A power equipment name alignment method, device and computer readable storage medium

Abstract

This application discloses a method, device, and computer-readable storage medium for aligning the names of power equipment, relating to the field of power plant operation and maintenance management technology. The method includes: acquiring the actual spatial distribution information of each power equipment in a target power plant, and constructing a first topology map to represent the actual positional relationships between the power equipment; each power equipment in the first topology map has its corresponding graph node associated with its own field identifier; acquiring the design position information of each power equipment in the engineering design drawings of the target power plant, and constructing a second topology map to represent the design positional relationships between the power equipment; each power equipment in the second topology map has its corresponding graph node associated with its own equipment name; and using a graph matching algorithm to match the topological structures of the first and second topology maps to establish a mapping relationship between the field identifiers of each power equipment and their respective equipment names. This application can accurately and efficiently align the names of power equipment.

Description

Technical Field

[0001] This application relates to the field of power plant operation and maintenance management technology, and in particular to a method for aligning the names of power equipment, the equipment, and a computer-readable storage medium. Background Technology

[0002] In the daily operation and maintenance of power plants, drone inspections are increasingly widely used due to their high accuracy and speed. Currently, drone inspections are typically combined with on-site current and voltage testing equipment for power equipment.

[0003] However, when drone inspections name power equipment, they usually generate on-site labels based on the order of flight inspections, which does not match the actual names of the power equipment.

[0004] Therefore, to ensure the consistency of string names, it is currently necessary to rely on manual methods, combining as-built drawings and personal experience, to determine and label the correct equipment names for electrical equipment discovered during inspections. This is not only inefficient but also inaccurate. Summary of the Invention

[0005] The main objective of this application is to provide a method, device, and computer-readable storage medium for aligning the names of electrical equipment, with the aim of achieving accurate and efficient alignment of electrical equipment names.

[0006] This application provides a method for aligning the names of electrical equipment, the method comprising:

[0007] The actual spatial distribution information of each power device in the target power plant is obtained, and a first topology map is constructed based on the actual spatial distribution information of each power device to represent the actual positional relationship between each power device; the graph nodes corresponding to each power device in the first topology map are associated with the respective field identifiers of each power device. The design location information of each of the power devices in the engineering design drawing of the target power station is obtained, and a second topology diagram is constructed based on the design location information of each of the power devices to represent the design location relationship between the power devices; the graph nodes corresponding to each of the power devices in the second topology diagram are associated with the respective equipment names of each power device. A graph matching algorithm is used to match the topological structures of the first topology graph and the second topology graph to establish a mapping relationship between the field identifiers of each power device and the respective device names of each power device.

[0008] In one embodiment, the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the pixel coordinates of each of the power devices, the relative positional relationship of each of the power devices in the panoramic image is determined; The first topology map is constructed based on the relative positions of the various electrical devices in the panoramic view.

[0009] In one embodiment, the step of obtaining the actual spatial distribution information of each power device in the target power station includes: Obtain a panoramic view of the target power plant; The panoramic view of the target power station is segmented using a pre-trained power equipment segmentation model to obtain a power equipment segmentation mask image. The pixel coordinates of each power device are identified from the power device segmentation mask image using a contour detection algorithm.

[0010] In one embodiment, the actual spatial distribution information includes the geographical coordinates of the power equipment; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the geographical coordinates of each of the power devices, the relative positional relationship of each of the power devices in physical space is determined; The first topology map is constructed based on the relative positions of each power device in physical space.

[0011] In one embodiment, the step of obtaining the actual spatial distribution information of each power device in the target power station includes: Obtain the three-dimensional point cloud data of the target power station; Clustering is performed on the three-dimensional point cloud data to obtain point cloud clusters corresponding to each of the power devices; Based on the point cloud clusters corresponding to each of the power devices, determine the geometric center coordinates of each of the power devices; The geographical coordinates of each power device are determined based on the geometric center coordinates of each power device.

[0012] In one embodiment, the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station, and the geographic coordinates of the power equipment; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the pixel coordinates of each of the power devices, the relative positional relationship of each of the power devices in the panoramic image is determined, and based on the geographic coordinates of each of the power devices, the relative positional relationship of each of the power devices in physical space is determined. The first topology map is constructed based on the relative positions of each power device in the panoramic view and in physical space.

[0013] In one embodiment, the step of obtaining the design location information of each of the power devices in the engineering design drawing of the target power station includes: The location information of the equipment names of each power device is identified from the engineering design drawings using a pre-trained optical character recognition model. The location information of the equipment name of each of the power devices is used as the design location information of each of the power devices.

[0014] In one embodiment, the step of constructing a second topology map representing the design location relationships between the power devices based on their design location information includes: Based on the design location information of each of the power devices, the relative positional relationship of each of the power devices in the engineering design drawing is determined; Based on the relative positions of the various electrical devices in the engineering design drawing, a second topology diagram is constructed.

[0015] In one embodiment, the method further includes: Obtain the engineering change record document of the target power plant; The pre-trained document understanding model identifies structured change information about power equipment in the target power plant from the engineering change record document; the structured change information includes the addition, removal, or relocation of target power equipment. Update the second topology graph based on the structured change information; A graph matching algorithm is used to match the topological structure of the first topology graph and the updated second topology graph to establish a mapping relationship between the field identifier of each power device and the device name of each power device.

[0016] In one embodiment, the step of updating the second topology graph based on the structured change information includes: If the structured change information includes the addition of a target power device, based on the design location information of the target power device, a graph node corresponding to the target power device and the device name of the target power device are added to the second topology graph; If the structured change information includes the removal of a target power device, the graph node and device name corresponding to the target power device in the second topology graph will be deleted from the second topology graph. When the structured change information includes the location movement of the target power equipment, the position of the graph node and equipment name corresponding to the target power equipment in the second topology graph is adjusted based on the new design location information of the target power equipment.

[0017] In addition, to achieve the above objectives, this application also provides a power equipment name alignment device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power equipment name alignment method as described above.

[0018] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the power equipment name alignment method as described above.

[0019] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the power equipment name alignment method as described above.

[0020] This application provides a method for aligning the names of power equipment, comprising: obtaining the actual spatial distribution information of each power equipment in a target power plant, and constructing a first topology map to represent the actual positional relationship between each power equipment based on the actual spatial distribution information of each power equipment; the graph nodes corresponding to each power equipment in the first topology map are associated with the respective field identifiers of each power equipment; obtaining the design position information of each power equipment in the engineering design drawings of the target power plant, and constructing a second topology map to represent the design positional relationship between each power equipment based on the design position information of each power equipment; the graph nodes corresponding to each power equipment in the second topology map are associated with the respective equipment names of each power equipment; and matching the topological structures of the first topology map and the second topology map using a graph matching algorithm to establish a mapping relationship between the field identifiers of each power equipment and the respective equipment names of each power equipment.

[0021] Therefore, the technical solution provided in this application constructs a first topology map and a second topology map representing the positional relationships of the equipment by utilizing the actual spatial distribution information and design location information of each power equipment in the target power plant. A graph matching algorithm is then used to match the topological structures of the two maps, thereby automatically establishing the mapping relationship between the field identification of the power equipment and its name. This achieves automatic alignment between the field identification of the power equipment and its name. Compared to conventional methods that rely on manual comparison, this approach is not only more efficient but also more accurate.

[0022] In summary, the technical solution provided in this application can accurately and efficiently align the names of power equipment. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating the power equipment name alignment method provided in the first embodiment of this application; Figure 2 This is a power equipment segmentation mask diagram provided in the first embodiment of this application; Figure 3 The recognition result diagram provided in the first embodiment of this application; Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0026] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0027] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0028] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0029] In the daily operation and maintenance of power plants, drone inspections are increasingly widely used due to their high accuracy and speed. However, drone inspections also have certain limitations, such as the tendency to generate false alarms and the difficulty in accurately locating defects. Therefore, current methods typically combine drone inspections with on-site current and voltage monitoring equipment for power equipment.

[0030] However, when naming power equipment during drone inspections, the site identifiers are usually generated based on the order of the flight inspection. For example, if a power device is located in row m and column n in a panoramic view of the power plant, the drone will name it mn. This naming method does not match the actual name of the power equipment.

[0031] Therefore, to ensure the consistency of string names, it is currently necessary to rely on manual methods, combining as-built drawings and personal experience, to determine and label the correct equipment names for electrical equipment discovered during inspections. This is not only inefficient but also inaccurate.

[0032] Based on this, this application provides a method for aligning the names of power equipment, comprising: obtaining the actual spatial distribution information of each power equipment in a target power plant, and constructing a first topology map to represent the actual positional relationship between each power equipment based on the actual spatial distribution information of each power equipment; the graph nodes corresponding to each power equipment in the first topology map are associated with the respective field identifiers of each power equipment; obtaining the design position information of each power equipment in the engineering design drawings of the target power plant, and constructing a second topology map to represent the design positional relationship between each power equipment based on the design position information of each power equipment; the graph nodes corresponding to each power equipment in the second topology map are associated with the respective equipment names of each power equipment; and matching the topological structures of the first topology map and the second topology map using a graph matching algorithm to establish a mapping relationship between the field identifiers of each power equipment and the respective equipment names of each power equipment.

[0033] Therefore, the technical solution provided in this application constructs a first topology map and a second topology map representing the positional relationships of the equipment by utilizing the actual spatial distribution information and design location information of each power equipment in the target power plant. A graph matching algorithm is then used to match the topological structures of the two maps, thereby automatically establishing the mapping relationship between the field identification of the power equipment and its name. This achieves automatic alignment between the field identification of the power equipment and its name. Compared to conventional methods that rely on manual comparison, this approach is not only more efficient but also more accurate.

[0034] In summary, the technical solution provided in this application can accurately and efficiently align the names of power equipment.

[0035] The executing entity of the power equipment name alignment method of this application can be a power equipment name alignment device with data processing, network communication and program running functions. For example, it can be a control system, control circuit, etc. that can realize the above functions, or it can be an electronic device such as a mobile phone or computer. This embodiment does not specifically limit it.

[0036] The following examples illustrate the implementation of various embodiments, using the power equipment name alignment device as the execution subject.

[0037] This application proposes a method for aligning the names of power equipment according to a first embodiment. Please refer to [link / reference]. Figure 1 The method for aligning the names of electrical equipment may include steps S10 to S30: Step S10: Obtain the actual spatial distribution information of each power device in the target power station, and construct a first topology map to represent the actual positional relationship between each power device based on the actual spatial distribution information of each power device; the graph nodes corresponding to each power device in the first topology map are associated with the respective field identifiers of each power device. The target power station refers to the power station whose name needs to be aligned with the name of the power equipment. There can be one or more target power stations; this embodiment does not impose a specific limitation. Actual spatial distribution information refers to data that reflects the spatial location and layout of the power equipment at the work site. This may include, but is not limited to, the pixel coordinates of the power equipment in the panoramic view of the power station and / or its geographical coordinates in physical space (i.e., the work site or a geographic coordinate system). This embodiment does not impose a specific limitation. The first topology graph is a data structure based on a graph mathematical model. The graph nodes in the first topology graph correspond to the power equipment at the work site. The site identifier is a unique identifier automatically or temporarily assigned to the equipment by the system during the site data acquisition process, such as the serial number mn generated by a drone inspection.

[0038] When obtaining the pixel coordinates of each power device in the panoramic image of the target power station, the panoramic image of the target power station can be obtained first; then, the panoramic image of the target power station can be segmented using a pre-trained power device segmentation model to obtain a power device segmentation mask image; and then, the pixel coordinates of each power device can be identified from the power device segmentation mask image using a contour detection algorithm.

[0039] The panoramic image refers to a high-resolution digital image with georeferenced information covering all or key areas of the target power station. It is typically created by drones through aerial photography and automatic stitching. To ensure consistency between the panoramic image of the target power station and the panoramic image of the engineering design drawings, the drone can perform flight detection of the panoramic image, using the engineering design drawings as units. For example, assuming the panoramic image of the engineering design drawings is divided into n parts, the drone can perform flight detection for each part of the engineering design drawings separately to generate the panoramic image. The power equipment segmentation model is used to perform pixel-level classification of the input image to distinguish between power equipment areas and background areas. It can be obtained by constructing a power equipment image segmentation dataset from the drone's perspective and training it using a segmentation neural network. Optional model architectures for the power equipment segmentation model may include, but are not limited to, Unet, Deeplabv3, etc., and this embodiment does not impose specific limitations on them.

[0040] A power equipment segmentation mask is a binary image of the same size as the panoramic image, which visually masks the shape and position of all power equipment in the image. In this mask, all pixels identified as power equipment are marked as foreground (usually represented by white or 1), while the remaining pixels are marked as background (usually represented by black or 0). For example, when using white to mark pixels identified as power equipment and black to mark the background, the resulting power equipment segmentation mask can be referenced... Figure 2 .

[0041] Contour detection algorithms are used to find and extract the outer boundaries of connected regions in binary images. The pixel coordinates of the power equipment refer to the data representing the location of the power equipment in the image coordinate system of the panoramic image. These coordinates can be the geometric center coordinates of all pixels within the masked area where the power equipment is located, or the center point coordinates of the smallest rectangle that can enclose the outline of the power equipment, etc. This embodiment does not impose specific limitations on these coordinates.

[0042] Understandably, by combining power equipment segmentation models with contour detection algorithms to obtain the pixel coordinates of power equipment from panoramic images, high-precision equipment area recognition can be achieved in complex on-site environments. This effectively overcomes lighting variations and background interference, avoids subjective errors from manual calibration, and thus improves the accuracy of the obtained pixel coordinates of power equipment.

[0043] When obtaining the geographic coordinates of each power device, the three-dimensional point cloud data of the target power station can be obtained first; then the three-dimensional point cloud data can be clustered to obtain the point cloud clusters corresponding to each power device; then the geometric center coordinates of each power device can be determined based on the point cloud clusters corresponding to each power device; and finally, the geographic coordinates of each power device can be determined based on the geometric center coordinates of each power device.

[0044] Three-dimensional point cloud data refers to a massive, discrete set of three-dimensional spatial points obtained through scanning with LiDAR (Light Detection and Ranging) or similar active remote sensing equipment, used to describe the surface morphology of a target power plant. Clustering of three-dimensional point cloud data involves grouping points belonging to the same physical entity (such as photovoltaic strings or transformers) together. A point cloud cluster is a spatially tightly clustered set of points obtained after clustering the three-dimensional point cloud data, representing an independent and complete power equipment entity. Geometric center coordinates represent the coordinates of the average or central position of a point cloud cluster in three-dimensional space, usually obtained by calculating the average coordinates of all points within the cluster. Geographic coordinates represent the location of the power equipment in a recognized geodetic coordinate system, typically expressed in the form of longitude, latitude, and elevation (λ, φ, h).

[0045] When performing clustering processing on 3D point cloud data, clustering can be performed based on density (suitable for scenarios where the spacing between devices is uneven) or based on Euclidean distance (suitable for scenarios where the devices are arranged in a relatively regular manner and the spacing is known). This embodiment does not make any specific limitations on this.

[0046] When determining the geographic coordinates of each power device based on its geometric center coordinates, if the original point cloud data itself already records reference geographic coordinates, the geometric center coordinates can be directly converted to geographic coordinates. Alternatively, control points with known precise geographic coordinates can be first deployed at the target power plant's work site, and then the point cloud coordinate system can be registered with these control points using least squares, thereby converting the entire point cloud to a geographic coordinate system. In this way, the geometric center coordinates can be converted to geographic coordinates. This embodiment does not impose specific limitations on this approach.

[0047] In addition, when determining the geographical coordinates of each power device using the geometric center coordinates of each power device, one can first combine the power device segmentation mask to analyze and obtain the approximate geographical coordinates of each power device. Then, using the approximate geographical coordinates of each power device, the geographical coordinates of each power device determined by the geometric center coordinates of each power device are registered to obtain the final geographical coordinates of each power device. The accuracy of the geographical coordinates determined in this way can reach the centimeter level.

[0048] Understandably, by acquiring high-precision 3D point cloud data and performing clustering and geometric center calculations, the geographical coordinates of each power device can be determined in batches and efficiently. Since this method directly determines geographical coordinates based on spatial measurement data, it is less affected by ambient lighting and viewing angle, resulting in physical coordinates that are not only highly accurate but also reliable.

[0049] Step S20: Obtain the design location information of each power device in the engineering design drawing of the target power station, and construct a second topology diagram to represent the design location relationship between each power device based on the design location information of each power device; the graph nodes corresponding to each power device in the second topology diagram are associated with the respective equipment names of each power device. Design location information refers to data extracted from engineering design drawings (such as CAD (Computer-Aided Design) as-built drawings) to characterize the location of electrical equipment within the engineering design drawings. The second topology diagram is a graph data structure similar to the first topology diagram, with its graph nodes corresponding to the electrical equipment in the engineering design drawings. Equipment names are unique, standard names officially used in design documents, asset management systems, and operation and maintenance specifications.

[0050] When obtaining the design location information of each power device in the engineering design drawing of the target power plant, considering that the location information of the equipment name in the engineering design drawing includes not only coordinate data representing the location of the power device, but also the equipment name, a pre-trained optical character recognition model can be used to identify the location information of each power device's name from the engineering design drawing, and use this information as the design location information of each power device. Alternatively, the location coordinates of each power device in the engineering design drawing can be directly obtained, and the location coordinates can be associated with the equipment name to obtain the design location information of each power device. Furthermore, the location coordinates of each power device in the engineering design drawing can also be directly used as the design location information of each power device. This embodiment does not impose specific limitations on this approach.

[0051] The core function of the Optical Character Recognition (OCR) model is to analyze images or scanned documents containing text content to automatically detect the text area (i.e., locate it) and recognize the character content within that area. Ultimately, it transforms the text information in the image into structured, editable, and queryable text data and coordinate information. For example, when using an OCR model to identify the location information of equipment names for various power devices from engineering design drawings, the overall recognition result can be represented as follows: Figure 3 ,Depend on Figure 3 It can be seen that the identified location information includes not only the location of the device name, but also the device name itself.

[0052] In one feasible implementation, the step of constructing a second topology map representing the design location relationships between the power devices based on the design location information of each power device may include steps S21-S22: Step S21: Based on the design location information of each power device, determine the relative positional relationship of each power device in the engineering design drawing; The relative positional relationship of each electrical device in an engineering design drawing refers to the positional order and proximity relationship between electrical devices based on coordinate comparison, unaffected by drawing scaling or translation. For example, electrical device A is "to the left" of electrical device B, and electrical device C and electrical device D are "on the same horizontal row".

[0053] When determining the relative positional relationship of each power device in the engineering design drawing based on the design location information of each power device, sorting and grouping can be performed directly based on the position coordinates in the design location information. For example, the horizontal coordinates (i.e., X-coordinates) of all power devices can be sorted and clustered to divide them into different "columns," and the vertical coordinates (i.e., Y-coordinates) can be sorted and clustered to divide them into different "rows." Thus, the relative positional relationship between the devices can be constructed using the row index and column index of the power device. Alternatively, geometric calculations can be used to determine the relative positional relationship of each power device in the engineering design drawing. For example, the azimuth angle of one power device relative to another power device can be calculated using the design location information (e.g., by calculating the angle through coordinate difference) to determine the relative positional relationship of each power device in the engineering design drawing. This embodiment does not specifically limit the implementation method of step S21.

[0054] Step S22: Construct a second topology diagram based on the relative positions of each power device in the engineering design drawing.

[0055] In this embodiment, by utilizing the design location information of each power device, the relative positional relationship of each power device in the engineering design drawing is determined, and a second topology graph is constructed accordingly. This transforms the unstructured visual information of the drawings into a graph data structure with power devices as nodes and relative positional relationships as edges. This provides a data foundation for subsequent high-precision, automated name alignment through graph matching algorithms, fundamentally avoiding potential misjudgments and efficiency bottlenecks that may occur when manually interpreting drawings.

[0056] Step S30: Using a graph matching algorithm, the topological structures of the first topology graph and the second topology graph are matched to establish a mapping relationship between the field identifier of each power device and the device name of each power device.

[0057] Graph matching algorithms are used to calculate the correspondence between graph nodes in two graphs. Instead of directly comparing the specific coordinates or names of nodes, these algorithms analyze the similarity of topological attributes such as connection patterns and neighboring structures within their respective graphs. Examples of graph matching algorithms include Node2Vec and Louvain. Node2Vec converts each node in both graphs into a low-dimensional vector; then, by calculating the similarity (e.g., cosine similarity) between these vectors, it finds the most matching node pairs, thus establishing a mapping between the field identifier of electrical equipment and its name. Louvain identifies equipment groups (such as those in the same row or area) in both graphs, aligns these groups, and then aligns individual devices within each group, establishing a mapping between the field identifier of electrical equipment and its name.

[0058] As described above, the technical solution provided in this embodiment constructs a first topology map and a second topology map representing the location relationships of the equipment by utilizing the actual spatial distribution information and design location information of each power device in the target power plant. A graph matching algorithm is then used to match the topological structures of the two maps, thereby automatically establishing the mapping relationship between the field identification of the power equipment and its name. This achieves automatic alignment between the field identification of the power equipment and its name. Compared to conventional methods that rely on manual comparison, this approach is not only more efficient but also more accurate.

[0059] Therefore, the technical solution provided in this embodiment can accurately and efficiently achieve the alignment of power equipment names.

[0060] Based on the first embodiment described above, a second embodiment of the power equipment name alignment method of this application is proposed. In the second embodiment, when the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station, the step of constructing a first topological map to characterize the actual positional relationship between the power equipment based on the actual spatial distribution information of each power equipment may include steps S11 to S12: Step S11: Determine the relative positional relationship of each power device in the panoramic image based on the pixel coordinates of each power device. The relative positional relationship of each power device in the panoramic view refers to the layout and structural relationship between each power device on the panoramic view.

[0061] When determining the relative positional relationship of each power device in the panoramic image based on its pixel coordinates, a shortest path algorithm can be used to determine the shortest path between each power device based on its pixel coordinates, generating a distance matrix between the power devices. Then, a clustering algorithm is used to group the horizontal (X) and vertical (Y) coordinates to obtain the relative positional relationship of each power device in the panoramic image. Alternatively, the horizontal (X) coordinates of all power devices can be sorted and clustered to create different "columns," and the vertical (Y) coordinates can be sorted and clustered to create different "rows." The relative positional relationship between the devices can then be constructed using the row and column indices of the power devices. Alternatively, the KNN (K-Nearest Neighbors) algorithm can be used to find the K nearest devices for each power device based on its pixel coordinates (distance can be determined by the Euclidean distance of the pixel coordinates), thereby establishing an adjacency set as the layout structure relationship between the power devices in the panoramic image. This embodiment does not specifically limit the implementation of step S11.

[0062] Step S12: Construct a first topology map based on the relative positions of each power device in the panoramic view.

[0063] In this embodiment, the relative positions of each power device in the panoramic image are determined using the pixel coordinates of each device, and a first topological graph is constructed accordingly. This transforms the two-dimensional visual scene information collected by the UAV into a graph data structure with power devices as nodes and their relative positions in the image space as edges. This provides a data foundation for subsequent high-precision, automated name alignment using graph matching algorithms, effectively avoiding the inefficiency and subjective errors caused by manually judging and recording the positions of devices one by one from the image.

[0064] Furthermore, since this embodiment only needs to rely on UAV visual data when constructing the first topology map, and UAV visual data itself is easy to acquire and process, the efficiency of constructing the first topology map in this embodiment is relatively high.

[0065] Based on the first embodiment described above, a third embodiment of the power equipment name alignment method of this application is proposed. In the third embodiment, when the actual spatial distribution information includes the geographical coordinates of the power equipment, the step of constructing a first topological map to characterize the actual positional relationship between the power equipment based on the actual spatial distribution information of each power equipment may include steps S13 to S14: Step S13: Based on the geographical coordinates of each power device, determine the relative positional relationship of each power device in physical space; The relative positional relationship of each power device in physical space refers to the spatial layout and connection relationship between each power device in physical space, which reflects the actual proximity, orientation and connection topology between the devices.

[0066] When determining the relative positional relationship of each power device in the panoramic image based on its pixel coordinates, the KNN algorithm can be used to find the K devices with the closest Euclidean distance to each power device in the geographic coordinate system, thereby establishing an adjacency set as the relative positional relationship of each power device in physical space. Alternatively, a fixed distance threshold can be set, and two power devices whose geographic coordinates are less than the threshold can be considered spatially adjacent to obtain the relative positional relationship of each power device in physical space. Furthermore, the azimuth angles between each power device can be calculated using its pixel coordinates to determine the relative positional relationship of each power device in the panoramic image. This embodiment does not specifically limit the implementation method of step S13.

[0067] Step S14: Construct a first topology map based on the relative positions of each power device in the physical space.

[0068] In this embodiment, by utilizing the high-precision geographic coordinates of each power device, their relative positions in physical space are determined, and a first topological graph is constructed accordingly. This transforms high-precision real-space measurement data into a graph data structure with power devices as nodes and real-space proximity relationships as edges. This provides a data foundation for subsequent high-precision, automated name alignment using graph matching algorithms, fundamentally avoiding errors such as perspective distortion and scale uncertainty that may arise from image estimation.

[0069] Furthermore, since the geographical coordinates used in constructing the first topology map in this embodiment have high precision and absolute spatial significance, the constructed first topology map has higher reliability and robustness in expressing the real positional relationships between various power devices.

[0070] Based on the first embodiment described above, a fourth embodiment of the power equipment name alignment method of this application is proposed. In the fourth embodiment, when the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station and the geographical coordinates of the power equipment, the step of constructing a first topological map to characterize the actual positional relationship between the power equipment based on the actual spatial distribution information of each power equipment may include steps S15-S16: Step S15: Based on the pixel coordinates of each power device, determine the relative positional relationship of each power device in the panoramic image, and based on the geographic coordinates of each power device, determine the relative positional relationship of each power device in the physical space. Step S16: Construct a first topology map based on the relative positions of each power device in the panoramic view and in physical space.

[0071] When constructing the first topology map based on the relative positions of each power device in the panoramic image and in physical space, the adjacency relationship sets generated using pixel coordinates and those generated using geographic coordinates, obtained through the KNN algorithm, can be intersected or merged to form a processed adjacency relationship set, which is then used to construct the first topology map. Alternatively, an initial topology map can be generated first based on the relative positions of each power device in the panoramic image, and then the structure of the initial topology map can be fine-tuned using a graph optimization algorithm based on the relative positions of each power device in physical space to generate the first topology map. Similarly, an initial topology map can be generated first based on the relative positions of each power device in physical space, and then the structure of the initial topology map can be fine-tuned using a graph optimization algorithm based on the relative positions of each power device in the panoramic image to generate the first topology map. This embodiment does not specifically limit the implementation method of step S16.

[0072] This embodiment utilizes both the pixel coordinates and geographic coordinates of power equipment to collaboratively determine their relative positions in image and physical space, and constructs a first topology map accordingly. This combines the advantages of readily available and rapidly processed visual data with the high precision of geographic data. On one hand, the global layout information provided by the panoramic image helps in quickly understanding the overall arrangement of the equipment; on the other hand, the high-precision spatial information provided by geographic coordinates can correct geometric errors caused by viewing angle and distortion, and give the topology map a true scale and orientation. Thus, the final constructed first topology map possesses both good structural robustness and extremely high spatial accuracy, providing a data foundation for subsequent high-precision, automated name alignment using graph matching algorithms. Compared to methods relying solely on pixel coordinates or geographic coordinates, the first topology map constructed in this embodiment demonstrates higher accuracy and reliability in aligning large-scale, complex terrain or power plant scenarios with visual occlusion.

[0073] Based on the first, second, third, and / or fourth embodiments described above, a fifth embodiment of the power equipment name alignment method of this application is proposed. In the fifth embodiment, the power equipment name alignment method may further include steps S01 to S04: Step S01: Obtain the engineering change record document of the target power station; Engineering change record documents refer to written or electronic documents generated during the design, construction, and operation and maintenance of power plants to record changes in the layout, configuration, or status of power equipment. These documents may include, but are not limited to, as-built drawings, design change notices, engineering liaison forms, and supplementary as-built drawings. This embodiment does not impose specific limitations on these documents.

[0074] Step S02: Using a pre-trained document understanding model, identify structured change information about the power equipment in the target power plant from the engineering change record document; the structured change information includes the addition, removal, or relocation of the target power equipment; Document understanding models are large language or visual language models specifically trained for fine-tuning engineering documents. They not only possess general text understanding capabilities but also learn engineering terminology, common phrases in change descriptions, drawing symbols, and table structures, enabling them to extract key content from unstructured engineering documents. Document understanding models can be trained using large-scale text-image understanding models like Qwen2-VL. The training corpus can include, but is not limited to, historical civil engineering documents, handwritten records, and tables; this embodiment does not impose specific limitations on this.

[0075] Structured change information refers to changes to electrical equipment as output by the document understanding model, represented in a computer-parseable format (such as JSON). Target electrical equipment refers to one or more specific pieces of electrical equipment described in the engineering change log document that require addition, removal, or relocation.

[0076] When identifying structured change information about power equipment in a target power plant from engineering change record documents using a pre-trained document understanding model, if the engineering change record document is primarily in natural language, the document understanding model can directly read the text to identify sentences such as "Add power equipment B to the east of power equipment A" and "Remove power equipment A," and parse them into structured fields as structured change information. If the engineering change record document contains scanned copies of sketches and markings, the document understanding model can simultaneously process the images in the engineering change record document and extract the text to understand the correspondence between visual elements such as arrows and annotations and the text descriptions, thereby obtaining structured change information.

[0077] Step S03: Update the second topology graph based on the structured change information; When updating the second topology diagram based on structured change information, if the structured change information includes the addition of a target power device, the diagram node corresponding to the target power device and the device name of the target power device are added to the second topology diagram based on the design location information of the target power device; if the structured change information includes the removal of a target power device, the diagram node and device name corresponding to the target power device in the second topology diagram are deleted from the second topology diagram; if the structured change information includes the relocation of a target power device, the positions of the diagram node and device name corresponding to the target power device in the second topology diagram are adjusted based on the new design location information of the target power device.

[0078] Step S04: Using a graph matching algorithm, the topological structure of the first topology graph and the updated second topology graph are matched to establish a mapping relationship between the field identifier of each power device and the device name of each power device.

[0079] In this embodiment, the unstructured engineering change record document is obtained by using a document understanding model to understand it and transform it into machine-readable structured change information. The second topology map is then updated accordingly to ensure that the second topology map is always synchronized with the latest design status of the target power plant. Finally, the first topology map, which reflects the actual layout on site, is matched with the updated second topology map to establish an accurate mapping relationship between the on-site identification of power equipment and the equipment name.

[0080] Therefore, this embodiment realizes a fully automated process from change perception to alignment result update, enabling the system to have continuous adaptive alignment capability. This fundamentally overcomes the problem of outdated design benchmarks caused by power plant reconstruction, expansion, or equipment relocation, ensuring that the accuracy, completeness, and timeliness of equipment name alignment can be maintained reliably for a long time, even during the dynamic evolution of the power plant status.

[0081] This application also provides a power equipment name alignment device, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the power equipment name alignment method in the above embodiments.

[0082] The following is for reference. Figure 4 It shows a structural schematic diagram of a power equipment name alignment device suitable for implementing embodiments of this application. Figure 4 The power equipment name alignment device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0083] like Figure 4As shown, the power equipment name alignment device may include a processing unit 101 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory 102 or a program loaded from storage device 103 into random access memory 104. Random access memory 104 also stores various programs and data required for the operation of the power equipment name alignment device. The processing unit 101, read-only memory 102, and random access memory 104 are interconnected via bus 105. Input / output interface 106 is also connected to bus 105. Typically, the following systems can be connected to input / output interface 106: input devices 107 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 108 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 103 including, for example, magnetic tapes, hard disks, etc.; and communication devices 109. Communication device 109 allows the power equipment name alignment device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagram shows electrical equipment with various systems aligned to the device names, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0084] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 103, or installed from read-only memory 102. When the computer program is executed by processing device 101, it performs the functions defined in the methods of the embodiments of this application.

[0085] The power equipment name alignment device provided in this application adopts the power equipment name alignment method in the above embodiments, and can accurately and efficiently achieve the alignment of power equipment names. Compared with the prior art, the beneficial effects of the power equipment name alignment device provided in this application are the same as the beneficial effects of the power equipment name alignment method provided in the above embodiments, and other technical features in this power equipment name alignment device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0086] It should be understood that various parts of the embodiments of this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0087] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the above claims.

[0088] This application also provides a computer-readable storage medium storing a computer program that can run on a processor, the computer program being used to execute the power equipment name alignment method in the above embodiments.

[0089] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0090] The aforementioned computer-readable storage medium may be included in the power equipment name alignment device; or it may exist independently and not assembled into the power equipment name alignment device.

[0091] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the power equipment name alignment device, the power equipment name alignment device performs the following actions: It acquires the actual spatial distribution information of each power equipment in the target power plant, and constructs a first topology graph representing the actual positional relationships between the power equipment based on this information. In the first topology graph, each power equipment's corresponding graph node is associated with its respective field identifier. It then acquires the design position information of each power equipment in the engineering design drawings of the target power plant, and constructs a second topology graph representing the design positional relationships between the power equipment based on this information. In the second topology graph, each power equipment's corresponding graph node is associated with its respective equipment name. Finally, it uses a graph matching algorithm to match the topological structures of the first and second topology graphs to establish a mapping relationship between the field identifiers of each power equipment and their respective equipment names.

[0092] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0094] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0095] The computer-readable storage medium provided in this application embodiment stores computer-readable program instructions for executing the above-described power equipment name alignment method, which can accurately and efficiently achieve the alignment of power equipment names. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application embodiment are the same as the beneficial effects of the power equipment name alignment method provided in the above-described embodiments, and will not be repeated here.

[0096] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the power equipment name alignment method described above.

[0097] The computer program product provided in this application can accurately and efficiently align the names of power equipment. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the power equipment name alignment method provided in the above embodiments, and will not be repeated here.

[0098] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for aligning the names of electrical equipment, characterized in that, The method includes: The actual spatial distribution information of each power device in the target power plant is obtained, and a first topology map is constructed based on the actual spatial distribution information of each power device to represent the actual positional relationship between each power device; the graph nodes corresponding to each power device in the first topology map are associated with the respective field identifiers of each power device. The design location information of each of the power devices in the engineering design drawing of the target power station is obtained, and a second topology diagram is constructed based on the design location information of each of the power devices to represent the design location relationship between the power devices; the graph nodes corresponding to each of the power devices in the second topology diagram are associated with the respective equipment names of each power device. A graph matching algorithm is used to match the topological structures of the first topology graph and the second topology graph to establish a mapping relationship between the field identifiers of each power device and the respective device names of each power device.

2. The method as described in claim 1, characterized in that, When the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the pixel coordinates of each of the power devices, the relative positional relationship of each of the power devices in the panoramic image is determined; The first topology map is constructed based on the relative positions of the various electrical devices in the panoramic view.

3. The method as described in claim 2, characterized in that, The step of obtaining the actual spatial distribution information of each power device in the target power station includes: Obtain a panoramic view of the target power plant; The panoramic view of the target power station is segmented using a pre-trained power equipment segmentation model to obtain a power equipment segmentation mask image. The pixel coordinates of each power device are identified from the power device segmentation mask image using a contour detection algorithm.

4. The method as described in claim 1, characterized in that, When the actual spatial distribution information includes the geographical coordinates of the power equipment; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the geographical coordinates of each of the power devices, the relative positional relationship of each of the power devices in physical space is determined; The first topology map is constructed based on the relative positions of each power device in physical space.

5. The method as described in claim 4, characterized in that, The step of obtaining the actual spatial distribution information of each power device in the target power station includes: Obtain the three-dimensional point cloud data of the target power station; Clustering is performed on the three-dimensional point cloud data to obtain point cloud clusters corresponding to each of the power devices; Based on the point cloud clusters corresponding to each of the power devices, determine the geometric center coordinates of each of the power devices; The geographical coordinates of each power device are determined based on the geometric center coordinates of each power device.

6. The method as described in claim 1, characterized in that, When the actual spatial distribution information includes the pixel coordinates of the power equipment in the panoramic view of the target power station, and the geographic coordinates of the power equipment; The step of constructing a first topological map representing the actual positional relationships between the power devices based on their actual spatial distribution information includes: Based on the pixel coordinates of each of the power devices, the relative positional relationship of each of the power devices in the panoramic image is determined, and based on the geographic coordinates of each of the power devices, the relative positional relationship of each of the power devices in physical space is determined. The first topology map is constructed based on the relative positions of each power device in the panoramic view and in physical space.

7. The method as described in claim 1, characterized in that, The step of obtaining the design location information of each of the power devices in the engineering design drawing of the target power station includes: The location information of the equipment names of each power device is identified from the engineering design drawings using a pre-trained optical character recognition model. The location information of the equipment name of each of the power devices is used as the design location information of each of the power devices.

8. The method as described in claim 1, characterized in that, The step of constructing a second topology map representing the design location relationships between the power devices based on their design location information includes: Based on the design location information of each of the power devices, the relative positional relationship of each of the power devices in the engineering design drawing is determined; Based on the relative positions of the various electrical devices in the engineering design drawing, a second topology diagram is constructed.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Obtain the engineering change record document of the target power plant; The pre-trained document understanding model identifies structured change information about power equipment in the target power plant from the engineering change record document; the structured change information includes the addition, removal, or relocation of target power equipment. Update the second topology graph based on the structured change information; A graph matching algorithm is used to match the topological structure of the first topology graph and the updated second topology graph to establish a mapping relationship between the field identifier of each power device and the device name of each power device.

10. The method as described in claim 9, characterized in that, The step of updating the second topology graph based on the structured change information includes: If the structured change information includes the addition of a target power device, based on the design location information of the target power device, a graph node corresponding to the target power device and the device name of the target power device are added to the second topology graph; If the structured change information includes the removal of a target power device, the graph node and device name corresponding to the target power device in the second topology graph will be deleted from the second topology graph. When the structured change information includes the location movement of the target power equipment, the position of the graph node and equipment name corresponding to the target power equipment in the second topology graph is adjusted based on the new design location information of the target power equipment.

11. A power equipment name alignment device, characterized in that, The power equipment name alignment device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power equipment name alignment method as described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the power equipment name alignment method as described in any one of claims 1 to 10.

Images