Power distribution network fault detection and positioning method and device, computer device and storage medium

Abstract

The application relates to a power distribution network fault detection and positioning method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring power grid data of at least one power grid device on a power distribution network; determining a fault condition of the power distribution network according to the power grid data of each power grid device; acquiring fault data of at least one power grid device on the power distribution network in the case that the power distribution network has a fault; and determining a fault position of the power distribution network where the fault occurs according to the fault data of each power grid device. The method can improve the utilization degree of power grid data, and further improve the fault identification and positioning accuracy and efficiency.

Description

Technical Field

[0001] This application relates to the field of power distribution network technology, and in particular to a method, apparatus, computer equipment, and storage medium for detecting and locating faults in power distribution networks. Background Technology

[0002] In power systems, distribution networks are an indispensable and important component. Distribution network automation specifically refers to the monitoring of the operating status of distribution systems based on the primary network structure and related equipment, with distribution automation systems as the core, and utilizing various communication methods. It also involves the scientific and standardized management of distribution systems through information integration with other systems. However, existing terminal waveform recordings of line faults and disturbances lack remote transmission capabilities or cannot be reliably transmitted. The lack of on-site data for pre-warning, post-fault inversion, and fault location at the master station leads to low efficiency in distribution network operation and maintenance, insufficient technical support capabilities, and low utilization of synchronous measurement big data in the distribution network. This results in difficulties in accurate fault identification and location. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, device, computer equipment, and storage medium for fault detection and location in power distribution networks that can accurately locate faults, in order to address the aforementioned technical problems.

[0004] Firstly, this application provides a method for detecting and locating faults in a power distribution network, including:

[0005] Acquire grid data from at least one grid device on the distribution network;

[0006] Determine the fault status of the distribution network based on the power grid data of each power grid device;

[0007] In the event of a fault in the distribution network, acquire fault data of at least one power grid device on the distribution network;

[0008] Based on the fault data of each power grid device, determine the location of the fault in the distribution network.

[0009] In one embodiment, the fault status of the distribution network is determined based on the grid data of each grid device, including:

[0010] For each power grid device, its operating characteristics are determined based on the power grid data.

[0011] Based on the operating characteristics of each power grid device, determine the fault reference values ​​for the distribution network;

[0012] A fault is determined to have occurred in the distribution network when the fault reference value of the distribution network is greater than the preset reference threshold.

[0013] In one embodiment, fault reference values ​​for the distribution network are determined based on the operating characteristics of each power grid device, including:

[0014] For each power grid device, the initial reference value is determined based on the operating characteristics of the power grid device and the operating characteristics of the adjacent power grid devices.

[0015] Based on the initial reference values ​​of each power grid device and the preset values ​​of the distribution network topology, the fault reference values ​​of the distribution network are determined.

[0016] In one embodiment, determining the initial reference value of the power grid equipment based on its operating characteristics and the operating characteristics of adjacent power grid equipment includes:

[0017] Based on the operating characteristics of the power grid equipment, determine the first parameter value of the power grid equipment; and for each adjacent power grid equipment, determine the first parameter value of the adjacent power grid equipment based on the operating characteristics of the adjacent power grid equipment.

[0018] The initial reference value of the power grid equipment is determined based on the first parameter value of the power grid equipment, the preset power grid weight, the first parameter value of the adjacent power grid equipment, and the preset adjacent weight.

[0019] In one embodiment, determining the fault location on the distribution network based on fault data from various power grid devices includes:

[0020] The power grid equipment corresponding to the fault data is designated as the faulty equipment.

[0021] For each faulty device, the target location corresponding to the faulty device is determined based on the location of the faulty device on the distribution network and the traveling wave signal at at least one measurement point within a preset range of the location of the faulty device.

[0022] The target location corresponding to the faulty equipment is taken as the fault location of the fault in the distribution network;

[0023] Among them, the faulty device is used to receive the power grid data measured by each measurement point connected to the faulty device; the traveling wave signal is a high-frequency signal output by the measurement point when it detects an abnormality in the power grid data; the target location is the location where the fault occurs within a preset range of the location of the faulty device.

[0024] In one embodiment, the method further includes:

[0025] The fault data of each faulty device is input into a pre-trained fault classification model to obtain the fault type of the faulty device at the corresponding target location;

[0026] When the fault type is a preset type, the operating status of the faulty device is adjusted according to the operating status of the adjacent power grid devices.

[0027] Secondly, this application also provides a power distribution network fault detection and location device, comprising:

[0028] The data acquisition module is used to acquire power grid data from at least one power grid device on the distribution network.

[0029] The fault determination module is used to determine the fault status of the distribution network based on the power grid data of each power grid device.

[0030] The fault acquisition module is used to acquire fault data of at least one power grid device in the power distribution network when a fault occurs in the power distribution network.

[0031] The location determination module is used to determine the location of the fault in the distribution network based on the fault data of each power grid device.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] Acquire grid data from at least one grid device on the distribution network;

[0034] Determine the fault status of the distribution network based on the power grid data of each power grid device;

[0035] In the event of a fault in the distribution network, acquire fault data of at least one power grid device on the distribution network;

[0036] Based on the fault data of each power grid device, determine the location of the fault in the distribution network.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Acquire grid data from at least one grid device on the distribution network;

[0039] Determine the fault status of the distribution network based on the power grid data of each power grid device;

[0040] In the event of a fault in the distribution network, acquire fault data of at least one power grid device on the distribution network;

[0041] Based on the fault data of each power grid device, determine the location of the fault in the distribution network.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] Acquire grid data from at least one grid device on the distribution network;

[0044] Determine the fault status of the distribution network based on the power grid data of each power grid device;

[0045] In the event of a fault in the distribution network, acquire fault data of at least one power grid device on the distribution network;

[0046] Based on the fault data of each power grid device, determine the location of the fault in the distribution network.

[0047] The aforementioned method, apparatus, computer equipment, and storage medium for detecting and locating faults in a distribution network acquire grid data from at least one grid device in the distribution network; determine the fault status of the distribution network based on the grid data from each grid device; acquire fault data from at least one grid device in the distribution network when a fault occurs; and determine the location of the fault in the distribution network based on the fault data from each grid device. This embodiment can improve the utilization of synchronized grid data, thereby improving the accuracy and efficiency of fault identification and location. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is an application environment diagram of a power distribution network fault detection and location method provided in this embodiment;

[0050] Figure 2A This is a flowchart illustrating a method for detecting and locating faults in a power distribution network, as provided in this embodiment.

[0051] Figure 2B This embodiment provides a chip structure diagram;

[0052] Figure 3 This is a flowchart illustrating a step for determining a fault reference value, as provided in this embodiment.

[0053] Figure 4 This is a flowchart illustrating a fault adjustment method provided in this embodiment;

[0054] Figure 5This is a structural block diagram of a power distribution network fault detection and location device provided in this embodiment;

[0055] Figure 6 This is an internal structural diagram of a computer device provided in this embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The power distribution network fault detection and location method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on the cloud or other network servers. The computer device acquires grid data from at least one grid device in the distribution network; determines the fault status of the distribution network based on the grid data of each grid device; acquires fault data from at least one grid device in the distribution network when a fault occurs; and determines the fault location in the distribution network based on the fault data of each grid device. The computer device can be either a terminal or a server. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0058] In one exemplary embodiment, such as Figure 2A As shown, a method for detecting and locating faults in a power distribution network is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps S201 to S204. Wherein:

[0059] S201 Obtains grid data from at least one grid device on the distribution network.

[0060] The power grid data may include at least one of voltage, current, frequency, phase, and harmonics.

[0061] In some embodiments, the topology type corresponding to the distribution network is obtained, and the topology of the distribution network is determined according to the topology type (e.g., based on design drawings or on-site surveys); the grid equipment and lines in the distribution network are determined according to the topology; the number of grid equipment on the distribution network is determined according to the number of grid equipment in the distribution network; the grid data of each grid equipment is acquired in real time based on the FPGA, and the PPS signal output by the GPS is acquired; in response to the PPS signal being in a normal state, the soft clock is synchronized using the PPS signal; in response to the synchronization being completed, the sampling time scale of the grid data acquired for each grid equipment is determined based on the interpolation mechanism, so as to synchronize the grid data corresponding to each grid equipment in time and obtain the synchronized grid data.

[0062] The topology of a distribution network includes radial, ring, mesh, and multi-terminal network topologies. The topology type for a specific region can be obtained from design drawings or on-site surveys. Network equipment describes the location of equipment within the distribution network, while lines describe the connections between these devices. Equipment information also includes location information, specifically coordinates. Network equipment typically refers to the connection points of distribution equipment or loads, such as cable terminations, distribution boxes, and switchgear.

[0063] For example, the interpolation mechanism includes: when the local clock is latched into the interpolation RAM buffer, a pulse is output to latch a synchronous clock count, and the latching time is defined as T1; a fixed time delay between the latching time and the actual sampling time is defined as Td; in the interpolation module, when the interpolation module uses the interpolation time, a pulse for latching and the interpolation time are output as T2; based on the latching time T1, the fixed time delay Td and the interpolation time T2, the sampling synchronization time of the interpolated telemetry value is calculated as: Tsmp = T1 - Td + T2, where Tsmp is the sampling time stamp.

[0064] For example, such as Figure 2BAs shown, an FPGA (Field Programmable Gate Array) is a chip whose internal structure can be reprogrammed to achieve different functions. It is a dedicated hardware chip responsible for acquiring voltage and current sampling data. Internal code needs to be written to run it, and its acquisition efficiency is higher than that of a CPU acquiring data itself. After acquisition, the data is transmitted to the CPU (main chip) for further processing via an external communication interface. GPS / BD is a GPS module that outputs the year, month, day, hour, minute, and second, as well as a PPS signal for the CPU and FPGA. The PPS signal is a precise level signal output once per second. The FPGA uses a soft clock to count within one second, with a soft clock resolution of 1μs, to time-stamp the sampled data. The soft clock is defined as a 32-bit unit. The counting range is 0-999999, and it automatically resets to zero after overflowing. The soft clock is a timing value maintained by the software code itself without hardware dependence. The sampling time register is used to latch the sampling time of the first sample in each group of sampled data. When the main chip reads the sampled value, it reads the sampling time synchronously. The value of the register is updated before the FPGA sends the sampling interrupt. The FPGA needs to notify the CPU to take away the data after it collects some data. The notification method is interrupt. The sampling time register is a storage unit that stores the value of the soft clock. When the CPU retrieves the sampled data from the FPGA, it will also retrieve this value. In this way, the data reaching the CPU has a time stamp synchronized with the satellite, that is, the sampling time stamp.

[0065] Furthermore, the soft clock implementation method includes: after power-on, before the FPGA acquires the PPS signal, the soft clock does not count and remains in a state of all zeros. When the PPS signal is captured for the first time, the quality of the PPS signal is first judged. If the PPS signal is normal, the soft clock is synchronized with the PPS signal for time synchronization; otherwise, time synchronization is not performed until the PPS signal is normal. After successful time synchronization, if the PPS signal is lost or its quality is not satisfactory, the soft time will no longer be synchronized with the PPS and will enter a timekeeping state until the second pulse returns to normal. The time synchronization state and the PPS state are written into the register address respectively and can be read by the CPU.

[0066] Furthermore, the method for calculating the sampling time stamp includes: In the FPGA, a 32-bit local relative clock counter (hereinafter referred to as "local clock") is set up for interpolation synchronization calculation; when the local clock is latched into the interpolation RAM buffer, a pulse is output to latch a synchronization clock count, this time is denoted as T1; there is a fixed time delay between the latching time and the actual sampling time, denoted as Td; in the interpolation module, when the interpolation module uses the interpolation time (the default value is 7812), a pulse (for latching) and the interpolation time are output, denoted as T2. The interpolation time is the sampling frequency calculated by the CPU based on the voltage, which can change at any time. Latching prevents the change in interpolation time from introducing calculation errors. From the above, the sampling synchronization time of the interpolated telemetry value can be calculated as: Tsmp = T1 - Td + T2, where Tsmp is the synchronization time for writing to the register, which is the sampling time stamp.

[0067] S202 determines the fault status of the distribution network based on the power grid data of each power grid device.

[0068] In one optional embodiment, fault features are extracted from the synchronization data corresponding to each terminal based on short-time Fourier transform. The fault features from all the synchronization data corresponding to all terminals are then fused. Based on the fusion result, abnormal fluctuations are detected to determine whether a fault has occurred in the distribution network. The fault features include: voltage dips, instantaneous current peak values, and harmonic distortion.

[0069] In another alternative embodiment, for each power grid device, the operating characteristics of the power grid device are determined based on the power grid data of the power grid device; the fault reference value of the distribution network is determined based on the operating characteristics of each power grid device; and if the fault reference value of the distribution network is greater than a preset reference threshold, it is determined that a fault has occurred in the distribution network.

[0070] S203 acquires fault data of at least one power grid device in the distribution network in the event of a fault in the distribution network.

[0071] In some embodiments, in the event of a fault in the distribution network, the computer device acquires fault data of at least one power grid device on the distribution network.

[0072] S204 determines the location of the fault in the distribution network based on the fault data of each power grid device.

[0073] In one optional embodiment, based on fault data, the location information of the power grid equipment collecting the fault data is determined; the traveling wave signals of multiple measurement points within a preset range corresponding to the location information of the power grid equipment and the time difference of the traveling wave signals arriving at the collection points are obtained, and a system of linear equations is constructed. The traveling wave method is based on the traveling wave theory, that is, when a fault occurs in the distribution network, the fault point will generate sudden changes in voltage and current, forming a traveling wave. These traveling waves propagate along the transmission line at near the speed of light. By installing traveling wave detection devices at different locations, these traveling wave signals can be captured, and then fault location can be performed. For example, assuming there are n measurement points, each measurement point records the arrival time of the traveling wave signal as v, and the signal propagation speed is v, then the linear equation is d, where d is the distance from the fault point to the i-th measurement point; the system of linear equations is solved to obtain the location information of the fault point. The constructed system of linear equations can be solved by methods such as Gaussian elimination to obtain the specific location of the fault point, such as the distance from the starting point of the line.

[0074] In another optional embodiment, the power grid equipment corresponding to the fault data is designated as the fault equipment; for each fault equipment, a target location corresponding to the fault equipment is determined based on the location of the fault equipment on the distribution network and the traveling wave signal of at least one measurement point within a preset range of the location of the fault equipment; the target location corresponding to the fault equipment is designated as the fault location on the distribution network where the fault occurred; wherein, the fault equipment is used to receive power grid data measured by each measurement point connected to the fault equipment; the traveling wave signal is a high-frequency signal output by the measurement point when it detects an abnormality in the power grid data; the target location is the location where the fault occurred within a preset range of the location of the fault equipment.

[0075] The aforementioned method, apparatus, computer equipment, and storage medium for detecting and locating faults in a distribution network acquire grid data from at least one grid device in the distribution network; determine the fault status of the distribution network based on the grid data from each grid device; acquire fault data from at least one grid device in the distribution network when a fault occurs; and determine the location of the fault in the distribution network based on the fault data from each grid device. This embodiment can improve the utilization of synchronized grid data, thereby improving the accuracy and efficiency of fault identification and location.

[0076] Figure 3 This is a flowchart illustrating the steps for determining fault reference values ​​in one embodiment. This embodiment refines the steps for determining fault reference values ​​for the distribution network based on the operating characteristics of each power grid device in the above example. This embodiment provides an optional method for determining fault reference values, including the following steps:

[0077] S301 determines the initial reference value for each power grid device based on its operating characteristics and the operating characteristics of its neighboring power grid devices.

[0078] The operating characteristics may include at least one of voltage sag, instantaneous current peak, and harmonic distortion. It should be noted that voltage sag refers to the rapid drop in the effective value of the supply voltage to 90%-10% of the rated value, and harmonic distortion refers to the presence of additional harmonic components in the output signal due to the non-linearity of the system, which is the ratio of the root mean square (RMS) value of the target harmonic (second order, third order, etc.) to the root mean square value of the signal current.

[0079] In some optional embodiments, a first parameter value of the power grid equipment is determined based on the operating characteristics of the power grid equipment; and, for each adjacent power grid equipment, a first parameter value of the adjacent power grid equipment is determined based on the operating characteristics of the adjacent power grid equipment; and an initial reference value of the power grid equipment is determined based on the first parameter value of the power grid equipment, a preset power grid weight, the first parameter value of the adjacent power grid equipment, and a preset adjacent weight.

[0080] In another optional embodiment, synchronization data from each terminal is acquired and preprocessed. This preprocessing includes data cleaning, a common technique whose specific steps are not detailed here. The target window function and window length are determined. These can be selected based on actual needs, such as a Hanning or Hamming window, to balance time and frequency resolution requirements. A shorter window length results in higher time resolution but may decrease frequency resolution, and vice versa. Based on the target window function and window length, the preprocessed synchronization data from each terminal is divided into multiple time intervals. The time-frequency diagram is obtained by dividing the data into windows and performing a short-time Fourier transform on each window to obtain the frequency components corresponding to the synchronous data within the target window. The specific scheme of the short-time Fourier transform is a commonly used method, and its process will not be elaborated here. Frequency components refer to the components of different frequencies in a signal or system. The Fourier transform results of all windows are combined to obtain the target time-frequency diagram, which is a two-dimensional array representing the time-frequency of the signal. Based on the time-frequency diagram, fault-related features are extracted, including at least voltage drops, instantaneous current peaks, and harmonic distortion. That is, the changes of the signal with time and frequency are observed and analyzed in the time-frequency diagram to extract fault-related features.

[0081] S302 determines the fault reference value of the distribution network based on the initial reference value of each power grid device and the preset value of the distribution network topology type.

[0082] In some embodiments, the location information of power grid equipment in the topology of the distribution network, i.e., the coordinate information of the power grid equipment, is obtained; based on the location information of the power grid equipment in the topology of the distribution network, the first volatility of the lines between the target power grid equipment and adjacent power grid equipment is determined, and the sum of the first volatility corresponding to the target power grid equipment is calculated, wherein the method for calculating the first volatility is as follows: ,in, , Let represent the coordinate values ​​of the target power grid equipment and adjacent power grid equipment, respectively. The sum of the first volatility refers to the sum of the first volatility values ​​corresponding to the target power grid equipment and multiple adjacent power grid equipment. Based on the sum of the first volatility values ​​corresponding to multiple target power grid equipment, the second volatility values ​​corresponding to all power grid equipment are determined, where the second volatility value refers to the sum of the first volatility values ​​corresponding to multiple target power grid equipment. The fault characteristics of the target power grid equipment are obtained, and based on the first fusion function, the first fusion result of the target power grid equipment is determined. The first fusion function includes the following formula (1-1):

[0083] (1-1)

[0084] Where N1 represents the first fusion result, a1, a2 and a3 all represent weighting coefficients, T represents the voltage drop amplitude, U represents the instantaneous current peak value, and P represents the ratio of the root mean square value of the target harmonic corresponding to the harmonic distortion to the root mean square value of the signal current. The relevant parameters in the above formula and the formula below are all normalized parameter values ​​to eliminate the dimensions between parameters, improve the calculation speed, and improve the fault location efficiency.

[0085] Based on the second fusion function, the second fusion result between the target power grid equipment and the adjacent power grid equipment adjacent to the target power grid equipment is determined. The second fusion function includes the following formula (1-2):

[0086] (1-2)

[0087] Where N2 represents the second fusion result, a4 and a5 both represent weighting coefficients, N1 represents the first fusion result of the target power grid equipment, and N 12 The second fusion result of adjacent grid equipment is represented; the third fusion result of all grid equipment is determined based on the sum of the second fusion results of multiple target grid equipment; the fault characteristic fusion result is determined based on the second volatility and the third fusion result, as well as the third fusion function, which includes the following formulas (1-3):

[0088] (1-3)

[0089] Where N4 represents the fault feature fusion result, a6 represents the adjustment coefficient, and Y iThis represents the assigned value corresponding to the i-th topology type of distribution network. This assignment is based on expert experience. K represents the second volatility, and N3 represents the third fusion result. In this embodiment, for each grid device, an initial reference value is determined based on the operating characteristics of the grid device and the operating characteristics of its neighboring grid devices. Based on the initial reference values ​​of each grid device and the preset assignment of the topology type of the distribution network, the fault reference value of the distribution network is determined more accurately.

[0090] Figure 4 This is a flowchart illustrating a fault adjustment method in one embodiment. This embodiment provides an optional approach to the fault adjustment method, including the following steps:

[0091] S401 inputs the fault data of each faulty device into a pre-trained fault classification model to obtain the fault type of the faulty device at the corresponding target location.

[0092] In some embodiments, fault data of each faulty device is acquired; a target clustering algorithm is determined, including K-means and DBSCAN, and the appropriate target clustering algorithm can be selected according to actual needs; based on the target clustering algorithm, fault data in the synchronous data is summarized and statistically analyzed, wherein the method of summarizing and analyzing data through clustering algorithms is a common method, and its specific process will not be elaborated here; historical fault data is acquired and divided into training set and test set, wherein the division ratio can be set to 7:3, etc.; based on machine learning algorithm, an initial classification model is constructed, and the initial target classification model is trained and validated using the training set and test set, wherein the machine learning algorithm can be decision tree and neural network, and the basic neural network model can be selected according to actual needs; in response to the validation result meeting the preset standard, the target classification model is output, wherein the preset standard can be that the training accuracy meets the requirements or the number of training times meets the requirements, and the expression of the target classification model includes the following formula (1-4):

[0093] (1-4)

[0094] Where μ represents the number of power grid devices corresponding to the fault data at time, W represents the output value of the target classification model, h represents the number of power grid devices corresponding to the fault data at location, and B m Let represent the logistic probability value corresponding to the m-th fault data, n represent the amount of fault data, and C represent the fusion feature value of the fault data; input the fusion result of the fault data and fault features into the target classification model to obtain the output value; determine the corresponding fault type based on the output value and the preset classification criteria, which include the following formulas (1-5):

[0095] (1-5)

[0096] Where x1 represents the second preset threshold and G represents the classification result; in response to G=0, the fault type is determined to be the first fault type, where the first fault type is the common fault type mentioned above; in response to G=1, the fault type is determined to be the second fault type, where the second fault type is the uncommon fault type mentioned above.

[0097] 402 If the fault type is a preset type, adjust the operating status of the faulty equipment according to the operating status of the adjacent power grid equipment.

[0098] In some embodiments, in response to the fault type of the fault point being a first fault type, no adjustment is made to the power grid data of the fault point. Specifically, if the fault type is a common fault, the operating status of adjacent power grid equipment is obtained to determine whether it is affected, and the power grid data of the adjacent power grid equipment is adjusted according to the degree of impact, such as adjusting current data. In response to the fault type of the fault point being a second fault type, the operating status of adjacent power grid equipment connected to the fault point is obtained, and the power grid data of the fault point is adjusted according to the operating status. Specifically, if the fault type is an uncommon fault, the operating status of adjacent power grid equipment is obtained to determine whether it is affected, and the power grid data of the faulty power grid equipment is adjusted according to the degree of impact, such as adjusting output voltage data.

[0099] In this embodiment, the fault data of each faulty device is input into a pre-trained fault classification model to obtain the fault type of the faulty device at the corresponding target location; when the fault type is a preset type, the operating status of the faulty device is accurately adjusted according to the operating status of the adjacent power grid devices of the faulty device to repair the fault location.

[0100] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0101] Based on the same inventive concept, this application also provides a power grid fault detection and location device for implementing the power grid fault detection and location method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the power grid fault detection and location device provided below can be found in the limitations of the power grid fault detection and location method described above, and will not be repeated here.

[0102] In one exemplary embodiment, such as Figure 5 As shown, a power distribution network fault detection and location device is provided, comprising: a data acquisition module 10, a fault determination module 20, a fault acquisition module 30, and a location determination module 40, wherein:

[0103] Data acquisition module 10 is used to acquire power grid data of at least one power grid device on the distribution network;

[0104] The fault determination module 20 is used to determine the fault status of the distribution network based on the power grid data of each power grid device.

[0105] The fault acquisition module 30 is used to acquire fault data of at least one power grid device in the power distribution network when a fault occurs in the power distribution network.

[0106] The location determination module 40 is used to determine the fault location of the fault in the distribution network based on the fault data of each power grid equipment.

[0107] In some embodiments, the fault determination module 20 is further configured to determine the operating characteristics of each power grid device based on the power grid data of the power grid device; determine the fault reference value of the distribution network based on the operating characteristics of each power grid device; and determine that a fault has occurred in the distribution network when the fault reference value of the distribution network is greater than a preset reference threshold.

[0108] In some embodiments, the fault determination module 20 is further configured to determine an initial reference value for each power grid device based on the operating characteristics of the power grid device and the operating characteristics of adjacent power grid devices; and to determine a fault reference value for the distribution network based on the initial reference value of each power grid device and the preset value of the topology type to which the distribution network belongs.

[0109] In some embodiments, the fault determination module 20 is further configured to determine a first parameter value of the power grid equipment based on the operating characteristics of the power grid equipment; and, for each adjacent power grid equipment, determine a first parameter value of the adjacent power grid equipment based on the operating characteristics of the adjacent power grid equipment; and determine an initial reference value of the power grid equipment based on the first parameter value of the power grid equipment, a preset power grid weight, the first parameter value of the adjacent power grid equipment, and a preset adjacent weight.

[0110] In some embodiments, the location determination module 40 is further configured to identify the power grid equipment corresponding to the fault data as the fault equipment; for each fault equipment, determine the target location corresponding to the fault equipment based on the location of the fault equipment on the distribution network and the traveling wave signal of at least one measurement point within a preset range of the location of the fault equipment; and use the target location corresponding to the fault equipment as the fault location where the fault occurred on the distribution network; wherein, the fault equipment is configured to receive power grid data measured by each measurement point connected to the fault equipment; the traveling wave signal is a high-frequency signal output by the measurement point when it detects an abnormality in the power grid data; and the target location is the location where the fault occurred within a preset range of the location of the fault equipment.

[0111] In some embodiments, the location determination module 40 is further configured to input the fault data of each faulty device into a pre-trained fault classification model to obtain the fault type of the faulty device at the corresponding target location; and, if the fault type is a preset type, adjust the operating state of the faulty device according to the operating state of the adjacent power grid devices of the faulty device.

[0112] Each module in the aforementioned power distribution network fault detection and location device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0113] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a method for detecting and locating faults in a power distribution network.

[0114] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0116] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0117] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0119] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting and locating faults in a power distribution network, characterized in that, The method includes: Acquire grid data from at least one grid device on the distribution network; Based on the grid data of each of the grid devices, the fault status of the distribution network is determined; wherein, for each grid device, the operating characteristics of the grid device are determined based on the grid data of the grid device. Based on the operating characteristics of each of the power grid devices, a fault reference value for the distribution network is determined. For each power grid device, an initial reference value for the power grid device is determined based on its operating characteristics and the operating characteristics of its adjacent power grid devices. A first parameter value for the power grid device is determined based on its operating characteristics. For each adjacent power grid device, a first parameter value for the adjacent power grid device is determined based on its operating characteristics. The initial reference value of the power grid equipment is determined based on the first parameter value of the power grid equipment, the preset power grid weight, the first parameter value of the adjacent power grid equipment, and the preset adjacent weight. Based on the initial reference values ​​of each power grid device and the preset values ​​of the topology type to which the distribution network belongs, the fault reference value of the distribution network is determined, and the location information of the power grid devices in the topology of the distribution network, i.e., the coordinate information of the power grid devices, is obtained. Based on the location information of the power grid devices in the topology of the distribution network, the first volatility of the line between the target power grid device and adjacent power grid devices is determined, and the sum of the first volatility corresponding to the target power grid device is calculated. The calculation method of the first volatility is as follows: Where (x1, y1, z1) and (x2, y2, z2) represent the coordinate values ​​of the target power grid equipment and adjacent power grid equipment, respectively; the sum of the first volatility refers to the sum of the first volatility values ​​between the target power grid equipment and multiple adjacent power grid equipment; based on the sum of the first volatility values ​​corresponding to multiple target power grid equipment, the second volatility values ​​corresponding to all power grid equipment are determined; where the second volatility value refers to the sum of the first volatility values ​​corresponding to multiple target power grid equipment; the fault characteristics of the target power grid equipment are obtained, and based on the first fusion function, the first fusion result of the target power grid equipment is determined, the first fusion function including the following formula: N1 represents the first fusion result, a1, a2, and a3 all represent weighting coefficients, T represents the voltage drop amplitude, U represents the instantaneous current peak value, and P represents the ratio of the root mean square value of the target harmonic corresponding to the harmonic distortion to the root mean square value of the signal current. Based on the second fusion function, the second fusion result between the target grid equipment and adjacent grid equipment adjacent to the target grid equipment is determined. The second fusion function includes the following formula: N2 represents the second fusion result, a4 and a5 both represent weighting coefficients, N1 represents the first fusion result of the target power grid equipment, and N 12 The second fusion result represents the results of merging adjacent grid devices; based on the sum of the second fusion results corresponding to multiple target grid devices, the third fusion result corresponding to all grid devices is determined; based on the second volatility and the third fusion result, as well as the third fusion function, the fault characteristic fusion result is determined, the third fusion function including the following formula: N4 represents the fault feature fusion result, a6 represents the adjustment coefficient, and Y i The value assigned to the distribution network of the i-th topology type is given by experts based on experience. K represents the second volatility and N3 represents the third fusion result. If the fault reference value of the power distribution network is greater than a preset reference threshold, it is determined that a fault has occurred in the power distribution network. In the event of a fault in the distribution network, fault data of at least one power grid device on the distribution network shall be acquired. Based on the fault data of each of the power grid devices, the location of the fault in the distribution network is determined.

2. The method according to claim 1, characterized in that, Determining the location of the fault in the distribution network based on the fault data of each of the power grid devices includes: The power grid equipment corresponding to the fault data is designated as the faulty equipment. For each faulty device, the target location corresponding to the faulty device is determined based on the location of the faulty device on the distribution network and the traveling wave signal at at least one measurement point within a preset range of the location of the faulty device. The target location corresponding to the faulty equipment is taken as the fault location of the fault in the distribution network; The faulty device is used to receive power grid data measured by each measurement point connected to the faulty device; the traveling wave signal is a high-frequency signal output by the measurement point when it detects an abnormality in the power grid data; the target location is the location where the fault occurs within a preset range of the location of the faulty device.

3. The method according to claim 2, characterized in that, The method further includes: The fault data of each faulty device is input into a pre-trained fault classification model to obtain the fault type of the faulty device at the corresponding target location; When the fault type is a preset type, the operating status of the faulty device is adjusted according to the operating status of the adjacent power grid devices of the faulty device.

4. A power distribution network fault detection and location device for implementing the power distribution network fault detection and location method of any one of claims 1-3, characterized in that, The device includes: The data acquisition module is used to acquire power grid data from at least one power grid device on the distribution network. The fault determination module is used to determine the fault status of the distribution network based on the power grid data of each of the power grid devices. The fault acquisition module is used to acquire fault data of at least one power grid device on the power distribution network when a fault occurs in the power distribution network. The location determination module is used to determine the location of the fault that occurred on the distribution network based on the fault data of each of the power grid devices.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images