Power distribution network fault accurate positioning method and related device

Abstract

The application provides a power distribution network fault accurate positioning method and related device, the method comprises the following steps: obtaining the reference topological structure corresponding to the target line in the target power distribution network, and performing flattening processing on the reference topological structure to obtain the target topological structure; determining the target device position data according to the target topological structure; obtaining the reference operation data of all devices in the target topological structure within the current time period; determining the model input sample according to the target device position data and the reference operation data; inputting the model input sample into the target neural network model for inference calculation to obtain the model output result; determining the target operation state and the target fault position of the target line according to the model output result. By flattening the power distribution network topological structure and converting it into numerical position data, and then performing model inference after fusing the device operation data, the accuracy of power distribution network fault positioning is improved.

Description

Technical Field

[0001] This application relates to the field of distribution network fault location technology, and in particular to a method and related apparatus for accurate fault location in distribution networks. Background Technology

[0002] Currently, power distribution network lines in remote mountainous areas are generally tens or even hundreds of kilometers long, covering a wide area with complex terrain. The distance between two adjacent monitoring devices is often several kilometers or even tens of kilometers. When power distribution network faults occur, existing technologies generally use the interval location method to locate the fault. This involves monitoring abnormal changes in electrical quantities to determine if the fault location is within the interval between two adjacent monitoring devices, followed by manual interval inspection. However, due to the large distance between adjacent devices, manual inspection is not only labor-intensive and time-consuming, but also suffers from low repair efficiency due to the complex terrain of mountainous areas. Furthermore, interval location can only pinpoint the general area of ​​the fault, failing to accurately locate the specific fault point, resulting in large errors in fault location accuracy. This seriously affects the rapid restoration of power and reliable operation of the power distribution network.

[0003] Therefore, improving the accuracy of fault location in power distribution networks is an urgent issue that needs to be addressed. Summary of the Invention

[0004] This application provides a method and related apparatus for accurate fault location in a power distribution network. By flattening the power distribution network topology and converting it into numerical location data, and then integrating equipment operation data into a neural network model for inference, fault status determination and accurate location can be achieved, thereby improving the accuracy of power distribution network fault location.

[0005] In a first aspect, embodiments of this application provide a method for accurate fault location in a power distribution network, the method comprising: Obtain the reference topology corresponding to the target line in the target distribution network, and flatten the reference topology to obtain the target topology; the reference topology includes: target power source, a main line monitoring devices and b branch line monitoring devices; a and b are both positive integers; Determine the target device location data based on the target topology; Obtain reference operating data for all devices in the target topology within the current time period; The model input sample is determined based on the target device location data and the reference operating data; The input samples of the model are input into the target neural network model for inference calculation to obtain the model output results; the target neural network model is a neural network model that meets the preset convergence conditions; The target operating status and target fault location of the target line are determined based on the output results of the model.

[0006] Secondly, embodiments of this application provide a precise fault location device for a distribution network, the device comprising a first acquisition module, a first determination module, a second acquisition module, a second determination module, an inference module, and a third determination module, wherein: The first acquisition module is used to acquire the reference topology corresponding to the target line in the target distribution network, and to flatten the reference topology to obtain the target topology; the reference topology includes: target power source, a main line monitoring devices and b branch line monitoring devices; a and b are both positive integers; The first determining module is used to determine the target device location data based on the target topology. The second acquisition module is used to acquire reference operating data of all devices in the target topology within the current time period; The second determining module is used to determine the model input sample based on the target device location data and the reference operating data; The inference module is used to input the model input sample into the target neural network model for inference calculation and obtain the model output result; the target neural network model is a neural network model that meets the preset convergence condition; The third determining module is used to determine the target operating status and target fault location of the target line based on the output results of the model.

[0007] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0009] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0010] By implementing the embodiments of this application, the distribution network topology can be flattened and transformed into numerical location data. Then, the equipment operation data can be integrated and input into a neural network model for reasoning to achieve fault status determination and accurate location positioning, thereby improving the accuracy of distribution network fault location. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a system architecture diagram of a power distribution network fault accurate location system provided in an embodiment of this application; Figure 2 This is a schematic diagram of a reference topology provided in an embodiment of this application; Figure 3 This is a schematic diagram of a target topology provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a method for accurately locating faults in a power distribution network, as provided in an embodiment of this application. Figure 6 This is a schematic diagram of a process for determining target location data provided in an embodiment of this application; Figure 7 This is a flowchart illustrating the output result of an analytical model provided in an embodiment of this application; Figure 8 This is a block diagram of the functional modules of a power distribution network fault accurate location device provided in the embodiments of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0014] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0015] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0016] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0017] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0018] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] Currently, power distribution network lines in remote mountainous areas are generally tens or even hundreds of kilometers long, covering a wide area with complex terrain. The distance between two adjacent monitoring devices is often several kilometers or even tens of kilometers. When power distribution network faults occur, existing technologies generally use the interval location method to locate the fault. This involves monitoring abnormal changes in electrical quantities to determine if the fault location is within the interval between two adjacent monitoring devices, followed by manual interval inspection. However, due to the large distance between adjacent devices, manual inspection is not only labor-intensive and time-consuming, but also suffers from low repair efficiency due to the complex terrain of mountainous areas. Furthermore, interval location can only pinpoint the general area of ​​the fault, failing to accurately locate the specific fault point, resulting in large errors in fault location accuracy. This seriously affects the rapid restoration of power and reliable operation of the power distribution network.

[0020] Therefore, improving the accuracy of fault location in power distribution networks is an urgent issue that needs to be addressed.

[0021] To address the aforementioned problems, this application provides a method and related apparatus for accurate fault location in a distribution network. First, a reference topology corresponding to the target line in the target distribution network is obtained, and this reference topology is flattened to obtain the target topology. The reference topology includes: a target power source, a main line monitoring devices, and b branch line monitoring devices; a and b are both positive integers. Target device location data is determined based on the target topology. Then, reference operating data of all devices in the target topology within the current time period is obtained. Model input samples are determined based on the target device location data and the reference operating data. Next, the model input samples are input into a target neural network model for inference calculation to obtain the model output result. The target neural network model is a neural network model that meets preset convergence conditions. Finally, the target operating state and target fault location of the target line are determined based on the model output result.

[0022] It is evident that by flattening the distribution network topology and converting it into numerical location data, and then integrating equipment operation data into a neural network model for inference, fault status determination and precise location can be achieved, thereby improving the accuracy of distribution network fault location.

[0023] For easier understanding, please refer to Figure 1 , Figure 1 This is a system architecture diagram of a distribution network fault accurate location system provided in an embodiment of this application. The distribution network fault accurate location system includes a sensing and acquisition layer, a data processing layer, and a model application layer.

[0024] The sensing and acquisition layer can obtain the reference topology of the target line by connecting to the drawings and ledgers of the target distribution network's operation and maintenance platform and combining them with on-site GPS measurements. This includes the distribution and connection relationships of the target power source, a main line monitoring devices, and b branch line monitoring devices. It can also collect electrical operation data of the target line in the current and historical time periods through current and voltage sensors deployed on each device, while recording the data acquisition timestamps to ensure synchronization.

[0025] The data processing layer defines the node hierarchy, performs linear sorting, and integrates parameters of the reference topology to generate a one-dimensional linear target topology. It then calculates the cumulative actual distance between each intermediate node and the root node, obtaining numerical target location data. Next, it performs outlier removal, missing value imputation, and standardization on the collected operational data to obtain structured target operational data. Finally, it concatenates the target location data and the target operational data dimensionally to generate model input samples. Simultaneously, it labels historical operational data with fault / no-fault tags, integrating these to obtain target training samples and completing the division of the training and test sets.

[0026] The model application layer iteratively trains and tests the original neural network model based on the target training samples, adjusting hyperparameters until the model meets preset convergence conditions to obtain the target neural network model. Then, the real-time generated model input samples are input into the target neural network model to obtain fault status identifiers and relative fault location values, determining the line's operating status. If a fault is detected, the final target fault location is determined by combining the total line length and the target topology. Finally, the operating status determination results and fault location information are visualized, and a fault location report is generated and pushed to the target distribution network's operation and maintenance platform.

[0027] It is evident that by flattening the tree-like topology into a one-dimensional linear structure, numerical representation of equipment location information is achieved, overcoming the technical bottleneck that traditional non-numerical topologies cannot be directly input into neural networks. Simultaneously, feature fusion of numerical location data and multi-dimensional electrical operation data enables the model to learn multi-dimensional correlation features, breaking through the limitation of relying solely on a single electrical quantity for location. This allows for precise fault location to specific line segments and offset distances, significantly improving fault location accuracy and repair efficiency in long mountainous line scenarios.

[0028] For easier understanding, please refer to Figure 2 , Figure 2This is a schematic diagram of a reference topology provided in an embodiment of this application. A(0): the root node, representing the target power source of the target distribution network (e.g., the outgoing line of a substation), is the starting point for the electrical energy input of the entire line; B(1), B(2), ..., B(a-1), B(a): a primary intermediate nodes, representing main line monitoring equipment distributed along the main line, arranged in series along the main line; where B(a) is the end node of the line (which can be considered the last main line monitoring equipment); C(2,1), C(2,2), C(i,1), ..., C(i,j): secondary intermediate nodes, representing branch line monitoring equipment branching off from the main line. Each branch node uniquely belongs to a primary intermediate node; for example, C(2,1) and C(2,2) belong to B(2), while C(i,1)~C(i,j) belong to B(i); F: represents the fault point on the branch line, used to illustrate fault occurrence scenarios. The arrows indicate the electrical connection direction of the reference topology (i.e., current flows from the power source to the load).

[0029] For easier understanding, please refer to Figure 3 , Figure 3 This is a schematic diagram of a target topology provided in an embodiment of this application. Starting from the target power supply A(0), first-level intermediate nodes B(1), B(2)...B(a) are arranged sequentially along the main line. Second-level intermediate nodes of each branch line (such as C(2,1), C(2,2), C(i,1)...C(i,j)) are inserted after their respective first-level intermediate nodes to form a complete linear topology sequence, and the corresponding electrical connection direction is retained, thereby obtaining the target topology.

[0030] The following is combined with Figure 4 The electronic devices in the embodiments of this application will be described. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0031] The processor can be used for: Obtain the reference topology corresponding to the target line in the target distribution network, and flatten the reference topology to obtain the target topology; the reference topology includes: target power source, a main line monitoring devices and b branch line monitoring devices; a and b are both positive integers; Determine the target device location data based on the target topology; Obtain reference operating data for all devices in the target topology within the current time period; The model input sample is determined based on the target device location data and the reference operating data; The input samples of the model are input into the target neural network model for inference calculation to obtain the model output results; the target neural network model is a neural network model that meets the preset convergence conditions; The target operating status and target fault location of the target line are determined based on the output results of the model.

[0032] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0033] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuit, etc., and the storage unit can be a memory.

[0034] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0035] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device may incorporate elements such as... Figure 1 The system architecture described above.

[0036] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 5 This application describes a method for accurate fault location in a power distribution network. Figure 5 This is a flowchart illustrating a method for accurately locating faults in a power distribution network, as provided in an embodiment of this application. The method specifically includes the following steps: Step S501: Obtain the reference topology corresponding to the target line in the target distribution network, and flatten the reference topology to obtain the target topology.

[0037] The reference topology includes: a target power source, a main line monitoring devices, and b branch line monitoring devices; where a and b are both positive integers.

[0038] Specifically, based on fault location requirements, a target line to be monitored is selected from the target distribution network. This target line can be a radial line in a mountainous distribution network, with its starting and ending points being the substation outgoing line (i.e., the target power source) to the load node at the end of the line. The reference topology includes one target power source, a main line monitoring devices, and b branch line monitoring devices. The target power source is the starting point of power input for the target line, i.e., the substation outgoing line. The a main line monitoring devices are distributed along the main path of the target line and are used to collect electrical quantity data such as current and voltage. The b branch line monitoring devices are distributed along the various branches of the main line, with each branch line monitoring device uniquely associated with one main line monitoring device.

[0039] The specific steps for flattening the reference topology to obtain the target topology include: A1. Take the target power source as the root node, and take the a main line monitoring devices and the b branch line monitoring devices as a first-level intermediate nodes and b second-level intermediate nodes, respectively. A2. According to the preset first sorting rule, the root node and a first-level intermediate nodes are linearly sorted to obtain the first topological sequence; A3. According to the preset second sorting rule, insert the b secondary intermediate nodes after their respective primary intermediate nodes to obtain the second topological sequence; A4. Obtain the line parameters and electrical connection relationships corresponding to the reference topology; A5. Integrate the second topology sequence according to the line parameters and electrical connection relationships to obtain the target topology structure.

[0040] In a specific embodiment, firstly, the target power source in the reference topology is defined as the root node. This root node is the starting point for power input in the entire distribution network topology, corresponding to the substation outgoing line of the mountainous distribution network. Simultaneously, the 'a' main line monitoring devices in the reference topology are defined as first-level intermediate nodes. These nodes are distributed along the main path of the target line and are used to collect electrical operation data of the main line. The 'b' branch line monitoring devices are defined as second-level intermediate nodes. These nodes are distributed along the branch paths of the main line, and their parent nodes are the corresponding first-level intermediate nodes.

[0041] Then, according to the preset first sorting rule, the root node and a first-level intermediate nodes are linearly sorted to obtain the first topological sequence. The preset first sorting rule can be the order of physical distance from the root node to each first-level intermediate node from near to far. In specific implementation, the root node is used as the starting point of the sequence, and along the extension direction of the main line, the first-level intermediate nodes closest to the root node, the second closest first-level intermediate nodes, etc. are arranged in sequence until all first-level intermediate nodes are arranged.

[0042] Next, according to the preset second sorting rule, b secondary intermediate nodes are inserted after their respective primary intermediate nodes to obtain the second topological sequence. The preset second sorting rule can be the access order and branch extension direction of the secondary intermediate nodes and their respective primary intermediate nodes. In practice, the parent primary intermediate node corresponding to each secondary intermediate node is first determined, and then the secondary intermediate node is arranged after its parent primary intermediate node. If a primary intermediate node corresponds to multiple secondary intermediate nodes, they are arranged sequentially according to the proximity of the branch extension direction.

[0043] Then, obtain the line parameters and electrical connection relationships corresponding to the reference topology. The line parameters include, but are not limited to, physical parameters such as the segment length between each node, line impedance, and conductor cross-sectional specifications. The electrical connection relationships include, but are not limited to, logical parameters such as the cascading relationship between nodes (e.g., the series relationship between the root node and the first-level intermediate node), the branch affiliation relationship (e.g., the subordinate relationship between the second-level intermediate node and the first-level intermediate node above it), and the current transmission direction. These are not specifically limited here.

[0044] Finally, based on the line parameters and electrical connections, the second topology sequence is labeled and integrated to obtain a one-dimensional linear target topology. Specifically, parameters such as segment lengths and line impedances are labeled one-to-one between nodes in the second topology sequence; simultaneously, electrical connections are embedded into the sequence as attribute tags, and nodes are connected according to the current transmission direction, clarifying the hierarchical attributes and connection logic of each node.

[0045] It is evident that by defining hierarchy, linear sorting, and integrating parameters, the tree-shaped distribution network topology is flattened into a one-dimensional linear structure, realizing the structuring and computability of non-numerical device location information, laying the foundation for subsequent location data quantification and model input.

[0046] Step S502: Determine the target device location data based on the target topology.

[0047] For easier understanding, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a process for determining target location data according to an embodiment of this application. The target topology includes the root node and N intermediate nodes, each intermediate node including a first-level or second-level intermediate node, where N is a positive integer and a+b=N. The specific steps for determining the target location data based on the target topology include: B1. Obtain the cumulative actual distance between each of the N intermediate nodes and the root node to obtain N cumulative actual distances; B2. Determine the total length of the lines corresponding to the target topology; B3. Obtain the ratio of each of the N cumulative actual distances to the total length of the line, and obtain N ratios; B4. Determine the target location data based on the N ratios.

[0048] In a specific embodiment, based on the line parameters marked in the target topology, the cumulative actual distance between each of the N intermediate nodes and the root node (i.e., the target power source) is calculated sequentially to obtain N cumulative actual distances. The cumulative actual distance is the sum of the lengths of the segmented lines traversed from the root node to that intermediate node.

[0049] Next, based on the line parameters marked in the target topology, the longest power supply path of the target line is selected, and the cumulative actual distance from the root node to the end node of the line along this path is calculated, which is then determined as the total line length corresponding to the target topology. Then, the ratio of each of the N cumulative actual distances to the total line length is calculated, resulting in N ratios.

[0050] Finally, the N ratios are arranged in a linear order according to the N intermediate nodes in the target topology to form a one-dimensional numerical sequence, which is the target location data.

[0051] It can be seen that by calculating the cumulative actual distance between each intermediate node and the root node and the ratio to the total length of the line, the non-numerical topological location information is transformed into a standardized numerical sequence in the interval [0, 1], realizing the quantitative representation of the equipment location and providing calculable location features for the input samples of the model to be constructed by fusion with electrical operation data.

[0052] Step S503: Obtain reference operating data of all devices in the target topology within the current time period.

[0053] Specifically, based on the node composition of the target topology, the data acquisition targets are clearly defined as the root node (i.e., the target power source), a primary intermediate nodes (i.e., main line monitoring devices), and b secondary intermediate nodes (i.e., branch line monitoring devices), ensuring coverage of all key monitoring nodes of the target line. Then, according to the real-time requirements of fault location, a time window for the current period (e.g., the most recent 5 minutes, 10 minutes) is set to ensure that the collected data reflects the current operating status of the target line. Next, through the sensing modules installed on each node monitoring device, electrical operating parameters of preset dimensions are collected, i.e., reference operating data. This reference operating data includes, but is not limited to, current data, voltage data, and power data, without specific limitations here.

[0054] Step S504: Determine the model input sample based on the target device location data and the reference operating data.

[0055] The specific steps of determining the model input sample based on the target location data and the reference running data include: C1. Preprocess the reference running data to obtain the target running data; the target running data includes M-1 dimensions of data; each dimension of data includes N actual running data, where M is an integer greater than 1; C2. Determine the target location data as the first dimension data; C3. Concatenate the first dimension data with the M-1 dimension data to obtain a fused feature matrix; the fused feature matrix has M dimensions and N data lengths. C4. Determine the fusion feature matrix as the input sample for the model.

[0056] In a specific embodiment, firstly, preprocessing is performed on the collected reference operating data to eliminate data noise, standardize the data format, and meet the input requirements of the neural network model. This preprocessing operation includes at least three steps: outlier removal, missing value imputation, and data standardization. Outlier removal uses the 3σ principle to identify and remove abnormal data such as current and voltage caused by sensor malfunctions or communication interference. Missing value imputation uses the mean of data from the same node and dimension to fill in a small number of missing values ​​that appeared during data acquisition. Data standardization maps the operating data of each dimension to the [0, 1] interval to eliminate the impact of dimensional differences on model training. After preprocessing, the target operating data is obtained, which contains M-1 dimensions (M is an integer greater than 1). These dimensions correspond to the core electrical parameters of the distribution network operation, such as current, voltage, and power dimensions. Each dimension contains N actual operating data points, corresponding one-to-one with the N intermediate nodes in the target topology.

[0057] Then, the target location data is defined as the first dimension of the model input. This first dimension represents the topological location features of each intermediate node and is used to provide location association information for the neural network model. Following the principle of consistent node order, the first dimension is concatenated with M-1 other dimensions to obtain a fused feature matrix. This fused feature matrix has M dimensions (i.e., 1 location dimension + M-1 electrical dimensions) and a data length of N (the same as the number of intermediate nodes).

[0058] Finally, the fused feature matrix is ​​used as the model input sample for the target neural network model. This model input sample contains both the topological location features and electrical operation features of each node, which can provide comprehensive data support for fault location.

[0059] It is evident that by preprocessing the operational data and concatenating it with numerical location data, a model input sample integrating topological location features and multi-dimensional electrical operation features was constructed, providing more comprehensive feature information for the neural network model and effectively improving the accuracy and robustness of fault location.

[0060] Step S505: Input the model input sample into the target neural network model for inference calculation to obtain the model output result.

[0061] The target neural network model is a neural network model that meets the preset convergence conditions.

[0062] The method further includes the following steps: D1. Obtain historical operating data of all devices in the target topology within a preset historical time period; the historical operating data includes abnormal fault data and normal operation data; D2. Label the abnormal fault data with fault tags based on the target device location data to obtain the first training sample; D3. Label the normal operation data with fault-free tags to obtain the second training sample; D4. Integrate the first training sample and the second training sample to obtain the target training sample; D5. Train the preset original neural network model according to the target training samples to meet the preset convergence condition, and obtain the target neural network model.

[0063] In a specific embodiment, firstly, based on the operation and maintenance log and monitoring database of the target line, a preset historical time period (e.g., the past 3 years) is set, and historical operating data of the root node, a first-level intermediate nodes, and b second-level intermediate nodes in the target topology are collected. This historical operating data needs to cover all operating conditions of the target line, specifically including two types of data: abnormal fault data and normal operation data. Abnormal fault data: This filters electrical operating data when the line experiences faults such as short circuits and grounding, simultaneously recording the fault occurrence time, fault type, and manually confirmed fault location. Normal operation data: This filters steady-state operating data under fault-free conditions, covering operating parameters during different load periods (peak, flat, and valley periods) and under different weather conditions.

[0064] Then, the fault location and fault type corresponding to each fault event in the abnormal fault data are extracted, and the intermediate node or node interval corresponding to the fault location in the target topology is queried; the target location data corresponding to the fault location (i.e., the ratio of cumulative distance to total line length) is retrieved and used as the fault location label, and the fault type label is marked according to the fault type (e.g., short circuit, grounding). The abnormal fault data is bound with the corresponding fault location label and fault type label to obtain the first training sample. Then, the normally operating data is uniformly labeled with a fault-free label to indicate that the target line corresponding to the data is in normal operating condition and no fault has occurred. The fault-free label is then bound with the normally operating data to obtain the second training sample.

[0065] Next, the first and second training samples are mixed and integrated according to a preset sample ratio (e.g., the ratio of the first training sample to the second training sample is 1:4, which can be adjusted according to the actual data distribution) to obtain the target training sample. During the integration process, the samples are randomly shuffled to avoid interference from the sample order to the model training. Finally, the preset original neural network model is trained based on the target training sample to meet the preset convergence condition, thus obtaining the target neural network model.

[0066] It is evident that by collecting historical operating data covering both normal and fault conditions, combining location data with fault labels, and constructing balanced training samples, the model can fully learn the fault correlation features of location and electrical quantities, thereby improving the model's fault identification accuracy and generalization ability, and providing a reliable model foundation for subsequent real-time accurate positioning.

[0067] The specific steps of training the preset original neural network model based on the target training samples to satisfy the preset convergence condition and obtain the target neural network model include: E1. Divide the target training samples into a training set and a test set according to a preset ratio; E2. Train the original neural network model using the training set to obtain a reference neural network model; E3. Test the reference neural network model according to the test set and obtain the test results; E4. If the test results meet the preset convergence conditions, then the reference neural network model is determined to be the target neural network model. E5. If the test result does not meet the preset convergence condition, adjust the hyperparameters of the reference neural network model and repeat the training and testing until the test result meets the preset convergence condition to obtain the target neural network model.

[0068] In a specific embodiment, the target training samples are first divided into a training set and a test set according to a preset ratio, preferably 7:3 or 8:2. The training set is used for iterative optimization of model parameters, and the test set is used to verify the generalization performance of the model. Furthermore, a validation set of 10% to 15% can be further divided from the training set to monitor overfitting in real time during training, ensuring the accuracy of the model's training direction.

[0069] Then, the Pi-Sigma neural network was selected as the original neural network model, with the number of input layer neurons set to M (consistent with the dimension of the fusion feature matrix), the number of hidden layer neurons to K, and the number of output layer neurons to 2. The weight vector w between the input layer and the hidden layer was initialized. k The initial weights follow a uniform distribution within the interval [-0.5, 0.5]. The training set samples are then input into the original neural network model in batches, and the model output values ​​are calculated through forward propagation. Specifically, the squared error function is used to calculate the error between the model's predicted value and the sample label value, and then the error is backpropagated using the gradient descent algorithm to iteratively update the weight vector w. k During training, if a validation set is used, the model performance is evaluated using the validation set after each iteration. If the validation set error increases continuously for several iterations, the model is considered overfitting, and the training is terminated prematurely. When the loss function value of the training set stabilizes, the training is stopped, and a reference neural network model is obtained.

[0070] Next, the test set samples are input into the reference neural network model, inference calculations are performed, and test results are obtained. These test results include at least two core indicators: fault state determination accuracy and fault location accuracy. Fault state determination accuracy is the proportion of samples where the model correctly distinguishes between normal operating conditions and abnormal fault states out of the total number of samples in the test set. Fault location accuracy is the proportion of samples where the model predicts the fault location versus the actual fault location, or the proportion of samples with a prediction error less than a preset threshold (e.g., 50 meters) out of the total number of fault samples.

[0071] If the test results fully meet the preset convergence conditions, then the reference neural network model is directly determined as the target neural network model. The preset convergence conditions can be a fault state determination accuracy of ≥98% and an average fault location error of ≤30 meters; no specific limitations are specified here.

[0072] If the test results do not meet the preset convergence conditions, hyperparameter tuning is performed. Hyperparameter tuning includes, but is not limited to, adjusting the learning rate, the number of hidden layer neurons, and the training batch and iteration count; specific limitations are not specified here. Specifically, for learning rate adjustment: if the model loss function decreases slowly, appropriately increase the learning rate (e.g., from 0.01 to 0.05); if the loss function fluctuates too much, appropriately decrease the learning rate (e.g., from 0.01 to 0.001). For the number of hidden layer neurons: if the model is underfitting, increase the number of hidden layer neurons K; if the model is overfitting, decrease the number of hidden layer neurons K. For training batch and iteration count adjustment: increase the batch size to improve training stability, or increase the number of iterations to ensure the model converges sufficiently. After completing the hyperparameter tuning, repeat steps E2-E4 of the training and testing process until the test results meet the preset convergence conditions, obtaining the target neural network model that meets the accuracy requirements.

[0073] It is evident that by dividing the training set and test set and executing iterative training, testing, and hyperparameter tuning processes, the trained neural network model can meet the preset convergence conditions, thereby improving the accuracy and stability of model fault localization.

[0074] In one possible embodiment, the Pi-Sigma neural network has M input layer neurons, perfectly matching the dimensions of the input samples (including features such as position, current, and voltage); K hidden layer neurons, used for weighted summation and nonlinear mapping of the input features; and 2 output layer neurons, outputting the fault state identifier y1 and the fault relative position value y2, respectively. Simultaneously, a connection weight vector w between the input layer and the hidden layer is defined. k And the connection weights w between the hidden layer and the output layer k1 w k2 For an input M-dimensional sample X, first calculate the weighted input S of each neuron in the hidden layer. k That is, the sum of the products of each dimension of the input layer data and its corresponding weight; then, the S is activated by the Sigmoid activation function. k A nonlinear transformation is performed to obtain the hidden layer output H. k Finally, the outputs Hk of all neurons in the hidden layer are compared with their corresponding weights w. k1 w k2 By performing a weighted summation, we obtain the actual output vector of the network: y = [y1, y2]. T The total error E(w) between the actual and ideal output of the network is calculated using the squared error function. The error is then backpropagated using the gradient descent algorithm to iteratively update the connection weights between the input and hidden layers, and between the hidden and output layers. Finally, the optimal weight vector w that minimizes the total error E(w) is found. *, complete network training to ensure that the trained model can accurately output the fault status and location results.

[0075] It should be noted that y1 = 0 indicates a fault, and y1 = 1 indicates no fault. When y1 = 1, then y2 = 0, indicating no fault and no fault location; when y1 = 0, then 0 < y2 <= 1, indicating a fault, and the relative fault location is y2.

[0076] Step S506, determine the target operating state and target fault location of the target line according to the output result of the model.

[0077] For easy understanding, please refer to Figure 7 , Figure 7 is a schematic flowchart of a process for analyzing the output result of a model provided by an embodiment of the present application. Among them, the output result of the model includes a fault status identification value and a relative fault location value. Determining the target operating state and target fault location according to the output result of the model includes: F1. If the fault status identification value is a preset first value, determine that the target operating state is a normal operating state; F2. If the fault status identification value is a preset second value, determine that the target operating state is an abnormal fault state; F3. Determine a reference fault location according to the total line length and the relative fault location value; F4. Determine the target fault location according to the target topology structure and the reference fault location.

[0078] In a specific embodiment, first, compare the fault status identification value output by the target neural network model with a preset first value (which can be set to 1, indicating no fault in the line). If the fault status identification value is equal to the preset first value, determine that the target operating state of the target line is a normal operating state, and there is no need to perform subsequent fault location calculations.

[0079] If the fault status identification value is equal to a preset second value (which can be set to 0, indicating a fault in the line), determine that the target operating state of the target line is an abnormal fault state, and start the subsequent fault location process. Among them, multiply the total line length and the relative fault location value to obtain a reference fault location, that is, the cumulative actual distance F between the fault point and the root node.

[0080] Then, compare the cumulative actual distance F corresponding to the reference fault location with the target topology structure, and filter out the adjacent node combinations that satisfy L p <F<L p+1 where p is a positive integer less than N. Among them, the node distance list corresponding to the target topology structure is {L1, L2,..., L N}, where Li This represents the cumulative actual distance between the i-th intermediate node and the root node, and the list of node distances is arranged in a one-dimensional linear order according to the target topology. Based on this combination of adjacent nodes, the fault point can be determined to be located on the line segment between the p-th intermediate node and the (p+1)-th intermediate node. Then, the difference ΔL = FL between the reference fault location and the cumulative actual distance to the p-th intermediate node is calculated. p The difference is the offset distance of the fault point relative to the p-th intermediate node, thus the target fault location is "the line segment ΔL downstream of the p-th intermediate node".

[0081] It is evident that by quickly determining the line operating status through fault status identification values, and by combining the total line length with the relative position of the fault and the target topology to achieve precise fault location, the efficiency of fault status identification and location accuracy of the distribution network are greatly improved.

[0082] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0083] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0084] When dividing each function into modules according to its corresponding function. Figure 8 This is a functional module block diagram of a power distribution network fault accurate location device 800 provided in an embodiment of this application. The power distribution network fault accurate location device 800 includes a first acquisition module 810, a first determination module 820, a second acquisition module 830, a second determination module 840, an inference module 850, and a third determination module 860, wherein: Optionally, in the process of flattening the reference topology to obtain the target topology, the first acquisition module 810 is specifically used for: The target power source is taken as the root node, and the a main line monitoring devices and the b branch line monitoring devices are respectively taken as a first-level intermediate nodes and b second-level intermediate nodes; According to the preset first sorting rule, the root node and a first-level intermediate nodes are linearly sorted to obtain the first topological sequence; According to the preset second sorting rule, the b secondary intermediate nodes are inserted after their respective primary intermediate nodes to obtain the second topological sequence; Obtain the line parameters and electrical connection relationships corresponding to the reference topology; The second topology sequence is integrated based on the line parameters and electrical connection relationships to obtain the target topology.

[0085] Optionally, the target topology includes the root node and N intermediate nodes, each intermediate node including a first-level intermediate node or a second-level intermediate node, where N is a positive integer and a+b=N; in determining the target location data based on the target topology, the first determining module 820 is specifically used for: Obtain the cumulative actual distance between each of the N intermediate nodes and the root node to obtain N cumulative actual distances; Determine the total length of the lines corresponding to the target topology; Obtain the ratio of each of the N cumulative actual distances to the total length of the line, thus obtaining N ratios; The target location data is determined based on the N ratios.

[0086] Optionally, in determining the model input samples based on the target location data and the reference running data, the second determining module 840 is specifically used for: The reference running data is preprocessed to obtain the target running data; the target running data includes M-1 dimensions of data; each dimension of data includes N actual running data, where M is an integer greater than 1; The target location data is determined to be the first dimension data; The first dimension data is concatenated with the M-1 dimension data to obtain a fused feature matrix; the fused feature matrix has M dimensions and N data lengths. The fusion feature matrix is ​​determined as the input sample of the model.

[0087] Optionally, the inference module 850 is specifically used for: Acquire historical operating data of all devices in the target topology within a preset historical time period; the historical operating data includes abnormal fault data and normal operation data. Based on the target device location data, fault labels are labeled on the abnormal fault data to obtain the first training sample; The normal operation data is labeled with fault-free tags to obtain the second training sample; The first training sample and the second training sample are integrated to obtain the target training sample; The target neural network model is obtained by training a preset original neural network model based on the target training samples to meet the preset convergence condition.

[0088] Optionally, in the step of training a preset original neural network model based on the target training samples to satisfy the preset convergence condition and obtain the target neural network model, the inference module 850 is further specifically used for: The target training samples are divided into a training set and a test set according to a preset ratio; The original neural network model is trained using the training set to obtain a reference neural network model; The reference neural network model is tested according to the test set to obtain test results; If the test results meet the preset convergence conditions, then the reference neural network model is determined to be the target neural network model; If the test result does not meet the preset convergence condition, the hyperparameters of the reference neural network model are adjusted, and training and testing are repeated until the test result meets the preset convergence condition, thus obtaining the target neural network model.

[0089] Optionally, the model output includes a fault status identifier value and a fault relative location value. In determining the target operating state and target fault location based on the model output, the third determining module 860 is specifically used for: If the fault status identifier value is a preset first value, then the target operating state is determined to be a normal operating state; If the fault status identifier value is a preset second value, then the target operating state is determined to be an abnormal fault state; The reference fault location is determined based on the total length of the line and the relative fault location value. The target fault location is determined based on the target topology and the reference fault location.

[0090] It is evident that by flattening the distribution network topology and converting it into numerical location data, and then integrating equipment operation data into a neural network model for inference, fault status determination and precise location can be achieved, thereby improving the accuracy of distribution network fault location.

[0091] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The distribution network fault accurate location device 800 can be used to execute the above method embodiments of this application, and will not be described again.

[0092] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0093] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0094] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0095] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0096] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0097] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0098] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0099] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0100] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for accurate fault location in a power distribution network, characterized in that, The method includes: Obtain the reference topology corresponding to the target line in the target distribution network, and flatten the reference topology to obtain the target topology; the reference topology includes: target power source, a main line monitoring devices and b branch line monitoring devices; a and b are both positive integers; Determine the target device location data based on the target topology; Obtain reference operating data for all devices in the target topology within the current time period; The model input sample is determined based on the target device location data and the reference operating data; The input samples of the model are input into the target neural network model for inference calculation to obtain the model output results; the target neural network model is a neural network model that meets the preset convergence conditions; The target operating status and target fault location of the target line are determined based on the output results of the model.

2. The method as described in claim 1, characterized in that, The process of flattening the reference topology to obtain the target topology includes: The target power source is taken as the root node, and the a main line monitoring devices and the b branch line monitoring devices are respectively taken as a first-level intermediate nodes and b second-level intermediate nodes; According to the preset first sorting rule, the root node and a first-level intermediate nodes are linearly sorted to obtain the first topological sequence; According to the preset second sorting rule, the b secondary intermediate nodes are inserted after their respective primary intermediate nodes to obtain the second topological sequence; Obtain the line parameters and electrical connection relationships corresponding to the reference topology; The second topology sequence is integrated based on the line parameters and electrical connection relationships to obtain the target topology.

3. The method as described in claim 2, characterized in that, The target topology includes the root node and N intermediate nodes. Each intermediate node includes a first-level intermediate node or a second-level intermediate node. N is a positive integer, and a+b=N. The step of determining the target location data based on the target topology includes: Obtain the cumulative actual distance between each of the N intermediate nodes and the root node to obtain N cumulative actual distances; Determine the total length of the lines corresponding to the target topology; Obtain the ratio of each of the N cumulative actual distances to the total length of the line, thus obtaining N ratios; The target location data is determined based on the N ratios.

4. The method as described in claim 3, characterized in that, The step of determining the model input samples based on the target location data and the reference running data includes: The reference running data is preprocessed to obtain the target running data; the target running data includes M-1 dimensions of data; each dimension of data includes N actual running data, where M is an integer greater than 1; The target location data is determined to be the first dimension data; The first dimension data is concatenated with the M-1 dimension data to obtain a fused feature matrix; the fused feature matrix has M dimensions and N data lengths. The fusion feature matrix is ​​determined as the input sample of the model.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Acquire historical operating data of all devices in the target topology within a preset historical time period; the historical operating data includes abnormal fault data and normal operation data. Based on the target device location data, fault labels are labeled on the abnormal fault data to obtain the first training sample; The normal operation data is labeled with fault-free tags to obtain the second training sample; The first training sample and the second training sample are integrated to obtain the target training sample; The target neural network model is obtained by training a preset original neural network model based on the target training samples to meet the preset convergence condition.

6. The method as described in claim 5, characterized in that, The step of training a preset original neural network model based on the target training samples to satisfy the preset convergence condition, thereby obtaining the target neural network model, includes: The target training samples are divided into a training set and a test set according to a preset ratio; The original neural network model is trained using the training set to obtain a reference neural network model; The reference neural network model is tested according to the test set to obtain test results; If the test results meet the preset convergence conditions, then the reference neural network model is determined to be the target neural network model; If the test result does not meet the preset convergence condition, the hyperparameters of the reference neural network model are adjusted, and training and testing are repeated until the test result meets the preset convergence condition, thus obtaining the target neural network model.

7. The method as described in claim 3, characterized in that, The model output includes a fault status identifier value and a fault relative location value. Determining the target operating state and target fault location based on the model output includes: If the fault status identifier value is a preset first value, then the target operating state is determined to be a normal operating state; If the fault status identifier value is a preset second value, then the target operating state is determined to be an abnormal fault state; The reference fault location is determined based on the total length of the line and the relative fault location value. The target fault location is determined based on the target topology and the reference fault location.

8. A precise fault location device for a power distribution network, characterized in that, The device includes a first acquisition module, a first determination module, a second acquisition module, a second determination module, a reasoning module, and a third determination module, wherein: The first acquisition module is used to acquire the reference topology corresponding to the target line in the target distribution network, and to flatten the reference topology to obtain the target topology; the reference topology includes: target power source, a main line monitoring devices and b branch line monitoring devices; a and b are both positive integers; The first determining module is used to determine the target device location data based on the target topology. The second acquisition module is used to acquire reference operating data of all devices in the target topology within the current time period; The second determining module is used to determine the model input sample based on the target device location data and the reference operating data; The inference module is used to input the model input sample into the target neural network model for inference calculation and obtain the model output result; the target neural network model is a neural network model that meets the preset convergence condition; The third determining module is used to determine the target operating status and target fault location of the target line based on the output results of the model.

9. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images