Intelligent monitoring method and device for urban underground power distribution pipe network

Abstract

This disclosure presents an intelligent monitoring method and apparatus for urban underground power distribution networks. One specific implementation of the method includes: acquiring a dataset of urban underground power grid installations and a set of power distribution network area information; constructing a power distribution network structure model in a pre-set urban construction map; matching power line information from the power line information set with road information from the road information set to generate a dual-path mapping relationship information set; performing structural mapping on the power distribution network structure model based on the power distribution network area information set and the dual-path mapping relationship information set to generate a power distribution network structure tree; performing fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network; and, in response to the detected fiber optic anomaly, locating the abnormal vibration line and abnormal area of ​​the fiber optic cable according to the power distribution network structure tree to obtain fiber optic anomaly information. This implementation can be used to detect abnormal conditions in the power grid in a timely manner.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the fields of computer technology and power grid monitoring, specifically to intelligent monitoring methods and devices for urban underground power distribution networks. Background Technology

[0002] With the acceleration of urbanization and the continuous expansion of urban areas, the demand for electricity is also increasing. As a crucial infrastructure for urban power supply, underground power distribution networks are also expanding in scale and becoming increasingly complex. Traditional manual inspections and simple testing methods are no longer sufficient to meet the testing needs of large-scale and complex underground power distribution networks, urgently requiring intelligent testing methods to improve testing efficiency and accuracy.

[0003] Manual inspections typically require cable maintenance personnel to enter underground utility tunnels or inspect through manholes, resulting in harsh working conditions and inherent safety risks. Furthermore, the scope and frequency of manual inspections are limited, making real-time and comprehensive monitoring difficult and prone to overlooking potential faults. Manual inspections often involve entering utility tunnels or manholes, a method known as "opening windows" inspection. This often requires excavating manholes every few hundred meters to manually observe the wiring within specific areas. However, this method is costly. Excavation work also severely impacts urban traffic and residents' lives, and prolonged power outages for maintenance can cause significant socio-economic losses. Additionally, while electromagnetic detection equipment is commonly used during inspections, traditional electromagnetic detection equipment suffers from significant positioning errors, inability to identify non-energized lines, and severe interference from multiple cables, making it unsuitable for the precise inspection requirements of modern urban underground power distribution networks.

[0004] In summary, the main problems encountered during monitoring and maintenance are as follows: First, information collection is difficult due to the complex and ever-changing underground environment, making the deployment, power supply, and communication functions of IoT smart sensing terminals challenging. Second, spatial positioning is difficult; how to correct and improve positioning results to provide accurate visual support for on-site cable maintenance personnel is also a pressing issue. Third, prevention is difficult; manual prevention is costly and easily overlooked, and accidents caused by construction work resulting in the excavation of underground power cables occur frequently, with the number of faults attributed to external forces far exceeding the number of faults caused by damage to the cable itself.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure propose intelligent monitoring methods and devices for urban underground power distribution networks to solve the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide an intelligent monitoring method for urban underground power distribution networks. The method includes: acquiring a dataset of underground power grid installations and a set of power distribution network area information; constructing a power distribution network structure model in a preset urban construction map based on the aforementioned power grid installation dataset, wherein the power distribution network structure model includes a set of power distribution nodes, a set of power distribution line information, and a set of road information; performing matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set, wherein the dual-path mapping relationship information is used to characterize the correspondence between power distribution lines and roads; performing structural mapping on the aforementioned power distribution network structure model based on the aforementioned power distribution network area information set and the aforementioned dual-path mapping relationship information set to generate a power distribution network structure tree, wherein each node in the power distribution network structure tree corresponds to a power distribution area, and the power distribution area of ​​an upper-level node includes the power distribution area of ​​its child nodes; performing fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomalies, locating the abnormal vibration lines and abnormal areas of the fiber optic cables based on the aforementioned power distribution network structure tree to obtain fiber optic anomaly information.

[0009] Secondly, some embodiments of this disclosure provide an intelligent monitoring device for urban underground power distribution networks. The device includes: an acquisition unit configured to acquire a dataset of underground power grid installations and a set of power distribution network area information; a construction unit configured to construct a power distribution network structure model in a preset urban construction map based on the aforementioned power grid installation dataset, wherein the power distribution network structure model includes a set of power distribution nodes, a set of power distribution line information, and a set of road information; and a matching unit configured to perform matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set, wherein the dual-path mapping... The relational information is used to characterize the correspondence between power distribution lines and roads; the structure mapping unit is configured to perform structural mapping on the power distribution network structure model based on the above-mentioned power distribution network area information set and the above-mentioned dual-path mapping relational information set to generate a power distribution network structure tree, wherein each node in the power distribution network structure tree corresponds to a power distribution network area, and the power distribution network area of ​​the upper-level node includes the power distribution network area of ​​the child node; the anomaly detection unit is configured to perform fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomaly, locate the abnormal vibration line and abnormal area of ​​the fiber optic according to the above-mentioned power distribution network structure tree to obtain fiber optic anomaly information.

[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0012] The above-described embodiments of this disclosure have the following beneficial effects: the intelligent monitoring method for urban underground power distribution networks according to some embodiments of this disclosure can be used to detect abnormalities in the power grid in a timely manner. Specifically, the reasons why it is difficult to detect power grid abnormalities in a timely manner are: first, information collection is difficult, the underground environment is complex and changeable, and the deployment, power supply, and communication functions of IoT intelligent sensing terminals are quite challenging; second, spatial positioning is difficult, and how to correct and improve the positioning results to provide accurate visualization support for on-site cable maintenance personnel is also one of the urgent problems to be solved; third, prevention is difficult, manual prevention is costly and easily overlooked, and accidents caused by the excavation of underground power cables due to construction work occur frequently, with the number of faults attributed to external force damage far exceeding the number of faults caused by cable damage itself. Based on this, the intelligent monitoring method for urban underground power distribution networks according to some embodiments of this disclosure, firstly, considering the difficulty in collecting and integrating data, this disclosure constructs a power distribution network structure model in a preset urban construction map based on the power grid laying dataset. Here, by constructing a power distribution network structure model, it can be used to sort out the power grid structure, so as to facilitate overall control of power grid data. Then, considering the difficulty of spatial positioning. Therefore, road edge lines that are easily spatially located are introduced. This generates a dual-path mapping relationship information set. Thus, underground pipelines can be located based on easily identifiable road structures on the ground. Consequently, the location of faulty underground cables can be located using relative ground positional relationships. This simplifies spatial positioning and improves spatial positioning efficiency. Next, considering the difficulty in monitoring and preventing power grid anomalies, this disclosure performs structural mapping on the power distribution network structure model based on the distribution network area information set and the dual-path mapping relationship information set to generate a power distribution network structure tree. Therefore, a power distribution network structure tree is established based on the structure of the power distribution network structure model. This not only inherits the structural description features of the underground power grid from the power distribution network structure model, but also utilizes the convenience of the tree structure to accurately delineate the correspondence between each distribution network area, distribution network node, and distribution network line. Thus, when fiber optic anomalies are detected, the location of the anomaly and the scope of its impact can be located promptly. This enables the monitoring of power grid anomalies. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1 This is a flowchart of some embodiments of the intelligent monitoring method for urban underground power distribution networks according to this disclosure;

[0015] Figure 2This is a schematic diagram of coordinates relative to vectors;

[0016] Figure 3 This is a schematic diagram of the power supply area of ​​the child node;

[0017] Figure 4 These are schematic diagrams of some embodiments of the intelligent monitoring device for urban underground power distribution networks according to this disclosure;

[0018] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0019] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0020] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0021] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0022] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0023] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0024] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] Figure 1 A flowchart 100 is shown, illustrating some embodiments of an intelligent monitoring method for urban underground power distribution networks according to the present disclosure. The intelligent monitoring method for urban underground power distribution networks includes the following steps:

[0026] Step 101: Obtain the dataset of underground power grid installations and distribution network area information for the city.

[0027] In some embodiments, the implementing entity (e.g., a computing device) of the intelligent monitoring method for urban underground power distribution networks can acquire urban underground power grid laying datasets and distribution network area information sets via wired or wireless means. The power grid laying dataset characterizes the current laying status of the urban underground power grid. For example, the power grid laying data may include the laying location of each power grid line. The distribution network area information set may be information on distribution network areas divided according to actual electricity consumption ranges. For example, the dividing unit may be a residential area, office building, street, etc.

[0028] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0029] Step 102: Based on the power grid laying dataset, construct a power distribution network structure model in the preset urban construction map.

[0030] In some embodiments, the aforementioned executing entity can construct a power distribution network structure model in a preset urban construction map based on the aforementioned power grid laying dataset. This power distribution network structure model may include a set of distribution nodes, a set of power line information, and a set of road information. The power grid laying dataset can be input into the urban construction map to obtain the power distribution network structure model.

[0031] In some optional implementations of certain embodiments, the power grid laying data in the aforementioned power grid laying dataset may include: a set of power distribution equipment coordinates, a set of power distribution equipment numbers, a set of power distribution line coordinates, and a set of power distribution corridor boundary lines. The executing entity, based on the aforementioned power grid laying dataset, constructs a power distribution network structure model in a preset urban construction map, including:

[0032] S1. Transform the coordinate sets of power distribution equipment, power line, and power distribution corridor boundary lines from the aforementioned power grid laying dataset into the aforementioned urban construction map to obtain the power line information set. Each power line information set corresponds to one power line. Power distribution equipment coordinates represent the location of the power distribution equipment. The power distribution equipment number can be a unique identifier for the power distribution equipment. Each power line coordinate set can correspond to one power line. The power distribution corridor boundary line can be the route of the corridor boundary. Here, the coordinates of the power distribution equipment, power line, and power distribution corridor can be in a geographic coordinate system or a local coordinate system. Therefore, the coordinates of the power distribution equipment, power line, and power distribution corridor can be transformed into the map coordinate system of the urban construction map through coordinate transformation. Here, the urban construction map can be a simulated 3D map.

[0033] S2, extract road boundaries from the aforementioned city construction map to generate a road information set. The city construction map may include road boundary line vector data. Therefore, road identifiers and road boundary line equations can be extracted from road attribute fields as road information. Here, each road information corresponds to one road boundary (edge) line. The road information set may include road information corresponding to two or more boundary lines of a single road.

[0034] S3. In the converted city construction map, the coordinates of the power distribution equipment in the power distribution equipment coordinate set and the corresponding power distribution equipment numbers are used to construct power distribution nodes, resulting in a power distribution node set. Each power distribution line connects one or two power distribution nodes. Here, the power distribution nodes can be constructed from the coordinates of the power distribution equipment in the power distribution equipment coordinate set and the corresponding power distribution equipment numbers according to a preset data structure.

[0035] As an example, the data structure can be in JSON (JavaScript Object Notation) format. For instance, the data structure could include key-value pairs of power distribution equipment coordinates and equipment numbers.

[0036] S4. Based on the power distribution equipment number set, perform power grid structure division on each power distribution node in the aforementioned power distribution node set, and identify and bind each power distribution line to obtain the power distribution network structure model. This power distribution network structure model is a three-dimensional structure model. The power grid structure division is used to determine the hierarchical node relationships between each power distribution node. Here, each power distribution device in the power distribution equipment number set can be pre-configured according to its connection level.

[0037] As an example, the equipment connection levels can be divided into three levels. The distribution node corresponding to the first-level equipment number can be set as the root node. The distribution node corresponding to the second-level equipment number can be a child node under the root node according to the hierarchical relationship of the numbers. Similarly, the distribution node corresponding to the third-level equipment number is determined as a leaf node under the child node. Furthermore, the nodes can be associated with directed or undirected edges based on the current direction of the corresponding distribution lines. For example, if the distribution line has bidirectional flow, it can be set as an undirected edge; if it has unidirectional flow, it can be set as a directed edge. Thus, the power grid structure can be divided, and a distribution network structure model can be obtained.

[0038] Step 103: Match the power distribution line information in the power distribution line information set with the road information in the road information set to generate a dual-path mapping relationship information set.

[0039] In some embodiments, the aforementioned executing entity may perform matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set. The dual-path mapping relationship information is used to characterize the correspondence between power distribution lines and roads.

[0040] In some optional implementations of certain embodiments, the road information in the aforementioned road information set includes: road signs and a set of road boundary line equations. The executing entity performs matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set, including:

[0041] For each piece of information about a power distribution line in the power distribution line information set, perform the following processing steps:

[0042] S1, select at least one road information that matches the power distribution line information from the above road information set to obtain the target road information group. Specifically, the road boundary line equations closest to each power distribution line coordinate are selected by matching the coordinates of each power distribution line in the power distribution line coordinate set with the road boundary line equations in the road information.

[0043] S2, perform direction verification on each target road information in the aforementioned target road information group to eliminate incorrectly matched road boundary line equations, resulting in a processed road information group. Direction verification is used to eliminate road boundary line equations that are closest to the power distribution line and whose angle is greater than a preset angle threshold. Next, for each power distribution line coordinate in the target road information set and at least one corresponding target road information, the tangent vector of the power distribution line coordinate on the power distribution line can be determined as the first tangent vector. Then, the tangent vector of the coordinate point on the road boundary equation of the corresponding target road information that is closest to the power distribution line coordinate can be determined as the second tangent vector. Afterwards, the angle between the first and second tangent vectors can be determined. Here, if the angle is greater than a preset angle threshold, it indicates that the directional difference between the power distribution line and the road boundary equation at that power distribution line coordinate is too large. For example, if the power distribution line and the road boundary equation are intersecting at the power distribution line coordinate, forming a condition of being closest to the power distribution line coordinate, it leads to a matching error.

[0044] Here, the determination can also be made by combining the coordinates of multiple consecutive power distribution lines. For example, if the road boundary equations corresponding to a small number of power distribution line coordinates (e.g., one or two) differ from those corresponding to other power distribution line coordinates, and the angle between the tangents is greater than a preset angle threshold, then it is determined that the road boundary equations corresponding to these small number of power distribution line coordinates are incorrectly matched. Therefore, the incorrectly matched road boundary equations can be deleted.

[0045] Furthermore, if the road boundary line equation is a curve, the tangent vector at the corresponding coordinate position can be determined. If it is a straight line, the angle can be calculated directly using the slope of the straight line equation. Similarly, if the power distribution line coordinates are located on a straight line, to avoid numerous errors in the road boundary line equation matched using the power distribution line coordinates, segmented matching can be performed. Additionally, the above implementation method can be used to match the power distribution tunnel boundary line equation with the road boundary line equation to determine the relative position data between the road boundary and the underground power distribution tunnel boundary. Here, to avoid difficulties in establishing subsequent mapping relationships due to the deletion of incorrectly matched road boundary equations, the road boundary equations corresponding to adjacent correctly matched power distribution line coordinates can be used as matching objects for the power distribution line coordinates after deleting incorrectly matched road boundary equations. This improves the data in the processed road information group.

[0046] S3. Determine the relative vector sequence between each power distribution line coordinate in the aforementioned power distribution line coordinate set and the road boundary line equations included in the processed road information group, thus obtaining a set of relative vector sequences. First, the power distribution line coordinates corresponding to each boundary coordinate on the road boundary line equation can be determined according to the plane perpendicular direction of the road boundary line equation. Then, the vector from the boundary coordinates to the corresponding power distribution line coordinates can be determined as the relative vector. The relative vector can be a two-dimensional vector in the plane (horizontal and vertical axes) of the three-dimensional coordinate system in the power distribution network structure model.

[0047] As an example, such as Figure 2 As shown, Figure 2 A schematic diagram of coordinates relative to vectors is shown. Figure 2 The dashed lines in the diagram represent the vertical direction of the road boundary line equation. The arrows in the diagram represent the relative coordinate vectors from the road boundary line equation (i.e., the boundary of road 202) to the power distribution line coordinates (i.e., the coordinates of the power distribution line or power distribution tunnel 201 boundary).

[0048] S4, the above coordinate relative vector sequence set and the processed road information group are determined as the dual-path mapping relationship information in the above dual-path mapping relationship information set.

[0049] In practice, considering the difficulty of spatially locating underground pipeline networks, simply constructing a power distribution network structure model is insufficient to provide a clearer location reference in real-world scenarios. Therefore, a dual-path mapping relationship between roads and power grid lines can be established by matching the model with road boundary line equations. This facilitates accurate location of underground cables at the road construction end, using the road as a reference.

[0050] Step 104: Based on the distribution network area information set and the dual-path mapping relationship information set, perform structural mapping on the distribution network structure model to generate the distribution network structure tree.

[0051] In some embodiments, the aforementioned execution entity may perform structural mapping on the aforementioned power distribution network structure model based on the aforementioned distribution network area information set and the aforementioned dual-path mapping relationship information set, so as to generate a power distribution network structure tree.

[0052] In some optional implementations of certain embodiments, the power grid laying data in the aforementioned power grid laying dataset also includes the power supply area of ​​the distribution equipment. The executing entity performs structural mapping on the aforementioned power distribution network structure model based on the aforementioned distribution network area information set and the aforementioned dual-path mapping relationship information set to generate a power distribution network structure tree, including:

[0053] S1. Based on the distribution equipment power supply areas included in the power grid deployment data in the aforementioned power grid deployment dataset, in the aforementioned power distribution network structure model, the distribution nodes that represent leaf nodes in the distribution node set are selected by bounding boxes to obtain the leaf node power supply area set. Here, the power supply area of ​​the distribution equipment can be an area connecting the same distribution nodes. For example, the power supply area of ​​the distribution equipment can be a residential area. In practice, the power supply area of ​​the distribution equipment can have a corresponding relationship with the distribution nodes. Therefore, the power supply area of ​​the distribution equipment can be bounded in the power distribution network structure model, and the power supply area of ​​the distribution equipment can be bound to the leaf nodes (i.e., the distribution equipment) according to the corresponding relationship to obtain the leaf node power supply area.

[0054] S2, based on the aforementioned leaf node power supply area set and the hierarchical node relationship between the distribution nodes, the distribution nodes in the distribution node set are selected in a bottom-up structural order to determine the power supply area of ​​each distribution node's corresponding child node, thus obtaining the child node power supply area set. The child node power supply area of ​​each distribution node is composed of the child node power supply areas corresponding to its subordinate child nodes. Here, the area selection can use the minimum bounding rectangle to select the child node power supply areas corresponding to all child nodes under the distribution node.

[0055] In practice, considering that the power supply area corresponding to a leaf node is relatively more precise, a bottom-up structural order is used for region selection to avoid errors. Specifically, first, the power supply area corresponding to each leaf node is determined. Then, the power supply areas of each leaf node under the same child node can be used as the child node's power supply area. Thus, the region selection is completed. Alternatively, a hierarchical bounding box algorithm can be used to determine the child node's power supply area for each distribution node.

[0056] As an example, see Figure 3 , Figure 3 A schematic diagram of the power supply area for the child node is shown. Figure 3 The diagram illustrates a three-tiered distribution node hierarchy. Distribution node A can be the root node. Distribution nodes B and C can be child nodes of the root node. Distribution nodes D, E, F, G, and H are leaf nodes. Here, the rectangle containing a leaf node represents its corresponding leaf node power supply area. Furthermore, a child node can include the leaf node power supply areas of its respective leaf nodes, thus serving as its child node power supply area. Finally, the area corresponding to distribution node A can include the child node power supply areas of its various child nodes.

[0057] S3, the above-mentioned power distribution node set, leaf node power supply area set, child node power supply area set, and power distribution line information between power distribution nodes are combined into a power distribution network structure tree. Furthermore, based on the above-mentioned dual-path mapping relationship information set, information binding is performed between the power distribution line corresponding to each power distribution line and the corresponding road boundary line equation. The dual-path mapping relationship information is used to display the relative laying position of the power distribution line and the road boundary for the construction end. Here, a tree structure construction function (e.g., bounding box algorithm) can be used to construct the power distribution network structure tree from the above-mentioned power distribution node set, leaf node power supply area set, child node power supply area set, and power distribution line information between power distribution nodes. Secondly, information binding can be performed by creating a connection relationship between the power distribution line and the corresponding road boundary line equation based on a preset attribute connection addition function (e.g., the add_connection function). Here, the power distribution network structure tree can be a multi-branch tree structure.

[0058] In practice, quickly determining the impact range of power outages in urban power grids requires a multi-dimensional approach, combining grid structure analysis, data monitoring, and on-site investigation. Specifically, it often necessitates the use of SCADA (Supervisory Control and Data Acquisition System) to monitor real-time data such as current, voltage, and switch status at each substation and feeder. If a feeder switch trips, the system automatically marks the feeder as "faulty" and displays all transformer substations supplied by it. For example, the detection and location of simple power outages (e.g., low-voltage user tripping, momentary faults on a single feeder) by SCADA systems often takes a considerable amount of time, typically 1-5 minutes. Detection and warnings for complex power outages (e.g., high-voltage cable breaks, substation equipment failures) often take even longer, typically 5-10 minutes. Furthermore, if power flow calculations and GIS topology analysis are used to determine the impact range, the time required can be even longer (e.g., 10-30 minutes). Manual verification further complicates the process, leading to delays in fault detection. Therefore, considering the low efficiency of traditional detection methods, the above-described embodiments of this application treat power distribution equipment as power distribution nodes and power distribution lines as node associations. A power distribution network structure tree is established for each power distribution node, corresponding to its power supply area. This allows for comprehensive monitoring of the urban underground power distribution network. Furthermore, because each node is associated with a corresponding distribution network area, when a power fault is detected, the "fast intersection detection" feature of the power distribution network structure tree can be utilized to quickly filter potentially affected areas through spatial geometric operations (such as point (i.e., power distribution node) - box (i.e., distribution network area) intersection, box-box containment, etc.). For example, if the coordinates (horizontal coordinates) of a cable fault point are (x, y), simply traversing downwards from the root node and determining whether (x, y) is within a bounding box can quickly locate leaf nodes (such as residential areas) and parent nodes at all levels (such as streets, administrative districts). Simultaneously, reducing one coordinate dimension during filtering further improves filtering efficiency. Thus, through the power distribution network structure tree, fault reporting and fault area location can be achieved in milliseconds. It quickly delineates the smallest bounding box (cell) and its parent nodes at all levels (streets, administrative districts), greatly improving positioning efficiency.

[0059] Furthermore, in cases where multiple power supply lines correspond to a given area, they can be distinguished by the power distribution equipment numbers at each distribution node, thus corresponding to different power distribution lines within the same area. Consequently, the power supply areas corresponding to distribution nodes in the resulting power distribution network structure tree can overlap. This avoids incorrect delineation of the affected area during fault location.

[0060] Step 105: Detect fiber optic anomalies in the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomalies, locate the abnormal vibration line and abnormal area of ​​the fiber optic network according to the power distribution network structure tree to obtain fiber optic anomaly information.

[0061] In some embodiments, the aforementioned executing entity can perform fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomalies, locate the abnormal vibration lines and abnormal areas of the fiber optic cables according to the aforementioned power distribution network structure tree, thereby obtaining fiber optic anomaly information. Furthermore, a power distribution anomaly warning can be issued to the user terminals in the area corresponding to the fiber optic anomaly information.

[0062] In some optional implementations of certain embodiments, the aforementioned execution entity performs fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, including:

[0063] S1 controls the fiber optic data acquisition device to collect real-time data on cable fiber optic vibration. This fiber optic data acquisition device can be installed within the area's power distribution equipment (e.g., a distribution box) to acquire fiber optic data from multiple power distribution lines. Furthermore, each power distribution line has a pre-embedded fiber optic cable for measuring physical quantities such as temperature, strain, and vibration.

[0064] S2, perform signal conversion on the cable fiber vibration data in the above cable fiber vibration dataset to generate a cable fiber digital signal set. The signal conversion can be achieved by using a bandpass filtering algorithm to convert the cable fiber vibration data from optical signals to electrical signals, which then become the cable fiber digital signals.

[0065] S3, perform fiber optic vibration detection on each cable fiber optic digital signal in the aforementioned cable fiber optic digital signal set, and in response to the detection of an abnormal fiber optic vibration marker, determine the abnormal signal location coordinates corresponding to the abnormal vibration marker in the aforementioned power distribution network structure model. Specifically, a vibration anomaly identification algorithm can be used to perform fiber optic anomaly detection on each cable fiber optic digital signal in the aforementioned cable fiber optic digital signal set. Here, the vibration anomaly identification algorithm can output an abnormal fiber optic vibration signal. The abnormal fiber optic vibration signal can include an abnormal fiber optic vibration marker and an abnormal fiber optic location. The abnormal fiber optic vibration marker can be used to characterize the presence of abnormal fiber optic vibration. The abnormal fiber optic location can be the location where the fiber optic vibration wave is abnormal. Therefore, when an abnormal fiber optic vibration marker is detected, the abnormal fiber optic location can be converted into abnormal signal location coordinates. Here, the fiber optic vibration wave can correspond to the actual location of the fiber optic cable, thus the coordinates of the actual location of the fiber optic cable on the corresponding power distribution line in the power distribution network structure model can be determined as the abnormal signal location coordinates.

[0066] As an example, a vibration anomaly identification algorithm can be a combination of a threshold detection algorithm and a fast Fourier transform (FFT) or wavelet transform (WFT) algorithm. For instance, signal decomposition can be performed using an FFT or WFT algorithm, followed by threshold detection to filter out abnormal signals, thereby identifying vibration anomalies.

[0067] S4. The scene camera corresponding to the coordinates of the aforementioned abnormal signal location is invoked to capture road images. The power distribution network structure model can inherit elements from the city construction map (e.g., camera locations, road structures, etc.). Before invoking, the power distribution network structure model can be used to select one (or more) scene cameras closest to the coordinates of the aforementioned abnormal signal location. This allows the capture of road images.

[0068] Additionally, access to the construction system (e.g., the data system of the construction unit responsible for a particular road section) can be made to determine the type of construction (e.g., characterizing the type of road repair). Simultaneously, access to the construction system can be requested to view the cameras installed during construction, in order to capture road images.

[0069] S5, perform construction recognition on the aforementioned road images to generate construction information. This can be done using pre-trained convolutional neural networks (CNNs). The construction information may include the type of construction machinery (e.g., excavator identification).

[0070] S6. Based on the aforementioned construction information and the coordinates of the abnormal signal location, determine whether an optical fiber anomaly exists. Specifically, the aforementioned construction information and the coordinates of the abnormal signal location can be designated as information to be verified. Secondly, this information to be verified can be sent to the construction end as a warning. Additionally, a detection confirmation instruction can be issued to the construction end to instruct manual verification of the abnormal signal location coordinates. After detection and confirmation, the construction end can return indication information indicating whether an optical fiber anomaly exists. For example, if an optical fiber is damaged or broken, indication information indicating a fiber optic breakage can be returned.

[0071] In practice, power line faults can be caused not only by user-caused faults and equipment malfunctions, but also by cable faults resulting from road construction. Therefore, to more accurately detect fault types, scene cameras have been introduced to capture road images. This facilitates the assessment of the fault situation.

[0072] In some optional implementations of certain embodiments, the execution entity locates the optical fiber abnormal vibration line and abnormal area based on the aforementioned power distribution network structure tree, and obtains optical fiber abnormality information, including:

[0073] S1, determine the power distribution line information corresponding to the location coordinates of the above abnormal signal in the above power distribution network structure tree, and use it as the optical fiber abnormal vibration line. Specifically, the power distribution line corresponding to the coordinate set of the power distribution equipment in the power distribution line information can be marked as the optical fiber abnormal vibration line.

[0074] S2, in the aforementioned power distribution network structure tree, locate at least one leaf node power supply area and / or at least one child node power supply area corresponding to the power distribution node connected to the aforementioned optical fiber abnormal vibration line, and merge at least one leaf node power supply area and / or at least one child node power supply area into an optical fiber abnormality impact area. The leaf node power supply area or child node power supply area can be located using a breadth-first search algorithm or a width-first search algorithm.

[0075] S3. Perform power distribution detection on the aforementioned fiber optic anomaly-affected area to generate anomaly areas. Power distribution detection is used to delineate the areas actually affected by the fiber optic anomaly within the aforementioned fiber optic anomaly-affected area. Here, the power distribution equipment at each power distribution node within the fiber optic anomaly-affected area can be accessed to determine if the equipment is operating normally. If it is operating normally, the corresponding power supply area can be removed. Thus, the anomaly areas are obtained.

[0076] S4, the above-mentioned abnormal vibration line and the above-mentioned abnormal area of ​​the optical fiber are identified as optical fiber abnormal information.

[0077] Furthermore, because a hierarchical bounding box tree is used to construct the power distribution network structure tree, the system can proactively feed back power data from each distribution node at regular intervals to calculate the pressure at each node, based on the tree structure of the power distribution network structure tree. This facilitates the prevention of power supply anomalies.

[0078] The above-described embodiments of this disclosure have the following beneficial effects: the intelligent monitoring method for urban underground power distribution networks according to some embodiments of this disclosure can be used to detect abnormalities in the power grid in a timely manner. Specifically, the reasons why it is difficult to detect power grid abnormalities in a timely manner are: first, information collection is difficult, the underground environment is complex and changeable, and the deployment, power supply, and communication functions of IoT intelligent sensing terminals are quite challenging; second, spatial positioning is difficult, and how to correct and improve the positioning results to provide accurate visualization support for on-site cable maintenance personnel is also one of the urgent problems to be solved; third, prevention is difficult, manual prevention is costly and easily overlooked, and accidents caused by the excavation of underground power cables due to construction work occur frequently, with the number of faults attributed to external force damage far exceeding the number of faults caused by cable damage itself. Based on this, the intelligent monitoring method for urban underground power distribution networks according to some embodiments of this disclosure, firstly, considering the difficulty in collecting and integrating data, this disclosure constructs a power distribution network structure model in a preset urban construction map based on the power grid laying dataset. Here, by constructing a power distribution network structure model, it can be used to sort out the power grid structure, so as to facilitate overall control of power grid data. Then, considering the difficulty of spatial positioning. Therefore, road edge lines that are easily spatially located are introduced. This generates a dual-path mapping relationship information set. Thus, underground pipelines can be located based on easily identifiable road structures on the ground. Consequently, the location of faulty underground cables can be located using relative ground positional relationships. This simplifies spatial positioning and improves spatial positioning efficiency. Next, considering the difficulty in monitoring and preventing power grid anomalies, this disclosure performs structural mapping on the power distribution network structure model based on the distribution network area information set and the dual-path mapping relationship information set to generate a power distribution network structure tree. Therefore, a power distribution network structure tree is established based on the structure of the power distribution network structure model. This not only inherits the structural description features of the underground power grid from the power distribution network structure model, but also utilizes the convenience of the tree structure to accurately delineate the correspondence between each distribution network area, distribution network node, and distribution network line. Thus, when fiber optic anomalies are detected, the location of the anomaly and the scope of its impact can be located promptly. This enables the monitoring of power grid anomalies.

[0079] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an intelligent monitoring device for urban underground power distribution networks. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the intelligent monitoring device for urban underground power distribution networks can be specifically applied to various electronic devices.

[0080] like Figure 4As shown, an intelligent monitoring device 400 for urban underground power distribution networks in some embodiments includes: an acquisition unit 401, a construction unit 402, a matching unit 403, a structure mapping unit 404, and an anomaly detection unit 405. The acquisition unit 401 is configured to acquire a dataset of underground power grid installations and a set of power distribution network area information. The construction unit 402 is configured to construct a power distribution network structure model in a preset urban construction map based on the aforementioned power grid installation dataset. This power distribution network structure model includes a set of power distribution nodes, a set of power distribution line information, and a set of road information. The matching unit 403 is configured to perform matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set. This dual-path mapping relationship information is used to characterize the relationship between power distribution lines and roads. The structure mapping unit 404 is configured to perform structure mapping on the above-mentioned power distribution network structure model based on the above-mentioned distribution network area information set and the above-mentioned dual-path mapping relationship information set, so as to generate a power distribution network structure tree, wherein each node in the power distribution network structure tree corresponds to a distribution network area, and the distribution network area of ​​the upper-level node includes the distribution network area of ​​the child node; the anomaly detection unit 405 is configured to perform fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomaly, locate the abnormal vibration line and abnormal area of ​​the fiber optic according to the above-mentioned power distribution network structure tree, and obtain fiber optic anomaly information.

[0081] It is understandable that the various units recorded in the city's underground power distribution network intelligent monitoring device 400 are related to the reference. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the intelligent monitoring device 400 for urban underground power distribution networks and the units contained therein, and will not be repeated here.

[0082] The following is for reference. Figure 5 It illustrates a schematic diagram of the structure of an electronic device (such as a computing device) suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 5As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0083] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0084] In one embodiment, the processor is used to run a computer program stored in a memory to perform the following steps: acquiring a dataset of underground power grid installations and a set of distribution network area information; constructing a power distribution network structure model in a preset urban construction map based on the power grid installation dataset, wherein the power distribution network structure model includes a set of distribution nodes, a set of distribution line information, and a set of road information; matching the distribution line information in the distribution line information set with the road information in the road information set to generate a dual-path mapping relationship information set, wherein the dual-path mapping relationship information is used to characterize the correspondence between distribution lines and roads; performing structural mapping on the power distribution network structure model based on the distribution network area information set and the dual-path mapping relationship information set to generate a power distribution network structure tree, wherein each node in the power distribution network structure tree corresponds to a distribution network area, and the distribution network area of ​​an upper-level node includes the distribution network area of ​​its child nodes; performing fiber optic anomaly detection on the fiber optic data of the underground power distribution network, and in response to the detection of fiber optic anomalies, locating the abnormal vibration lines and abnormal areas of the fiber optic cables based on the power distribution network structure tree to obtain fiber optic anomaly information.

[0085] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0086] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0087] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0088] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for intelligent monitoring of urban underground power distribution networks, characterized in that, include: Obtain datasets of underground power grid installations and distribution network area information for the city; Based on the power grid laying dataset, a power distribution network structure model is constructed in a preset urban construction map, wherein the power distribution network structure model includes a power distribution node set, a power distribution line information set, and a road information set; The power distribution line information in the power distribution line information set is matched with the road information in the road information set to generate a dual-path mapping relationship information set, wherein the dual-path mapping relationship information is used to characterize the correspondence between power distribution lines and roads; Based on the distribution network area information set and the dual-path mapping relationship information set, the distribution network structure model is structurally mapped to generate a distribution network structure tree. Each node in the distribution network structure tree corresponds to a distribution network area. The distribution network area of ​​an upper-level node includes the distribution network areas of its child nodes. The power grid laying data in the power grid laying dataset also includes the power supply area of ​​the distribution equipment, including: Based on the power distribution equipment power supply area included in the power grid laying data, in the power distribution network structure model, the power distribution nodes that represent leaf nodes in the power distribution node set are selected by selecting the power distribution area to obtain the leaf node power supply area set. Based on the hierarchical node relationship between the leaf node power supply area set and the power distribution node, the power distribution nodes in the power distribution node set are selected in a top-down structural order to determine the child node power supply area corresponding to each power distribution node, thus obtaining the child node power supply area set. The child node power supply area of ​​the parent node is composed of the child node power supply areas corresponding to each child node under the parent node. The power distribution node set, leaf node power supply area set, child node power supply area set and power distribution line information between power distribution nodes are combined into a power distribution network structure tree. According to the dual-path mapping relationship information set, the power distribution line corresponding to each power distribution line information is bound to the corresponding road boundary line equation. The dual-path mapping relationship information is used to display the relative laying position of the power distribution line and the road boundary for the construction end. Fiber optic anomaly detection is performed on the fiber optic data of the urban underground power distribution network. In response to the detection of fiber optic anomaly, the abnormal vibration line and abnormal area of ​​the fiber optic cable are located according to the power distribution network structure tree to obtain fiber optic anomaly information.

2. The method according to claim 1, characterized in that, The method further includes: Based on the fiber optic anomaly information, activate the auxiliary detection camera to capture images of the abnormal line. Based on the captured images of the abnormal lines, the fiber optic anomaly information is updated in real time.

3. The method according to claim 1, characterized in that, The power grid laying dataset includes: a set of power distribution equipment coordinates, a set of power distribution equipment numbers, a set of power distribution line coordinates, and a set of power distribution corridor boundary lines. The step of constructing a power distribution network structure model in a preset urban construction map based on the power grid laying dataset includes: The coordinate sets of power distribution equipment, power distribution lines, and power distribution corridors included in each power grid laying data set are converted into the urban construction map to obtain a power distribution line information set, wherein each power distribution line information corresponds to one power distribution line. Road boundaries are extracted from the urban construction map to generate a road information set; In the converted city construction map, the coordinates of the power distribution equipment and the corresponding power distribution equipment numbers in the power distribution equipment coordinate set are used to construct power distribution nodes, resulting in a power distribution node set. Each power distribution line connects two power distribution nodes. Based on the set of power distribution equipment numbers, the power distribution nodes in the power distribution node set are divided into power grid structures, and each power distribution line is identified and bound to obtain a power distribution network structure model. The power distribution network structure model is a three-dimensional structure model, and the power grid structure division is used to determine the hierarchical node relationship between each power distribution node.

4. The method according to claim 3, characterized in that, The road information in the road information set includes: road signs and a set of road boundary line equations. The matching process between the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set includes: For each piece of information about a power distribution line in the power distribution line information set, perform the following processing steps: At least one road information matching the power distribution line information is selected from the road information set to obtain a target road information group. The road boundary line equations that are closest to each power distribution line coordinate are selected by matching the coordinates of each power distribution line in the power distribution line coordinate set with the road boundary line equations in the road information. Directional verification is performed on each target road information in the target road information group to eliminate road boundary line equations with incorrect matching, resulting in a processed road information group. The directional verification is used to eliminate road boundary line equations that are closest to the power distribution line and have an angle greater than a preset angle threshold. Determine the relative vector sequence between the coordinates of each power distribution line in the power distribution line coordinate set and the road boundary line equations included in the processed road information group, to obtain a set of relative vector sequences. The set of relative coordinate vector sequences and the processed road information group are determined as the dual-path mapping relationship information in the dual-path mapping relationship information set.

5. The method according to claim 4, characterized in that, The fiber optic anomaly detection of the fiber optic data of the urban underground power distribution network includes: Control the fiber optic data acquisition equipment to collect real-time data on cable and fiber optic vibration. The cable fiber vibration data in the cable fiber vibration dataset are converted into signals to generate a cable fiber digital signal set. Fiber vibration detection is performed on each fiber optic digital signal in the set of fiber optic digital signals, and in response to the detection of fiber optic abnormal vibration markers, the location coordinates of the abnormal signal corresponding to the abnormal vibration markers in the power distribution network structure model are determined. Call the scene camera corresponding to the location coordinates of the abnormal signal to capture road images; Construction identification is performed on the captured road images to generate construction information; Based on the construction information and the coordinates of the abnormal signal location, determine whether there is an optical fiber anomaly.

6. The method according to claim 5, characterized in that, The step of locating the abnormal fiber optic vibration line and abnormal area based on the power distribution network structure tree to obtain fiber optic anomaly information includes: The location coordinates of the abnormal signal are determined to correspond to the power distribution line information in the power distribution network structure tree, which is used as the abnormal vibration line of the optical fiber. In the power distribution network structure tree, find at least one leaf node power supply area and / or at least one child node power supply area corresponding to the power distribution node connected to the optical fiber abnormal vibration line, and merge at least one leaf node power supply area and / or at least one child node power supply area into an optical fiber abnormal influence area. Power distribution detection is performed on the optical fiber anomaly-affected area to generate anomaly areas, wherein power distribution detection is used to delineate the areas actually affected by optical fiber anomalies within the optical fiber anomaly-affected area. The abnormal vibration line and the abnormal region of the optical fiber are identified as optical fiber abnormality information.

7. An intelligent monitoring device for urban underground power distribution networks, characterized in that, include: The acquisition unit is configured to acquire datasets of underground power grid installations and distribution network area information within the city. The construction unit is configured to construct a power distribution network structure model in a preset urban construction map based on the power grid laying dataset, wherein the power distribution network structure model includes a power distribution node set, a power distribution line information set, and a road information set; The matching unit is configured to perform matching processing on the power distribution line information in the power distribution line information set and the road information in the road information set to generate a dual-path mapping relationship information set, wherein the dual-path mapping relationship information is used to characterize the correspondence between power distribution lines and roads; The structure mapping unit is configured to perform structure mapping on the power distribution network structure model based on the distribution network area information set and the dual-path mapping relationship information set to generate a power distribution network structure tree. Each node in the power distribution network structure tree corresponds to a distribution network area, and the distribution network area of ​​an upper-level node includes the distribution network areas of its child nodes. The power grid laying data in the power grid laying dataset also includes the power supply area of ​​the power distribution equipment, including: Based on the power distribution equipment power supply area included in the power grid laying data, in the power distribution network structure model, the power distribution nodes that represent leaf nodes in the power distribution node set are selected by selecting the power distribution area to obtain the leaf node power supply area set. Based on the hierarchical node relationship between the leaf node power supply area set and the power distribution node, the power distribution nodes in the power distribution node set are selected in a top-down structural order to determine the child node power supply area corresponding to each power distribution node, thus obtaining the child node power supply area set. The child node power supply area of ​​the parent node is composed of the child node power supply areas corresponding to each child node under the parent node. The power distribution node set, leaf node power supply area set, child node power supply area set and power distribution line information between power distribution nodes are combined into a power distribution network structure tree. According to the dual-path mapping relationship information set, the power distribution line corresponding to each power distribution line information is bound to the corresponding road boundary line equation. The dual-path mapping relationship information is used to display the relative laying position of the power distribution line and the road boundary for the construction end. An anomaly detection unit is configured to perform fiber optic anomaly detection on the fiber optic data of the urban underground power distribution network, and in response to the detection of fiber optic anomaly, locate the abnormal vibration line and abnormal area of ​​the fiber optic network according to the power distribution network structure tree, and obtain fiber optic anomaly information.

8. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the program, when executed by a processor, implements the method as described in any one of claims 1-6.

Images