0089] According to the split point f cut , can be divided and generated into various frequency band intervals Ω j : Where j is the number of frequency band intervals, and They are the interval edge values ​​of the divided frequency band intervals respectively.

[0090] Finally, each frequency band interval Ω can be calculated based on the following formula: j Perform inverse Fourier transform to obtain transient characteristic subband component (TSC):

[0091]

[0092] Among them, A j (t) is the amplitude function, is the phase angle function, is the frequency band indicator function. Furthermore, the frequency band indicator function satisfies: That is, the band indicator function If the frequency belongs to the divided frequency band interval, its value is 1, otherwise, its value is 0.

[0093] S203: Construct a time-frequency energy aggregation spectrum of the test point based on each of the transient characteristic sub-band components.

[0094] For example, the time-frequency energy aggregation spectrum can be defined based on the transient characteristic sub-band component as follows:

[0095]

[0096] Among them, H k (f,t)=A k (t)I k (f), H k (f) is the time-frequency energy aggregation spectrum, A j (t) is the instantaneous amplitude of the transient characteristic subband component, I k (f) is the amplitude frequency of the transient characteristic subband component, H k (f, t) can represent the weighting of the amplitude in the time domain and frequency domain.

[0097] S204 : Determine the instantaneous energy density sequence of the test point according to the time-frequency energy aggregation spectrum and a set energy density function.

[0098] For example, the instantaneous energy density function E is set to k (t):

[0099]

[0100] Among them, λ = 0.5 is the weight coefficient, H k (f) is the time-frequency energy aggregation spectrum, f max and f min is the time-frequency energy aggregation spectrum H k (f) The lower and upper limits of the effective frequency band, namely:

[0101] Furthermore, the time-frequency energy aggregation spectrum H determined above can be k (f), combined with the set instantaneous energy density function E k(t), the instantaneous energy density of the test point at each moment can be determined, and then, the instantaneous energy density sequence of the test point can be generated by arranging the instantaneous energy density of the test point at each moment based on the time sequence.

[0102] S205 : Determine a fault probability vector of the test circuit according to the instantaneous energy density sequence of each test point.

[0103] S206 : Determine a fault location of the test line according to the test point topology of the test line and the fault probability vector.

[0104] The above technical solution of this embodiment performs signal analysis on the zero-sequence current signal of the test point in each set power frequency cycle in the frequency domain to obtain the transient characteristic sub-band components corresponding to each zero-sequence current signal, constructs the time-frequency energy aggregation spectrum of the test point based on each transient characteristic sub-band component, and finally determines the instantaneous energy density sequence of the test point based on the time-frequency energy aggregation spectrum combined with the set energy density function. It can accurately separate and extract the transient characteristic sub-band components of the weak transient signal based on dynamic spectrum segmentation adaptive decomposition (DSSD), accurately capture the transient characteristics of weak high-resistance faults, and thus generate an accurate instantaneous energy density sequence of the test point, which can improve the accuracy of identifying and locating high-resistance faults.

[0105] Example 3

[0106] Figure 3 This is a flowchart of a method for locating a fault in a distribution network provided by the third embodiment of the present invention. This embodiment can further improve step S104 of the first embodiment above, which determines the fault location of the test line based on the test point topology structure of the test line and the fault probability vector. Figure 3 As shown, the method includes:

[0107] S301: When it is detected that a test line in a distribution network meets a fault location triggering condition, the zero-sequence current signals respectively possessed by each test point on the test line under a plurality of set power frequency cycles are determined.

[0108] S302 : For each of the test points, determine the instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles.

[0109] S303: Determine a fault probability vector of the test line according to the instantaneous energy density sequence of each test point.

[0110] S304: Determine test segments included in the test circuit according to the test point topology.

[0111] For example, the test points at the edge of the test segment in the test circuit can be determined based on the spatial position relationship of the test points in the test point topology and their electrical connection sequence in the test circuit, thereby determining the test segments included in the test circuit.

[0112] S305 : Determine the failure probability value corresponding to each of the test segments according to the failure probability vector, and determine the target test segment corresponding to the maximum failure probability value.

[0113] The target test segment may refer to a test segment with the highest probability of failure among all test segments.

[0114] For example, the test segment s corresponding to the maximum probability in the fault probability vector P can be determined based on the fault probability values ​​corresponding to the test segments in the fault probability vector. * =argmax s p s as the target test fragment segment.

[0115] S306 : When the maximum fault probability value reaches a set probability threshold, determine the target test segment as the fault occurrence location of the test line.

[0116] The set probability threshold may be set in advance by a technician based on experience, and may be used to determine whether the probability of a failure of a target test segment meets a confidence requirement.

[0117] For example, assuming that the probability threshold is set to 0.9, when the failure probability of the target test segment is greater than 0.9, it means that the failure probability of the target test segment meets the confidence requirement, and the target test segment can be directly determined as the failure location of the test line.

[0118] S307 : When the maximum fault probability value does not reach a set probability threshold, perform a redundancy check on the target test segment, and after the redundancy check passes, determine the target test segment as the fault occurrence location of the test line.

[0119] The redundancy check may be a pre-established check mechanism for further determining whether the target test segment can be used as the location where the fault occurs.

[0120] For example, assuming a probability threshold of 0.9 is set, when the probability of failure of the target test segment is less than 0.9, it indicates that the probability of failure of the target test segment does not meet the confidence requirement, and further redundancy check is required. For example, the failure probability vector of the test line is recalculated, and the location of the failure in the test line is determined. If the results of the recalculation of the failure probability vector of the test line and the results of the failure location of the test line remain unchanged, it can be determined that the target test segment can be determined as the location of the failure in the test line through the redundancy check.

[0121] Optionally, performing redundancy check on the target test segment may further include:

[0122] Acquire adjacent test segments of the target test segment, and determine an integrated energy density ratio formed by each of the adjacent test segments;

[0123] The target test segment is verified according to the energy density integral ratio, and when the energy density integral ratio is greater than a set ratio, it is determined that the redundancy verification is passed.

[0124] For example, the energy density integral ratio R formed by each adjacent test segment can be determined. ij :

[0125] R ij =∫E i (t)dt / ∫E j (t)dt

[0126] Among them, ∫E i (t)dt is the capability density integral of target test segment i, ∫E j (t)dt is the capacity density integral of test segment j, and i and j represent two adjacent test segments.

[0127] When R ij When the ratio is greater than the set value, it can be determined that the target test segment i has passed the redundancy check, and the fault is determined to have occurred in the target test segment i.

[0128] The above technical solution of this embodiment, after determining the fault probability vector of the test line, further determines the test segments included in the test line according to the test point topology structure, and then determines the fault probability value corresponding to each test segment according to the fault probability vector, and determines the target test segment corresponding to the maximum fault probability value. When the maximum fault probability value reaches the set probability threshold, the target test segment is determined as the fault location of the test line. When the maximum fault probability value does not reach the set probability threshold, the target test segment is redundancy checked and after passing the redundancy check, the target test segment is determined as the fault location of the test line, thereby achieving further verification of the target test segment with the highest fault probability based on the redundancy check mechanism, further improving the accuracy and safety of fault location.

[0129] Figure 4 This is a schematic diagram of the structure of a fault location device for a distribution network provided by the third embodiment of the present invention. Figure 4 As shown, the device includes:

[0130] The signal acquisition module 41 can be used to determine the zero-sequence current signals of each test point on the test line under multiple set power frequency cycles when detecting that the test line in the distribution network meets the fault location triggering condition;

[0131] The first determining module 42 may be configured to determine, for each of the test points, an instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles;

[0132] A second determining module 43 may be configured to determine a fault probability vector of the test circuit according to the instantaneous energy density sequence of each test point;

[0133] The fault location module 44 may be configured to determine a fault location of the test line according to the test point topology of the test line and the fault probability vector.

[0134] The above technical solution of this embodiment, when detecting that a test line in a distribution network meets a fault location trigger condition, determines the zero-sequence current signals respectively possessed by each test point on the test line under multiple set power frequency cycles, and then, for each test point, determines the instantaneous energy density sequence of the test point based on the zero-sequence current signal of the test point under each set power frequency cycle. Furthermore, based on the instantaneous energy density sequence of each test point, determines the fault probability vector of the test line. Finally, based on the test point topology structure of the test line and the fault probability vector, determines the fault location of the test line. This can achieve the determination of the fault location based on the fault probability vector of the test line determined by the instantaneous energy density sequence of each test point and the test point topology structure of the test line, thereby solving the problem of poor high-resistance fault location effect in the prior art and improving the efficiency and accuracy of high-resistance fault location in the distribution network.

[0135] Optionally, a method for detecting whether a test line in the distribution network meets a fault location triggering condition may include:

[0136] Determine a current bus zero-sequence voltage value of the test line in a current power frequency cycle, and obtain a previous bus zero-sequence voltage value of the test line in a previous power frequency cycle;

[0137] Determine a voltage change between the current bus zero-sequence voltage value and the previous bus zero-sequence voltage value;

[0138] If the voltage change value exceeds a set threshold, it is determined that the test limit meets a fault location trigger condition, and the current power frequency cycle is determined as a fault occurrence cycle of the test line.

[0139] Optionally, the signal acquisition module 41 may be specifically configured to record the power frequency cycle before the fault occurrence cycle, and the next power frequency cycle and the next next power frequency cycle after the fault occurrence cycle as the set power frequency cycle;

[0140] By providing a fault recording device corresponding to each test point on the test line, the zero-sequence current signal of each test point under each set power frequency cycle is obtained.

[0141] Optionally, the first determining module 42 further includes:

[0142] The component acquisition unit can be used to perform signal analysis on the zero-sequence current signal of the test point at each set power frequency cycle in the frequency domain to obtain the transient characteristic sub-band component corresponding to each zero-sequence current signal;

[0143] A construction unit may be configured to construct a time-frequency energy aggregation spectrum of the test point based on each of the transient characteristic sub-band components;

[0144] The sequence generating unit may be configured to determine the instantaneous energy density sequence of the test point according to the time-frequency energy aggregation spectrum in combination with a set energy density function.

[0145] Optionally, the component acquisition unit may be specifically configured to perform Fourier transform on each of the zero-sequence current signals to obtain a corresponding Fourier spectrum;

[0146] For each of the Fourier spectrums, extracting a set of spectrum maximum point positions and a set of spectrum minimum point positions of the Fourier spectrum according to a set number of modes;

[0147] Determine the frequency band splitting points according to the set objective function and the set of frequency spectrum maximum point positions and the set of frequency spectrum minimum point positions;

[0148] Generating frequency band intervals having the same number of modes according to the frequency band division points;

[0149] An inverse Fourier transform is performed on the Fourier spectrum in each of the frequency band intervals to generate transient characteristic sub-band components corresponding to the zero-sequence current signal, the number of which is the same as the frequency band intervals.

[0150] Optionally, the second determining module 43 may be specifically configured to divide each of the test points into upstream test points and downstream test points;

[0151] Inputting the upstream instantaneous energy density sequence of each upstream test point into the first channel network module in the network model, processing each upstream instantaneous energy density sequence through the convolution layer in the first channel network module, and obtaining the first test line local feature of each upstream test point;

[0152] Inputting the downstream instantaneous energy density sequence of each downstream test point into the second channel network module in the network model, processing each downstream instantaneous energy density sequence through the convolution layer in the second channel network module, and obtaining the second test line local feature of each downstream test point;

[0153] The first test line local feature and the second test line local feature are fused to generate a test line fusion feature, and the test line fusion feature is processed through a fully connected layer in the network model to generate a fault probability vector of the test line.

[0154] Optionally, the fault location module 44 may further include:

[0155] A first determining unit may be configured to determine a test segment included in the test circuit according to the test point topology;

[0156] A second determining unit may be configured to determine, based on the failure probability vector, a failure probability value corresponding to each of the test segments, and determine a target test segment corresponding to a maximum failure probability value;

[0157] a location determination unit, configured to determine the target test segment as the location where the fault occurs in the test line when the maximum fault probability value reaches a set probability threshold;

[0158] The redundancy check unit may be configured to perform a redundancy check on the target test segment when the maximum fault probability value does not reach a set probability threshold, and determine the target test segment as the fault location of the test line after the target test segment passes the redundancy check.

[0159] Optionally, performing redundancy check on the target test segment may include:

[0160] Acquire adjacent test segments of the target test segment, and determine an integrated energy density ratio formed by each of the adjacent test segments;

[0161] The target test segment is verified according to the energy density integral ratio, and when the energy density integral ratio is greater than a set ratio, it is determined that the redundancy verification is passed.

[0162] The distribution network fault location device provided in the embodiment of the present invention can execute the distribution network fault location method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0163] Example 5

[0164] Figure 5 A schematic diagram of the structure of an electronic device 50 that can be used to implement an embodiment of the present invention is shown. 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or claimed herein.

[0165] like Figure 5As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc., which is communicatively connected to the at least one processor 51. The memory stores a computer program that can be executed by the at least one processor. The processor 51 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 into the random access memory (RAM) 53. Various programs and data required for the operation of the electronic device 50 can also be stored in the RAM 53. The processor 51, ROM 52, and RAM 53 are connected to each other via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0166] Multiple components in the electronic device 50 are connected to the I / O interface 55, including an input unit 56, such as a keyboard, a mouse, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a magnetic disk, an optical disk, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0167] The processor 51 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as the method for locating a fault in a distribution network.

[0168] In some embodiments, the method for locating a fault in a power distribution network can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as a storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 11, one or more steps of the method for locating a fault in a power distribution network described above can be performed. Alternatively, in other embodiments, the processor 51 can be configured to execute the method for locating a fault in a power distribution network by any other appropriate means (e.g., by means of firmware).

[0169] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0170] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can 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 foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 electronic device. 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).

[0173] The systems and techniques described herein can 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 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 can 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), a blockchain network, and the Internet.

[0174] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0175] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0176] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for locating a fault in a distribution network, characterized in that: include: When it is detected that a test line in the distribution network meets a fault location trigger condition, the zero-sequence current signal of each test point on the test line under multiple set power frequency cycles is determined; For each of the test points, determining the instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles; Determining a fault probability vector of the test line according to the instantaneous energy density sequence of each of the test points; A fault location of the test line is determined according to the test point topology of the test line and the fault probability vector.

2. The method according to claim 1, characterized in that Methods for detecting whether a test line in a distribution network meets the fault location triggering conditions include: Determine a current bus zero-sequence voltage value of the test line in a current power frequency cycle, and obtain a previous bus zero-sequence voltage value of the test line in a previous power frequency cycle; Determine a voltage change between the current bus zero-sequence voltage value and the previous bus zero-sequence voltage value; If the voltage change value exceeds a set threshold, it is determined that the test limit meets a fault location trigger condition, and the current power frequency cycle is determined as a fault occurrence cycle of the test line.

3. The method according to claim 1, characterized in that Determining the zero-sequence current signals respectively possessed by each test point on the test line under a plurality of set power frequency cycles includes: The power frequency cycle before the fault occurrence cycle, the next power frequency cycle and the next next power frequency cycle after the fault occurrence cycle are respectively recorded as set power frequency cycles; By providing a fault recording device corresponding to each test point on the test line, the zero-sequence current signal of each test point under each set power frequency cycle is obtained.

4. The method according to claim 1, wherein Determining the instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles includes: Performing signal analysis on the zero-sequence current signal of the test point at each set power frequency cycle in the frequency domain to obtain transient characteristic sub-band components corresponding to each zero-sequence current signal; Constructing a time-frequency energy aggregation spectrum of the test point based on each of the transient characteristic sub-band components; The instantaneous energy density sequence of the test point is determined according to the time-frequency energy aggregation spectrum combined with a set energy density function.

5. The method according to claim 4, characterized in that The performing signal analysis on the zero-sequence current signal of the test point in each set power frequency cycle in the frequency domain to obtain the transient characteristic sub-band component corresponding to each zero-sequence current signal includes: Performing Fourier transformation on each of the zero-sequence current signals to obtain a corresponding Fourier spectrum; For each of the Fourier spectrums, extracting a set of spectrum maximum point positions and a set of spectrum minimum point positions of the Fourier spectrum according to a set number of modes; Determine the frequency band splitting points according to the set objective function and the set of frequency spectrum maximum point positions and the set of frequency spectrum minimum point positions; Generating frequency band intervals having the same number of modes according to the frequency band division points; An inverse Fourier transform is performed on the Fourier spectrum in each of the frequency band intervals to generate transient characteristic sub-band components corresponding to the zero-sequence current signal, the number of which is the same as the frequency band intervals.

6. The method according to claim 1, characterized in that Determining the fault probability vector of the test line according to the instantaneous energy density sequence of each test point includes: Dividing each of the test points into an upstream test point and a downstream test point; Inputting the upstream instantaneous energy density sequence of each upstream test point into the first channel network module in the network model, processing each upstream instantaneous energy density sequence through the convolution layer in the first channel network module, and obtaining the first test line local feature of each upstream test point; Inputting the downstream instantaneous energy density sequence of each downstream test point into the second channel network module in the network model, processing each downstream instantaneous energy density sequence through the convolution layer in the second channel network module, and obtaining the second test line local feature of each downstream test point; The first test line local feature and the second test line local feature are fused to generate a test line fusion feature, and the test line fusion feature is processed through a fully connected layer in the network model to generate a fault probability vector of the test line.

7. The method according to claim 1, characterized in that The determining the fault location of the test line according to the test point topology structure of the test line and the fault probability vector includes: Determining a test segment included in the test circuit according to the test point topology structure; Determining the failure probability value corresponding to each of the test segments according to the failure probability vector, and determining the target test segment corresponding to the maximum failure probability value; When the maximum fault probability value reaches a set probability threshold, determining the target test segment as the fault occurrence location of the test line; When the maximum fault probability value does not reach a set probability threshold, a redundancy check is performed on the target test segment, and after the redundancy check passes, the target test segment is determined as the fault occurrence location of the test line.

8. The method according to claim 7, characterized in that Performing redundancy checking on the target test segment includes: Acquire adjacent test segments of the target test segment, and determine an integrated energy density ratio formed by each of the adjacent test segments; The target test segment is verified according to the energy density integral ratio, and when the energy density integral ratio is greater than a set ratio, it is determined that the redundancy verification is passed.

9. A fault location device for a distribution network, characterized in that: include: A signal acquisition module is used to determine the zero-sequence current signals of each test point on the test line under multiple set power frequency cycles when detecting that the test line in the distribution network meets the fault location trigger condition; A first determining module is configured to determine, for each of the test points, an instantaneous energy density sequence of the test point according to the zero-sequence current signal of the test point under each of the set power frequency cycles; A second determination module is configured to determine a fault probability vector of the test line according to the instantaneous energy density sequence of each test point; A fault location module is used to determine a fault location of the test line according to the test point topology structure of the test line and the fault probability vector.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network high-resistance fault locating method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution network high-resistance fault location method according to any one of claims 1 to 8 when executed.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the method for locating a high-resistance fault in a distribution network according to any one of claims 1 to 8.

Images