Three-dimensional reconstruction method and system for surrounding environment of electric power facility

Abstract

The invention relates to the technical field of three-dimensional reconstruction, in particular to an electric power facility surrounding environment three-dimensional reconstruction method and system. The method comprises the following steps: acquiring electric power facility data, performing electric power facility layout structure analysis, and constructing an electric power facility three-dimensional model; obtaining electric power facility environment data, carrying out dynamic environment evolution, and constructing an electric power facility environment dynamic evolution model; performing rendering and model alignment embedding processing on the electric power facility three-dimensional model based on the electric power facility environment dynamic evolution model to generate an environment-electric power facility fusion model, and performing electric power facility corona loss fluctuation detection and environment fluctuation factor analysis; corona environment disturbance area detection and error calculation are carried out on the environment-electric power facility fusion model, disturbance error data are generated, and corona environment disturbance reconstruction processing is carried out on the environment-electric power facility fusion model. According to the invention, the electric power facility environment combined corona loss dynamic three-dimensional model reconstruction can be realized.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional reconstruction technology, and in particular to a method and system for three-dimensional reconstruction of the surrounding environment of power facilities. Background Art

[0002] Against the backdrop of today's rapidly developing power industry, the safe and stable operation of power facilities is crucial for ensuring electricity supply for production and daily life. With the continuous advancement of technologies such as ultra-high voltage transmission and smart grids, the scale and complexity of power facilities continue to increase, and the surrounding environments in which they operate are also becoming increasingly diverse and complex. Traditional power facility management and environmental monitoring methods are unable to promptly reflect the impact of environmental changes on power facilities. Existing 3D modeling technologies, when applied to the surrounding environments of power facilities, mostly focus solely on the geometric modeling of the facilities themselves, failing to fully consider the dynamic impact of environmental factors (such as meteorological conditions and topographic changes) on power facility operation. Furthermore, corona loss in power facilities is a significant factor affecting their operating efficiency and lifespan, and its fluctuations are closely related to the surrounding environment. However, there is currently a lack of methods that can integrate power facility models, environmental dynamic evolution models, and corona loss detection, resulting in low accuracy in 3D reconstruction of the surrounding environments of power facilities. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for three-dimensional reconstruction of the surrounding environment of power facilities to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a method for 3D reconstruction of the surrounding environment of power facilities includes the following steps:

[0005] Step S1: Acquire power facility data, perform power facility layout structure analysis based on the power facility data, and generate power facility layout structure data; construct a three-dimensional model of the power facility based on the power facility spatial layout structure data;

[0006] Step S2: Acquire power facility environmental data; perform dynamic environmental evolution according to the power facility environmental data to generate dynamic environmental evolution data; and construct a power facility environmental dynamic evolution model based on the dynamic environmental evolution data;

[0007] Step S3: Rendering the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; performing model alignment and embedding processing on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model;

[0008] Step S4: performing corona loss fluctuation detection on power facilities according to the environment-power facility fusion model to generate corona fluctuation loss data; performing environmental fluctuation factor analysis according to the dynamic environment evolution data to generate environmental fluctuation factor data; performing corona environment disturbance area detection on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate corona environment disturbance area data;

[0009] Step S5: performing disturbance error calculation based on the corona environment disturbance area data to generate disturbance error data; performing corona environment disturbance reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstruction model of the environment-power facility.

[0010] Furthermore, step S1 includes the following steps:

[0011] Step S11: acquiring power facility data, and performing power facility layout structure analysis based on the power facility data to generate power facility layout structure data;

[0012] Step S12: performing power facility spatial architecture analysis based on the power facility layout structure data to generate power facility spatial architecture data;

[0013] Step S13: performing power facility interaction node analysis on the power facility spatial architecture data to generate power facility interaction node data;

[0014] Step S14: constructing a three-dimensional model of the power facility based on the power facility interaction node data and the power facility spatial architecture data.

[0015] Furthermore, step S2 includes the following steps:

[0016] Step S21: acquiring power facility environmental data, and performing power facility environmental feature analysis based on the power facility environmental data to generate power facility environmental feature data;

[0017] Step S22: Calculating the environmental change cycle of the power facility environmental data based on the power facility environmental characteristic data to generate environmental change cycle data;

[0018] Step S23: performing a power facility environmental characteristic differentiation analysis based on the power facility environmental characteristic data and the environmental change cycle data to generate power facility environmental characteristic differentiation data;

[0019] Step S24: performing power facility environment change chain analysis based on the power facility environment feature differentiation data to generate power facility environment change chain data;

[0020] Step S25: performing dynamic environmental evolution based on the environmental change cycle data and the power facility environmental change chain data to generate dynamic environmental evolution data;

[0021] Step S26: constructing a power facility environment dynamic evolution model based on the dynamic environment evolution data.

[0022] Furthermore, step S3 includes the following steps:

[0023] Step S31: Analyze meteorological impact factors based on the dynamic evolution model of the power facility environment to generate meteorological impact factor data;

[0024] Step S32: performing a structural deformation mapping correlation process on the power facility according to the meteorological impact factor data to generate meteorological-deformation correlation factor data;

[0025] Step S33: Rendering the three-dimensional model of the power facility based on the weather-deformation correlation factor data to generate a rendered three-dimensional model of the power facility;

[0026] Step S34: performing model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model.

[0027] Furthermore, step S4 includes the following steps:

[0028] Step S41: performing power facility magnetic field wave frequency analysis based on the environment-power facility fusion model to generate power facility magnetic field wave frequency data;

[0029] Step S42: performing corona loss fluctuation detection based on the magnetic field wave frequency data of the power facility to generate corona fluctuation loss data;

[0030] Step S43: performing environmental fluctuation factor analysis based on the dynamic environmental evolution data to generate environmental fluctuation factor data;

[0031] Step S44: performing corona environmental disturbance area detection on the environment-power facility fusion model based on the corona fluctuation loss data and the environmental fluctuation factor data to generate corona environmental disturbance area data.

[0032] Furthermore, step S42 includes the following steps:

[0033] Step S421: performing magnetic field wave-frequency interaction analysis based on the magnetic field wave-frequency data of the power facility to generate wave-frequency interaction data;

[0034] Step S422: performing resonance mapping spectrum processing on the power facility magnetic field wave frequency data based on the wave frequency interaction data to generate resonance mapping spectrum data;

[0035] Step S423: performing electromagnetic medium jump response spectrum analysis according to the resonance mapping spectrum data to generate electromagnetic medium jump response spectrum data;

[0036] Step S424: performing corona loss fluctuation detection on the power facility magnetic field wave frequency data based on the electromagnetic medium jump response spectrum data to generate corona fluctuation loss data.

[0037] Furthermore, step S424 includes the following steps:

[0038] Conduct corona disturbance hierarchy analysis based on electromagnetic medium jump response spectrum data to generate corona disturbance hierarchy data;

[0039] Performing corona medium ionization shower mapping processing based on corona disturbance hierarchy data to generate corona medium ionization shower data;

[0040] Calculate the corona medium oscillation coefficient based on the corona medium ionizing shower data to generate the corona medium oscillation coefficient;

[0041] Based on the corona medium oscillation coefficient, the corona stratum ionization attenuation analysis is performed on the corona disturbance stratum data to generate the corona stratum ionization attenuation data;

[0042] Based on the corona layer ion attenuation data, the corona loss fluctuation detection is performed on the magnetic field wave frequency data of the power facility to generate the corona fluctuation loss data.

[0043] Furthermore, step S44 includes the following steps:

[0044] Step S441: performing corona wave frequency analysis based on the corona wave loss data to generate corona wave frequency data;

[0045] Step S442: performing corona wave frequency resonance processing on the corona wave frequency data based on the environmental fluctuation factor data to generate corona wave frequency resonance data;

[0046] Step S443: performing corona amplitude deviation analysis based on the corona wave frequency resonance data to generate corona amplitude deviation data;

[0047] Step S444: performing smoothness disturbance calculation on the corona wave frequency data according to the corona amplitude deviation data to generate smoothness disturbance data;

[0048] Step S445: performing corona environment disturbance area detection on the environment-power facility fusion model based on the smoothness disturbance data to generate corona environment disturbance area data.

[0049] Furthermore, step S5 includes the following steps:

[0050] Step S51: performing disturbance dislocation superposition depth analysis on the corona environment disturbance area data to generate disturbance dislocation superposition depth data;

[0051] Step S52: performing disturbance error calculation based on the disturbance misalignment superposition depth data to generate disturbance error data;

[0052] Step S53: performing three-dimensional reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstructed model of the environment-power facility.

[0053] Furthermore, the present invention also provides a three-dimensional reconstruction system for the surrounding environment of an electric power facility, which is used to execute the above-mentioned three-dimensional reconstruction method for the surrounding environment of an electric power facility. The three-dimensional reconstruction system for the surrounding environment of an electric power facility includes:

[0054] The power facility 3D construction module is used to obtain power facility data, perform power facility spatial layout structure analysis based on the power facility data, generate power facility spatial layout structure data; and construct a power facility 3D model based on the power facility spatial layout structure data.

[0055] A dynamic evolution model building module is used to obtain power facility environmental data; perform dynamic environmental evolution based on the power facility environmental data to generate dynamic environmental evolution data; and build a dynamic environmental evolution model for the power facility environment based on the dynamic environmental evolution data;

[0056] A fusion model rendering and embedding module is used to render the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; and perform model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model;

[0057] The electromagnetic disturbance area detection module is used to detect the corona loss fluctuation of power facilities based on the environment-power facility fusion model and generate corona fluctuation loss data; analyze the environmental fluctuation factor based on the dynamic environment evolution data and generate environmental fluctuation factor data; and detect the corona environment disturbance area based on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate the corona environment disturbance area data.

[0058] The model reconstruction module is used to calculate the disturbance error based on the corona environment disturbance area data and generate disturbance error data; based on the disturbance error data, the environment-power facility fusion model is subjected to corona environment disturbance reconstruction processing to generate a three-dimensional reconstruction model of the environment-power facility.

[0059] Beneficial effects of the present invention:

[0060] 1. The three-dimensional reconstruction method of the surrounding environment of power facilities proposed in the present invention has the beneficial effect of obtaining power facility data and analyzing the layout structure of power facilities based on the power facility data. The core advantage of this step is that it can systematically sort out the distribution status, connection relationship and topological structure of power facilities in space. Through accurate analysis of key information such as the direction of transmission lines, substation locations and tower distribution, the overall architecture of the power network can be clearly grasped, providing a solid data foundation for subsequent troubleshooting and planning expansion. Constructing a three-dimensional model of the power facility based on the layout structure data converts the abstract data into an intuitive and visual three-dimensional form. Operation and maintenance personnel can observe the three-dimensional structure of the power facility from multiple angles and all directions, improving their understanding and management efficiency of complex power facilities. Acquiring power facility environmental data and performing dynamic environmental evolution to generate dynamic environmental evolution data fully takes into account the complexity and dynamic nature of the power facility operating environment. The environmental data covers multiple factors such as meteorological conditions (such as wind speed, humidity and temperature), topography and landforms, and changes in surrounding buildings and facilities. By analyzing the evolution of this data over time, the possible impact of environmental changes on power facilities can be predicted. Building a dynamic environmental evolution model based on dynamic environmental evolution data can digitally and visually simulate dynamic environmental changes, such as the impact of typhoon paths on transmission lines and the changes in the electromagnetic environment around substations caused by urban development. This allows power operations and maintenance personnel to proactively anticipate potential risks and develop preventative measures to mitigate damage to power facilities from natural disasters and environmental changes, ensuring the stable operation of the power system. It also provides dynamic environmental data support for the full lifecycle management of power facilities. Rendering a 3D model of a power facility based on the dynamic environmental evolution model allows the facility to be presented within a simulated, real-world environment, enhancing the model's realism. Model alignment and embedding are then performed to generate a fusion model of the environment and power facility, achieving a deep integration of the power facility and its operating environment. This breaks the limitation of the separate power facility and environmental models, allowing operations and maintenance personnel to comprehensively analyze the interactions between the power facility and the environment within the same model. Corona loss fluctuation detection for power facilities based on the fusion model enables real-time and accurate monitoring of changes in power facility losses caused by corona phenomena during operation, reducing the waste of power resources and equipment damage caused by excessive corona losses. Environmental fluctuation factor analysis is performed based on dynamic environmental evolution data to clarify the degree and patterns of influence of various environmental factors on corona loss. For example, the correlation between environmental factors such as humidity and wind speed and corona loss is analyzed. Corona environmental disturbance area detection is performed based on corona fluctuation data and environmental impact fluctuation factor data. This can accurately locate areas with abnormal corona loss caused by environmental influences, helping operation and maintenance personnel quickly identify problem points.The disturbance error is calculated based on the data of the corona environment disturbance area. By quantifying the disturbance error, the degree and scope of the impact of the corona environment disturbance on the operation of power facilities can be accurately assessed. Based on the disturbance error data, the corona environment disturbance is reconstructed on the environment-power facility fusion model to achieve dynamic correction and optimization of the model, so that the model can more accurately reflect the true state of the power facilities under the corona environment disturbance. At the same time, the three-dimensional reconstructed model also provides a visual reference for the transformation and upgrading of power facilities, which helps designers optimize the structure of power facilities, timely reduce corona losses, improve the operating performance and service life of power facilities, and ensure the stable and efficient operation of the power system.

[0061] 2. The three-dimensional reconstruction system of the surrounding environment of electric power facilities proposed in the present invention is composed of a three-dimensional construction module of electric power facilities, a dynamic evolution model construction module, a fusion model rendering and embedding module, an electromagnetic disturbance area detection module and a model reconstruction module. It can realize the three-dimensional reconstruction method of the surrounding environment of any electric power facility described in the present invention, and is used to combine the operations between the computer programs running on each module to realize the three-dimensional reconstruction method of the surrounding environment of electric power facilities. The internal structures of the system cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient three-dimensional reconstruction process of the surrounding environment of electric power facilities, thereby simplifying the operating procedures of the three-dimensional reconstruction system of the surrounding environment of electric power facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0063] Figure 1 A schematic flow chart of the steps of the method for three-dimensional reconstruction of the surrounding environment of power facilities according to the present invention;

[0064] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0065] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0066] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0067] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0068] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0069] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for three-dimensional reconstruction of the surrounding environment of power facilities, the method comprising the following steps:

[0070] Step S1: Acquire power facility data, perform power facility layout structure analysis based on the power facility data, and generate power facility layout structure data; construct a three-dimensional model of the power facility based on the power facility spatial layout structure data;

[0071] Step S2: Acquire power facility environmental data; perform dynamic environmental evolution according to the power facility environmental data to generate dynamic environmental evolution data; and construct a power facility environmental dynamic evolution model based on the dynamic environmental evolution data;

[0072] Step S3: Rendering the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; performing model alignment and embedding processing on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model;

[0073] Step S4: performing corona loss fluctuation detection on power facilities according to the environment-power facility fusion model to generate corona fluctuation loss data; performing environmental fluctuation factor analysis according to the dynamic environment evolution data to generate environmental fluctuation factor data; performing corona environment disturbance area detection on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate corona environment disturbance area data;

[0074] Step S5: performing disturbance error calculation based on the corona environment disturbance area data to generate disturbance error data; performing corona environment disturbance reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstruction model of the environment-power facility.

[0075] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a flow chart showing the steps of a method for 3D reconstruction of the surrounding environment of an electric power facility according to the present invention. In this example, the method for 3D reconstruction of the surrounding environment of an electric power facility includes the following steps:

[0076] Step S1: Acquire power facility data, perform power facility layout structure analysis based on the power facility data, and generate power facility layout structure data; construct a three-dimensional model of the power facility based on the power facility spatial layout structure data;

[0077] In an embodiment of the present invention, high-precision geographic information acquisition equipment, such as a drone equipped with a laser radar (LiDAR), is used to perform a comprehensive scan of the area where power facilities are located. The LiDAR emits a laser beam and measures the time delay of the reflected light, thereby obtaining the three-dimensional coordinate information of each point on the surface of the power facility. This data serves as the primary source of power facility data. Graph theory and topological analysis methods are applied to the collected data to analyze the connectivity between the various components of the power facility. For example, the electrical connection topology between transformers, switchgear, and transmission lines within a substation is analyzed to generate detailed power facility layout data. To construct a three-dimensional model of the power facility, polygonal modeling techniques are employed based on this acquired power facility layout data. Each component of the power facility, such as a tower, is abstracted as a combination of cylindrical polygons, and conductors are treated as linear polygons with a specific tension curve. By precisely setting the vertex coordinates of each polygon to align with the actual measured spatial location of the power facility, a three-dimensional model that accurately reflects the actual form of the power facility is gradually constructed. Furthermore, material mapping technology is used to impart realistic material appearance to each component of the model, such as the metallic texture of the tower and the color of the conductor insulation, enhancing the realism of the three-dimensional model of the power facility.

[0078] Step S2: Acquire power facility environmental data; perform dynamic environmental evolution according to the power facility environmental data to generate dynamic environmental evolution data; and construct a power facility environmental dynamic evolution model based on the dynamic environmental evolution data;

[0079] In an embodiment of the present invention, environmental data from power facilities is acquired using a variety of environmental monitoring sensors. Temperature and humidity sensors are strategically distributed around the facility to accurately collect ambient temperature and humidity data by measuring the water vapor content and molecular thermal motion in the air. Anemometers monitor wind speed and direction in real time based on the rotation speed of their cups and the direction of the vane. Light intensity sensors are deployed to sense changes in ambient light intensity based on the photoelectric effect. Data collected by these sensors at regular intervals (e.g., every minute) is aggregated to form a time series of power facility environmental data. To achieve dynamic environmental evolution, time series analysis algorithms, such as the autoregressive integrated moving average (ARIMA) model, are employed. Taking temperature and humidity data as an example, by analyzing historical temperature and humidity data for trends, periodic fluctuations, and random interference factors, the evolution of temperature and humidity over a short period of time in the future is predicted. For wind speed and direction, a fluid dynamics model, combined with real-time monitoring data, simulates the flow of air around the power facility, generating dynamic environmental evolution data. Based on this data, a particle system and physics simulation engine are employed to construct a dynamic evolution model of the power facility environment. For example, the particle system is used to simulate the trajectory of sand particles drifting in the wind, and the physical simulation engine is used to simulate the swaying posture of vegetation under different wind speeds, vividly presenting the dynamic changes of the environment.

[0080] Step S3: Rendering the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; performing model alignment and embedding processing on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model;

[0081] In an embodiment of the present invention, physically based rendering (PBR) technology is employed when rendering the three-dimensional model of a power facility based on the dynamic evolution model of the power facility environment. PBR technology, based on the physical principles of real-world illumination, considers the reflection, refraction, and absorption properties of ambient light, direct light, and the material of an object. For example, under strong direct sunlight, the surface of metal components of a power facility produces strong specular reflections. PBR technology accurately simulates this optical phenomenon, making the rendered three-dimensional model of the power facility appear realistic under varying ambient lighting conditions. When performing model alignment and embedding to generate the environment-power facility fusion model, a spatial coordinate matching algorithm is employed. Using the coordinate system of the Geographic Information System (GIS) as a reference, the coordinates of the three-dimensional power facility model are uniformly matched with the geographic spatial coordinates of the dynamic evolution model. This ensures the accurate positioning of the power facility within the environmental scene. At the same time, various elements of the environmental model, such as terrain and vegetation, are integrated with the power facility model, allowing them to naturally connect in terms of spatial position and visual effect, forming an organic, integrated model—the environment-power facility fusion model.

[0082] Step S4: performing corona loss fluctuation detection on power facilities according to the environment-power facility fusion model to generate corona fluctuation loss data; performing environmental fluctuation factor analysis according to the dynamic environment evolution data to generate environmental fluctuation factor data; performing corona environment disturbance area detection on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate corona environment disturbance area data;

[0083] In an embodiment of the present invention, when detecting corona loss fluctuations in power facilities based on an environment-power facility fusion model, an electromagnetic simulation algorithm is used to combine the electrical parameters and environmental factors of the power facilities in the model. For example, considering that increased humidity can change air conductivity, thereby affecting the corona onset voltage, the electric field intensity distribution on the surface of the power facility under different environmental conditions is simulated and calculated. When the electric field intensity exceeds the air breakdown threshold, a corona phenomenon is determined to have occurred. The time, location, and intensity change of the corona onset are recorded to generate corona fluctuation loss data. Environmental fluctuation factor analysis is performed on dynamic environmental evolution data using multivariate statistical analysis methods such as principal component analysis (PCA). Dimensionality reduction is performed on multiple environmental variables such as temperature and humidity, wind speed and direction, and light intensity to extract the principal components that have the greatest impact on environmental fluctuations. For example, in specific areas, temperature and wind speed may be the main factors affecting environmental stability. These principal components are quantified as environmental fluctuation factor data. Based on the corona fluctuation data and the environmental impact fluctuation factor data, the environment-power facility fusion model is used to detect corona environmental disturbance areas, using a method that combines threshold determination and cluster analysis. The threshold range of corona loss and environmental factor fluctuation is set. When the detected data exceeds the threshold, the clustering algorithm is used to cluster these abnormal data points, determine the corona environment disturbance area, and generate corona environment disturbance area data.

[0084] Step S5: performing disturbance error calculation based on the corona environment disturbance area data to generate disturbance error data; performing corona environment disturbance reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstruction model of the environment-power facility.

[0085] In an embodiment of the present invention, a disturbance error is calculated based on the corona environment disturbance area data, and a root mean square error (RMSE) algorithm is used. The actual measurement data of the corona environment disturbance area is compared with the prediction data of the environment-power facility fusion model, and the square sum of the errors of each data point is calculated. Then, the average value is taken and the square root is taken to obtain the root mean square error value, which is used as the disturbance error data to measure the degree of deviation between the model prediction and the actual situation. When the environment-power facility fusion model is subjected to corona environment disturbance reconstruction processing based on the disturbance error data, a model correction algorithm is applied. For example, if the error is mainly concentrated in the corona loss prediction of a certain area, the cause of the error is analyzed. If the environmental factors of the area are not considered enough in the model, the environmental model parameters can be readjusted, such as increasing the weight of the influence of humidity on corona in the area. If the power facility model parameters are inaccurate, the electrical parameters can be recalibrated. By repeatedly adjusting the model parameters, the model prediction results are continuously approached to the actual measurement data, and finally a three-dimensional reconstruction model of the environment-power facility is generated, thereby improving the accuracy of the model in simulating the surrounding environment of the power facility and the corona phenomenon.

[0086] Furthermore, step S1 includes the following steps:

[0087] Step S11: acquiring power facility data, and performing power facility layout structure analysis based on the power facility data to generate power facility layout structure data;

[0088] Step S12: performing power facility spatial architecture analysis based on the power facility layout structure data to generate power facility spatial architecture data;

[0089] Step S13: performing power facility interaction node analysis on the power facility spatial architecture data to generate power facility interaction node data;

[0090] Step S14: constructing a three-dimensional model of the power facility based on the power facility interaction node data and the power facility spatial architecture data.

[0091] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0092] Step S11: acquiring power facility data, and performing power facility layout structure analysis based on the power facility data to generate power facility layout structure data;

[0093] In an embodiment of the present invention, multi-source data acquisition equipment is used to acquire power facility data. A three-dimensional laser scanner is used to perform on-site scanning of power facilities. This device emits a laser beam and measures the time difference between the laser's emission and its reflection from the power facility surface. Combined with the device's own position and angle information, it accurately calculates the three-dimensional coordinates of each sampling point on the power facility surface, generating point cloud data at a rate of thousands or even tens of thousands of points per second. Simultaneously, a total station is used to perform high-precision measurements of key power facility nodes, acquiring their precise plane coordinates and elevation data. This data is combined with the power facility's design drawings and as-built documentation to form a complete power facility data set. Based on the acquired data, topological analysis methods from graph theory are used to analyze the layout and structure of the power facilities. The various components of the power facilities, such as substations, transmission towers, transformers, and switchgear, are abstracted as nodes in a graph, and the transmission lines and cables connecting these nodes are abstracted as edges to construct a power facility topology map. By analyzing the connection relationship of nodes, the direction and length of edges in the topological graph, calculating indicators such as the degree centrality and betweenness centrality of nodes, we can sort out the spatial layout and connection logic between the various parts of the power facilities, and generate power facility layout structure data that records detailed node attributes, connection relationships, and line parameters.

[0094] Step S12: performing power facility spatial architecture analysis based on the power facility layout structure data to generate power facility spatial architecture data;

[0095] In an embodiment of the present invention, a spatial geometry analysis method is used to analyze the spatial architecture of power facilities. Using the Cartesian coordinate system as a reference, the nodes and edges in the layout structure data are mapped into three-dimensional space. For each power facility node, the precise position in three-dimensional space is determined based on its plane coordinates and elevation data. For the edges connecting the nodes, a connection path with a spatial curve shape is constructed in space according to the line direction and actual length. A spatial partitioning algorithm is used to divide the three-dimensional space where the power facilities are located into multiple subspace areas. For example, an octree partitioning method is used, with the circumscribed cube of the power facility area as the initial space, and the space is continuously divided into eight sub-cubes. Based on the distribution of the power facility components in space, the facility components contained in each subspace are determined until the preset accuracy requirements are met. In this way, the distribution range and mutual position relationship of the various components of the power facility in space are clearly defined, and power facility spatial architecture data containing spatial area division information, component spatial coordinate ranges, and spatial distances between components are generated.

[0096] Step S13: performing power facility interaction node analysis on the power facility spatial architecture data to generate power facility interaction node data;

[0097] In an embodiment of the present invention, a node analysis method is used to analyze interaction nodes within power facilities. First, key locations within the power facility where energy transmission, signal interaction, or physical connections occur are identified as potential interaction nodes, such as the connection points between transmission lines and towers, and the wiring terminals for electrical equipment within substations. The importance of interaction nodes is determined by calculating their connectivity and importance indicators. Connectivity refers to the number of edges connecting a node to other nodes. A higher connectivity indicates a more critical role for the node within the power facility network. Importance is assessed based on factors such as the node's location within the power transmission path and its impact on power system stability. Using a spatial distance algorithm, the actual spatial distance and shortest path between interaction nodes are calculated to analyze the interaction efficiency and potential interference between nodes. Information such as the interaction node type, location coordinates, connection relationship, importance indicator, and spatial distance is compiled to generate power facility interaction node data. For example, when analyzing the connection between a transmission line and a substation, the node's electrical connection method, specific location in space, and importance to the entire transmission network are clearly defined.

[0098] Step S14: constructing a three-dimensional model of the power facility based on the power facility interaction node data and the power facility spatial architecture data.

[0099] In an embodiment of the present invention, polygonal modeling technology is used to construct a three-dimensional model of a power facility. Based on interactive node data, key control points and connection points for each power facility component are determined. Based on the spatial position and morphology information of each component in the spatial architecture data, these control points are connected to construct polygonal mesh models of each power facility component. For transmission towers, the tower frame structure is constructed using a combination of quadrilateral and triangular polygons based on the shape and size of the tower in the spatial architecture data. For transmission lines, using interactive nodes as endpoints, a linear polygonal model with the actual catenary shape is fitted using a Bezier curve or spline curve algorithm, and the model is assigned diameter and material properties that meet actual specifications. The polygonal models of each component are assembled according to the positional relationships in the spatial architecture data. Texture mapping technology is used to map real-world texture images of the power facility materials onto the model surface, giving it a realistic appearance. Furthermore, connection constraints are set between components based on the interactive node data to ensure that the model can accurately simulate the physical interactions and energy transmission processes of the power facility in subsequent applications, ultimately generating a realistic and practical three-dimensional power facility model.

[0100] Furthermore, step S2 includes the following steps:

[0101] Step S21: acquiring power facility environmental data, and performing power facility environmental feature analysis based on the power facility environmental data to generate power facility environmental feature data;

[0102] Step S22: Calculating the environmental change cycle of the power facility environmental data based on the power facility environmental characteristic data to generate environmental change cycle data;

[0103] Step S23: performing a power facility environmental characteristic differentiation analysis based on the power facility environmental characteristic data and the environmental change cycle data to generate power facility environmental characteristic differentiation data;

[0104] Step S24: performing power facility environment change chain analysis based on the power facility environment feature differentiation data to generate power facility environment change chain data;

[0105] Step S25: performing dynamic environmental evolution based on the environmental change cycle data and the power facility environmental change chain data to generate dynamic environmental evolution data;

[0106] Step S26: constructing a power facility environment dynamic evolution model based on the dynamic environment evolution data.

[0107] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment, step S2 includes the following steps:

[0108] Step S21: acquiring power facility environmental data, and performing power facility environmental feature analysis based on the power facility environmental data to generate power facility environmental feature data;

[0109] In an embodiment of the present invention, environmental data of power facilities is obtained through a multi-type sensor network deployed around the power facilities. In terms of meteorological monitoring, an ultrasonic anemometer is used to accurately calculate real-time wind speed and direction by measuring the time difference between ultrasonic waves propagating in different directions in the air. A capacitive temperature and humidity sensor is used to obtain temperature and humidity data based on the characteristics of the capacitance value changing with ambient humidity and temperature. An ultraviolet lightning detector is deployed to record the time, intensity, and direction of lightning by detecting the ultraviolet radiation generated by lightning. In terms of geographical environmental monitoring, satellite remote sensing imagery and ground-based lidar scanning are used to obtain data such as topography and vegetation cover. The data collected by these sensors at intervals of one minute and the remote sensing image data updated every hour are integrated to form an original environmental data set. The original environmental data set is subjected to environmental feature analysis using a feature extraction algorithm. For meteorological data, statistical features such as the daily maximum and minimum temperature values ​​and the peak and valley values ​​of wind speed are extracted. For remote sensing images, an edge detection algorithm is used to identify terrain boundaries, and vegetation cover is extracted using a vegetation index calculation method (such as the Normalized Difference Vegetation Index (NDVI)). The various environmental features extracted, such as meteorological statistical parameters, terrain boundary coordinates, vegetation coverage areas, etc., are structured according to the preset data format to generate power facility environmental feature data containing environmental feature types, feature values ​​and spatial location information.

[0110] Step S22: Calculating the environmental change cycle of the power facility environmental data based on the power facility environmental characteristic data to generate environmental change cycle data;

[0111] In an embodiment of the present invention, the Fourier transform algorithm in time series analysis is used to calculate the environmental change cycle. Taking temperature data as an example, the hourly temperature values ​​for one consecutive year are composed into a time series, and the temperature change data in the time domain is converted to the frequency domain through Fourier transform to decompose the periodic components of different frequencies. The frequency domain spectrum is analyzed to identify the dominant periodic frequencies, such as the frequency peaks corresponding to 24 hours (daily cycle) and 365 days (annual cycle), and the specific duration and phase offset of these cycles are calculated. For wind speed and direction data, Fourier transform is also used to analyze its periodic characteristics so as to find seasonal wind direction periodic changes in certain areas. The information such as the cycle duration, cycle start time and change amplitude of each environmental feature is summarized to generate environmental change cycle data containing the change cycle parameters corresponding to different environmental features.

[0112] Step S23: performing a power facility environmental characteristic differentiation analysis based on the power facility environmental characteristic data and the environmental change cycle data to generate power facility environmental characteristic differentiation data;

[0113] In an embodiment of the present invention, a comparative analysis algorithm is used to perform differential analysis of environmental characteristics based on the environmental characteristic data of power facilities and the environmental change cycle data. The data of the same environmental characteristics in different cycle stages are compared. For example, the temperature data of summer (June-August) and winter (December-February) are segmented and compared according to the daily change cycle. Statistics such as the mean and standard deviation of the environmental characteristics in each cycle stage are calculated, and the numerical differences of the same environmental characteristics of power facilities in different geographical locations are compared. For example, the wind speed data around mountain substations and urban substations are compared to analyze the impact of terrain factors on wind speed. The difference values ​​of environmental characteristics in different cycles and different locations, as well as the difference types (such as numerical differences, change trend differences) and other information are recorded to generate differentiated data on environmental characteristics of power facilities.

[0114] Step S24: performing power facility environment change chain analysis based on the power facility environment feature differentiation data to generate power facility environment change chain data;

[0115] In an embodiment of the present invention, an association rule mining algorithm is used to analyze environmental change chains based on differentiated data on power facility environmental characteristics. Taking meteorological environmental characteristics as an example, the correlation between rising temperature, decreasing humidity, and changing wind speed is analyzed. By setting support and confidence thresholds, strongly correlated environmental change rules are mined. For example, when the temperature exceeds 30°C for three consecutive days, there is a certain probability that the relative humidity will drop by 15% and the wind speed may increase by 2 m / s. These association rules are then connected in series according to causal relationships and chronological order to construct an environmental change chain. For example, spring temperatures warm up (initial event) → vegetation begins to grow (intermediate event) → air humidity increases due to transpiration (subsequent event) → condensation may occur on the surface of power facilities (outcome event). Information such as event type, triggering conditions, occurrence sequence, and association probability in the environmental change chain is organized to generate power facility environmental change chain data containing a complete causal chain of environmental changes.

[0116] Step S25: performing dynamic environmental evolution based on the environmental change cycle data and the power facility environmental change chain data to generate dynamic environmental evolution data;

[0117] In an embodiment of the present invention, a discrete event simulation algorithm is used to simulate dynamic environmental evolution based on environmental change cycle data and power facility environmental change chain data. The simulation cycle is one year, and iterative calculations are performed in minute time steps. At each time step, the environmental characteristic values ​​at the current moment are updated based on the environmental change cycle data. For example, based on the daily temperature variation cycle, the temperature is set to the daily minimum at 6:00 a.m., and the temperature data is gradually updated at a preset heating rate. Simultaneously, based on the environmental change chain data, it is determined whether event triggering conditions are met. If the starting event of a particular environmental change chain is detected, subsequent events are triggered in sequence according to the chain, and the corresponding environmental characteristic data is updated. For example, if the temperature exceeds 30°C for three consecutive days, a humidity decrease and wind speed increase event is triggered, and the humidity and wind speed data are adjusted according to the associated probability and change amplitude. The environmental characteristic data for each time step is recorded to generate environmental parameter change data containing a complete time series, namely dynamic environmental evolution data.

[0118] Step S26: constructing a power facility environment dynamic evolution model based on the dynamic environment evolution data.

[0119] In an embodiment of the present invention, a dynamic evolution model of the power facility environment is constructed based on dynamic environmental evolution data using a physical engine combined with particle system technology. For wind field simulation in a meteorological environment, the Navier-Stokes equation in fluid mechanics is used, combined with wind speed and direction information in the dynamic environmental evolution data, to calculate the velocity field and pressure field of air flow in three-dimensional space, and drive the particle system to simulate the motion trajectory of particles such as dust, clouds, etc. carried by the wind. In response to the dynamic changes in vegetation, the parameters of the vegetation growth model are set according to the relationship between vegetation growth and environmental factors in the environmental change chain. The L-system algorithm is used to simulate the branch growth and leaf germination process of vegetation in a time series. The simulated meteorological environment and dynamic elements such as vegetation changes are integrated with the three-dimensional model of the power facility. Through texture mapping and animation rendering technology, the dynamic changes of environmental elements are intuitively presented in the model, and finally a dynamic evolution model of the power facility environment is constructed that can truly reflect the evolution of the environment around the power facility over time.

[0120] Furthermore, step S3 includes the following steps:

[0121] Step S31: Analyze meteorological impact factors based on the dynamic evolution model of the power facility environment to generate meteorological impact factor data;

[0122] In an embodiment of the present invention, a multivariate linear regression analysis method is used to analyze meteorological influencing factors using meteorological data recorded in a dynamic evolution model of the power facility environment. Meteorological parameters such as temperature, humidity, wind speed, and rainfall are extracted from the model data, and power facility operating indicators such as transmission line corona loss and insulator flashover probability are used as dependent variables. For example, when analyzing the impact of temperature on transmission line resistance, daily temperature data and transmission line resistance measurements for the corresponding time period over the past three years are collected. A linear regression model is constructed using temperature as the independent variable and resistance as the dependent variable. By calculating the regression coefficient, the impact of each meteorological factor on the power facility operating indicator is quantified. For the relationship between wind speed and transmission line vibration amplitude, a quantitative relationship is obtained through regression analysis: for every 1 m / s increase in wind speed, the line vibration amplitude increases by an average of 0.5 mm. Information such as the impact coefficient and impact direction (positive or negative impact) of each meteorological factor on different power facility operating indicators is compiled to generate meteorological influencing factor data containing the meteorological factor name, impact indicator, and response coefficient.

[0123] Step S32: performing a structural deformation mapping correlation process on the power facility according to the meteorological impact factor data to generate meteorological-deformation correlation factor data;

[0124] In one embodiment of the present invention, finite element analysis is used to map and correlate deformations of power facility structures. Taking a transmission tower as an example, a three-dimensional finite element model of the tower is constructed, and mechanical properties of the tower material, such as the elastic modulus and Poisson's ratio, are input into the model. Based on the magnitude and direction of the forces acting on the tower at different wind speeds as reported by meteorological impact factor data, corresponding wind loads are applied to the finite element model. Finite element calculations are used to simulate the stress distribution and deformation of the tower under different wind speeds. For example, at a wind speed of 10 m / s, the maximum displacement at the top of the tower is calculated to be 5 cm, with stress concentration areas at different locations. A mapping relationship is established between meteorological factors (such as wind speed and temperature changes) and deformation parameters (such as displacement, strain, and stress) of the power facility structure. The deformation values ​​of the corresponding structural parts of the power facility are recorded for each change in meteorological factor. For example, when the temperature drops by 10°C, the transmission line shrinks in length due to thermal expansion and contraction. The correlation between these meteorological factors and structural deformation, along with the quantified data, is compiled into meteorological-deformation correlation factor data.

[0125] Step S33: Rendering the three-dimensional model of the power facility based on the weather-deformation correlation factor data to generate a rendered three-dimensional model of the power facility;

[0126] In this embodiment of the present invention, physically based rendering (PBR) technology and a deformation animation algorithm are used to render a three-dimensional model of a power facility. During the rendering process, PBR technology is first used to calculate the reflection, refraction, and shadow effects of light on the power facility's surface based on lighting conditions such as the solar altitude and atmospheric scattering coefficient, as determined by meteorological influencing factor data. For example, under direct midday sunlight, the metal surface of a power facility produces strong specular reflections, and PBR accurately simulates this optical phenomenon. Combined with meteorological-deformation correlation factor data, the power facility model is dynamically deformed and rendered. When a wind speed of 8 m / s is detected, the deformation animation algorithm adjusts the three-dimensional vertices of the tower model according to the calculated displacements based on the tower's deformation parameters in the correlation data, creating a curved deformation effect caused by the wind. Simultaneously, the deformed model is given corresponding material changes, such as the appearance of fine cracks on the metal surface caused by deformation. Texture mapping and light and shadow rendering are then performed on the processed three-dimensional power facility model to generate a rendered three-dimensional model of the power facility that reflects the changes in appearance and morphology under the influence of meteorological factors.

[0127] Step S34: performing model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model.

[0128] In an embodiment of the present invention, spatial coordinate transformation and Boolean operations are used to perform model alignment and embedding based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment. Using the geodetic coordinate system of the Geographic Information System (GIS) as a reference, the coordinate system of the rendered three-dimensional model of the power facility is uniformly transformed with the coordinate system of the dynamic evolution model of the power facility environment. By measuring the positions of landmark points in the model (such as the center point of the substation and the base coordinates of the transmission tower) in real geographic space, the model is precisely placed at the corresponding geographic location in the environment model. Boolean operations are used to process overlaps between terrain, vegetation, and other elements in the environment model and the power facility model. For example, when a transmission line in the power facility model passes through a tree area in the environment model, a Boolean difference operation is used to remove the overlap between the trees and the line, ensuring the accuracy of the spatial relationship between the models. Simultaneously, meteorological elements in the dynamic evolution model, such as drifting clouds and flowing wind fields, are integrated with the rendered three-dimensional model of the power facility, allowing the power facility to present a natural interactive effect within the dynamic environment, ultimately generating a complete environment-power facility fusion model.

[0129] Furthermore, step S4 includes the following steps:

[0130] Step S41: performing power facility magnetic field wave frequency analysis based on the environment-power facility fusion model to generate power facility magnetic field wave frequency data;

[0131] In an embodiment of the present invention, a numerical calculation method based on Maxwell's equations is used to analyze the magnetic field frequency of power facilities within an environment-power facility fusion model. Within this fusion model, electrical parameters of the power facility are extracted, such as the current intensity, voltage level, and conductor spacing of the transmission lines, as well as data such as the number of winding turns and core material of the transformer within the substation. Based on finite element analysis (FEM), the space surrounding the power facility is divided into multiple tiny tetrahedral units. Within each unit, Ampere's circuit law and Faraday's law of electromagnetic induction in Maxwell's equations are solved. For an operating three-phase transmission line, the magnetic field intensity generated by each conductor at each point in space is calculated using the Biot-Savart law. The magnetic fields generated by each phase are vector-superimposed to produce a composite magnetic field. Using a fast Fourier transform (FFT), the time-domain magnetic field intensity signal is converted to the frequency domain. The magnetic field intensity distribution of different frequency components is analyzed to obtain the frequency characteristics of the magnetic field generated by the power facility during operation. This generates power facility magnetic field frequency data containing information such as the magnetic field frequency, corresponding amplitude, and spatial distribution coordinates.

[0132] Step S42: performing corona loss fluctuation detection based on the magnetic field wave frequency data of the power facility to generate corona fluctuation loss data;

[0133] In the embodiment of the present invention, the formula of Pick's law is: Where P is the corona loss power per unit length of wire (W / m), f is the current frequency (Hz), and δ is the relative density of air ( p is the atmospheric pressure in kPa, t is the ambient temperature in ℃), E is the electric field strength on the surface of the conductor (kV / cm), E0 is the corona starting electric field strength (kV / cm), and r is the radius of the conductor (cm). The current frequency f is obtained from the magnetic field wave frequency data of the power facility, and the atmospheric pressure p and the ambient temperature t are obtained through the meteorological influencing factor data in step S31, and then the relative density of air δ is calculated. The electric field strength E on the surface of the conductor is calculated by finite element analysis, and the corona starting electric field strength E0 is determined according to the material and surface condition of the conductor. The radius of the conductor r is known. Substitute each parameter into the formula of Pick's law to calculate the corona loss power P per unit length of the conductor. Repeat the above calculation process at different time points, and compare the corona loss power difference ΔP=P at adjacent time points. t+1 ―P t When |ΔP| exceeds the set threshold, it is determined that the corona loss has fluctuated, and the information such as the fluctuation time, position, and corona loss power before and after the fluctuation is recorded to generate corona fluctuation loss data.

[0134] Step S43: performing environmental fluctuation factor analysis based on the dynamic environmental evolution data to generate environmental fluctuation factor data;

[0135] In an embodiment of the present invention, principal component analysis (PCA) is used to analyze environmental fluctuation factors in dynamic environmental evolution data. The dynamic environmental evolution data includes time series data of multi-dimensional environmental parameters such as temperature, humidity, wind speed, rainfall, and atmospheric pressure. First, this data is standardized, converting the values ​​of each parameter into standard normal distribution data with a mean of 0 and a standard deviation of 1. The covariance matrix between each environmental parameter is calculated, and the covariance matrix is ​​decomposed by eigenvalues ​​to obtain eigenvalues ​​and eigenvectors. The eigenvalues ​​are arranged in descending order, and the first few eigenvectors with a cumulative contribution rate exceeding a certain percentage are selected as principal components. For example, if the combination of temperature, wind speed, and humidity is calculated to explain environmental fluctuations, these three parameters are identified as the main environmental fluctuation factors. The scores of each principal component factor at different time points and the weights of each original environmental parameter in the principal component are calculated to generate environmental fluctuation factor data containing information such as the environmental fluctuation factor name, weight coefficient, and time series score.

[0136] Step S44: performing corona environmental disturbance area detection on the environment-power facility fusion model based on the corona fluctuation loss data and the environmental fluctuation factor data to generate corona environmental disturbance area data.

[0137] In an embodiment of the present invention, a cluster analysis algorithm is used to detect the corona environmental disturbance area of ​​the environment-power facility fusion model based on the corona fluctuation loss data and the environmental fluctuation factor data. The DBSCAN (density-based spatial clustering application) algorithm is used to take the change in corona loss power in the corona fluctuation loss data and the change in the main environmental parameters in the environmental fluctuation factor data as sample features. All sample points are traversed, and the sample points with accessible density are clustered to form different clusters. When the power facilities corresponding to the sample points in a cluster are relatively concentrated in the spatial position in the fusion model, the area is determined to be a corona environmental disturbance area. The spatial coordinate range of each disturbance area, the power facility components included, the main environmental influencing factors and their changes, the degree of corona loss fluctuation and other information are recorded to generate corona environmental disturbance area data.

[0138] Furthermore, step S42 includes the following steps:

[0139] Step S421: performing magnetic field wave-frequency interaction analysis based on the magnetic field wave-frequency data of the power facility to generate wave-frequency interaction data;

[0140] In the embodiment of the present invention, a cross-correlation function calculation method is used to perform magnetic field wave-frequency interaction analysis on the magnetic field wave-frequency data of the power facility, and magnetic field strength signals of different frequency components are extracted from the magnetic field wave-frequency data of the power facility. The magnetic field strength signals of two different frequencies f1 and f2 are assumed to be x(t) and y(t), respectively. The cross-correlation function calculation formula is: Where τ is the time delay. During the calculation process, in order to ensure the accuracy of the analysis results, the time window length and time delay range need to be reasonably selected. The time window length should cover enough signal cycles to reflect the signal characteristics, and the time delay range needs to be set according to the signal characteristics to avoid missing important interaction information. Taking the magnetic field signals generated by two different busbars in a substation as an example, the collected magnetic field strength signals of f1 = 50 Hz and f2 = 100 Hz are divided according to the time series, and the time window length is taken as T. In each time window, the cross-correlation value R under different time delays τ is calculated by the above formula. xy (τ), when R xy When a peak in (τ) occurs, it indicates a strong interaction between the magnetic field signals of the two frequency components. The time delay τ corresponding to the peak, the frequency combination (f1, f2), and the magnitude of the cross-correlation value are recorded. Calculations are performed for all frequency components pairwise, and frequency combinations with significant interaction and related parameters are compiled into wave-frequency interaction data.

[0141] Step S422: performing resonance mapping spectrum processing on the power facility magnetic field wave frequency data based on the wave frequency interaction data to generate resonance mapping spectrum data;

[0142] In the embodiment of the present invention, based on the wave frequency interaction data, matrix transformation and visual mapping technology are used to perform resonance mapping spectrum processing. A matrix with magnetic field frequency as rows and columns is constructed, and the matrix elements correspond to the cross-correlation values ​​of different frequency combinations. The matrix elements correspond to the cross-correlation values ​​of different frequency combinations. If the frequency f i With f j The cross-correlation value is R ij , then fill in R in the i-th row and j-th column of the matrix ij . Normalize the matrix and map the element values ​​to the [0,1] interval. The formula is: where R min and R max are the minimum and maximum values ​​in the matrix, respectively. Using a graphics drawing tool, the normalized matrix is ​​converted into a two-dimensional spectrum. The horizontal and vertical axes represent different magnetic field frequencies, respectively. The color depth or grayscale of each point in the spectrum corresponds to the normalized cross-correlation value. The darker the color, the stronger the interaction between the two frequency components, that is, the more likely resonance will occur. Mark the frequency combinations corresponding to the darker areas in the spectrum to generate resonance mapping spectrum data containing frequency coordinates, cross-correlation values, and spectrum image information.

[0143] Step S423: performing electromagnetic medium jump response spectrum analysis according to the resonance mapping spectrum data to generate electromagnetic medium jump response spectrum data;

[0144] In the embodiment of the present invention, the electromagnetic medium response theory is used to analyze the electromagnetic medium jump response spectrum. The frequency combination (f m ,f n ), the dielectric constant of the electromagnetic medium around the power facilities is ε, the magnetic permeability is μ, and the electrical conductivity is σ. Under sinusoidal excitation, the complex dielectric constant of the electromagnetic medium is Where f is the excitation frequency. According to Maxwell's equations, the electric field strength in the medium is and magnetic field strength Satisfies the wave equation: Solving the wave equation, we can get the relationship between the electric field strength in the medium and the frequency, E(f). When the frequency changes around the resonant frequency, we can calculate the rate of change of the electric field strength. If at a certain frequency point f0, If the absolute value of suddenly increases and exceeds the set threshold, the frequency point is determined to be a sudden response point of the electromagnetic medium. The frequency, electric field intensity change rate, and medium parameters of the sudden response point are recorded to generate electromagnetic medium sudden response spectrum data containing frequency, response intensity, and medium parameters.

[0145] Step S424: performing corona loss fluctuation detection on the power facility magnetic field wave frequency data based on the electromagnetic medium jump response spectrum data to generate corona fluctuation loss data.

[0146] In the embodiment of the present invention, corona loss fluctuation detection is performed based on the electromagnetic medium jump response spectrum data and combined with Pick's law. The Pick's law formula is: Where P is the corona loss power per unit length of wire (W / m), f is the current frequency (Hz), and δ is the relative density of air ( p is the atmospheric pressure in kPa, t is the ambient temperature in °C), E is the electric field strength on the surface of the conductor (kV / cm), E0 is the corona starting electric field strength (kV / cm), and r is the conductor radius (cm). The frequency of the jump response point is obtained from the electromagnetic medium jump response spectrum data, and the atmospheric pressure p and ambient temperature t are obtained in combination with the meteorological influence factor data in step S31, and then the relative density of air δ is calculated. The electric field strength E on the surface of the conductor is calculated by finite element analysis, and the corona starting electric field strength E0 is determined according to the conductor material and surface condition. The conductor radius r is known. Substitute each parameter into the Pick's law formula to calculate the corona loss power P per unit length of the conductor. Repeat the above calculation process at different time points, and compare the corona loss power difference ΔP=P at adjacent time points. t+1 ―P t When |ΔP| exceeds the set threshold, it is determined that the corona loss has fluctuated, and the information such as the fluctuation time, position, and corona loss power before and after the fluctuation is recorded to generate corona fluctuation loss data.

[0147] Furthermore, step S424 includes the following steps:

[0148] Conduct corona disturbance hierarchy analysis based on electromagnetic medium jump response spectrum data to generate corona disturbance hierarchy data;

[0149] In an embodiment of the present invention, the analytic hierarchy process (AHP) is used to perform corona disturbance hierarchy analysis on electromagnetic medium jump response spectrum data. Information such as the frequency, electric field intensity change rate, and dielectric parameters of the jump response point are extracted from the electromagnetic medium jump response spectrum data. A three-layer hierarchical model is constructed: the target layer is the corona disturbance degree, the criterion layer includes factors such as frequency influence, electric field intensity change influence, and dielectric parameter influence, and the solution layer corresponds to different jump response points. Weights are set for each criterion layer factor, and pairwise comparisons are performed using a 1-9 scaling method. For example, the frequency influence and the electric field intensity change influence are compared in importance. If the frequency influence is considered slightly more important, a value of 3 is assigned to construct a judgment matrix. The weights are then checked for consistency by calculating the maximum eigenvalue and eigenvector of the judgment matrix to ensure the rationality of the weight setting. For each jump response point, its index value under each criterion layer factor is standardized and then multiplied by the corresponding weight and summed to obtain the corona disturbance degree score for that point. The sudden response points are divided into different classes according to the scores, for example, high disturbance class (score ≥ 80), medium disturbance class (60 ≤ score < 80), and low disturbance class (score < 60). The sudden response point information, score, division basis, etc. contained in each class are recorded to generate corona disturbance class data.

[0150] Preferably, corona medium ionization shower mapping processing is performed according to the corona disturbance hierarchy data to generate corona medium ionization shower data;

[0151] In the embodiment of the present invention, a spatial mapping algorithm is used to map the ionization shower of the corona medium based on the corona disturbance layer data. The space around the power facility is divided into three-dimensional grids, and the side length of each grid is set to 0.1 meters. For the sudden response point of the high disturbance layer, the probability of ionization of the corona medium in the grid around the point is calculated based on the corresponding frequency and electric field intensity change rate using gas discharge theory. The ionization probability calculation formula is P ionization =α·E·ΔV, where α is the ionization coefficient (dependent on gas type, temperature, and pressure), E is the electric field strength at that point, and ΔV is the grid volume. For each grid, the ionization probabilities generated by all the sudden-response points within it are summed. When the total ionization probability exceeds a set threshold, the grid is identified as a corona medium ionization shower region. The spatial coordinate range, sudden-response point information, and ionization probability of each ionization shower region are recorded to generate corona medium ionization shower data.

[0152] Preferably, the corona medium oscillation coefficient is calculated based on the corona medium ionizing shower data to generate the corona medium oscillation coefficient;

[0153] In the embodiment of the present invention, the oscillation coefficient of the corona medium is calculated using the oscillation amplitude calculation method. For each corona medium ion shower area, the electric field intensity data of 100 time points are continuously collected at an interval of 1 second to form a time series E(t). The standard deviation of the time series is calculated as Where n = 100, E i is the electric field strength at the i-th time point is the average value of the electric field intensity. Define the oscillation coefficient of the corona medium This coefficient reflects the degree of oscillation of the electric field intensity within the ionizing shower region. The above calculation is performed for each ionizing shower region, and the oscillation coefficient value, corresponding spatial coordinates, and acquisition time of each region are recorded to generate corona medium oscillation coefficient data containing the oscillation coefficients of multiple ionizing shower regions.

[0154] Preferably, corona stratum ionization attenuation analysis is performed on the corona disturbance stratum data based on the corona medium oscillation coefficient to generate corona stratum ionization attenuation data;

[0155] In the embodiment of the present invention, based on the corona medium oscillation coefficient, the corona disturbance layer data is analyzed by using an attenuation model to analyze the corona layer ionization attenuation. The ionization attenuation model A=A0·e is established. ―β·K , where A is the degree of ionization after considering the oscillation coefficient, A0 is the initial ionization degree (i.e., the disturbance degree score in the corona disturbance hierarchy analysis), β is the attenuation coefficient (determined by regression analysis of historical corona loss data and oscillation coefficient), and K is the corona medium oscillation coefficient. For each sudden response point in the corona disturbance hierarchy, the oscillation coefficient of the ionized shower region in which it is located is substituted into the above formula to calculate the degree of ionization after considering attenuation. Compare the initial disturbance degree score and the degree of ionization after attenuation to calculate the ionization attenuation rate. The initial score, degree of ionization after decay, ionization decay rate and other information of each jump response point are recorded to generate corona stratum ionization decay data.

[0156] Preferably, corona loss fluctuation detection is performed on the power facility magnetic field wave frequency data based on the corona stratification ion attenuation data to generate corona fluctuation loss data.

[0157] In the embodiment of the present invention, the corona loss fluctuation detection is performed based on the corona stratification attenuation data and combined with the Pick's law. The Pick's law formula is: Where P is the corona loss power per unit length of wire (W / m), f is the current frequency (Hz), and δ is the relative density of air ( p is the atmospheric pressure in kPa, t is the ambient temperature in °C), E is the electric field strength on the conductor surface (kV / cm), E0 is the electric field strength at the start of the corona (kV / cm), and r is the radius of the conductor in cm. The frequency f of the sudden response point and the degree of ionization after attenuation are obtained from the corona stratification attenuation data. The electric field strength E on the conductor surface is corrected according to the degree of ionization (for example, the higher the degree of ionization, the greater the effective electric field strength. The correction formula is: E original =The original electric field strength). The atmospheric pressure p and ambient temperature t are obtained from the meteorological influence factor data in step S31, and then the relative air density δ is calculated. The electric field strength E on the surface of the conductor is calculated using finite element analysis, and the corona starting electric field strength E0 is determined based on the conductor material and surface condition. The conductor radius r is known. Substitute each parameter into the Pick's law formula to calculate the corona loss power P per unit length of conductor. Repeat the above calculation process at different time points and compare the corona loss power difference ΔP=P at adjacent time points. t+1 ―P t When |ΔP| exceeds the set threshold, it is determined that the corona loss has fluctuated, and the information such as the fluctuation time, position, and corona loss power before and after the fluctuation is recorded to generate corona fluctuation loss data.

[0158] Furthermore, step S44 includes the following steps:

[0159] Step S441: performing corona wave frequency analysis based on the corona wave loss data to generate corona wave frequency data;

[0160] In an embodiment of the present invention, a fast Fourier transform (FFT) algorithm is used to perform corona wave frequency analysis on the corona fluctuation loss data. The corona fluctuation loss data records the corona loss power of the unit length power facility at different times in the form of a time series, such as collecting data every 10 minutes to form a sequence containing power loss values ​​at multiple time points. The time series data is input into the FFT algorithm. The corona loss power data in the time domain is converted to the frequency domain to obtain the power amplitude corresponding to different frequency components. The frequency domain data is analyzed, the main frequency components and their corresponding amplitudes are extracted, and corona wave frequency data containing information such as frequency value, amplitude size, and frequency ratio is generated.

[0161] Step S442: performing corona wave frequency resonance processing on the corona wave frequency data based on the environmental fluctuation factor data to generate corona wave frequency resonance data;

[0162] In an embodiment of the present invention, a frequency matching and superposition algorithm is used to perform corona frequency resonance processing on corona wave frequency data based on environmental fluctuation factor data. The environmental fluctuation factor data includes the changing parameters of environmental factors such as temperature, humidity, and wind speed. First, the natural frequency of each environmental factor is analyzed. The frequency components in the corona wave frequency data are compared with the natural frequencies of the environmental fluctuation factors one by one. When the difference between a frequency in the corona wave frequency and the natural frequency of the environmental factor is less than a set threshold, it is determined that the two may resonate. For frequency components with potential resonance, their amplitudes are adjusted based on the intensity of the environmental factor change. For example, if the environmental factor intensity coefficient is m (derived through historical data regression analysis, for example, for every 1 m / s increase in wind speed, the intensity coefficient m increases by 0.1), the original amplitude of the corresponding frequency in the corona wave frequency is A0, and the adjusted amplitude is A0, where A=A0×(1+m). The adjusted frequency components and their amplitudes are rearranged to generate corona wave frequency resonance data containing information such as the resonant frequency, the adjusted amplitude, and the associated environmental factors.

[0163] Step S443: performing corona amplitude deviation analysis based on the corona wave frequency resonance data to generate corona amplitude deviation data;

[0164] In an embodiment of the present invention, a standard deviation calculation method is used to perform corona amplitude deviation analysis. For each frequency component in the corona wave frequency resonance data, its amplitude data over multiple consecutive time periods are collected to form an amplitude sequence. The standard deviation of the amplitude sequence is calculated using the formula: Where n is the number of points in the amplitude sequence, A i is the amplitude at the i-th time point, is the average value of the amplitude sequence. The standard deviation reflects the degree of fluctuation in the amplitude of the frequency component, that is, the amplitude deviation. The frequency value, standard deviation, and average amplitude of each frequency component are recorded to generate corona amplitude deviation data.

[0165] Step S444: performing smoothness disturbance calculation on the corona wave frequency data according to the corona amplitude deviation data to generate smoothness disturbance data;

[0166] In the embodiment of the present invention, the slope change calculation method of adjacent points is used to perform smoothness perturbation calculation on the corona wave frequency data. For each frequency component in the corona wave frequency data, the data points whose amplitude changes with time are sequentially connected, and the slope between adjacent data points is calculated. Among them A i and A i+1 are adjacent time points t i and t i+1 Analyze the difference Δk between adjacent slopes i =k i+1 ―k i, the sum of the absolute values ​​of all adjacent slope differences is taken as the smoothness perturbation value of the frequency component The larger the smoothness disturbance value, the more unstable the amplitude change of the frequency component. The smoothness disturbance value of all frequency components in the corona wave frequency data is calculated to generate smoothness disturbance data containing information such as frequency and smoothness disturbance value.

[0167] Step S445: performing corona environment disturbance area detection on the environment-power facility fusion model based on the smoothness disturbance data to generate corona environment disturbance area data.

[0168] In an embodiment of the present invention, based on the smoothness disturbance data, a spatial clustering algorithm is used to detect the corona environment disturbance area of ​​the environment-power facility fusion model. The smoothness disturbance data is associated with the spatial position information of the power facility in the fusion model, and each power facility component corresponds to a set of smoothness disturbance values ​​(smoothness disturbance values ​​containing multiple frequency components). The DBSCAN (density-based spatial clustering application) algorithm is used, with the coordinates of the power facility components in space as sample points and the smoothness disturbance values ​​corresponding to the components as features, to traverse all sample points. When the number of sample points of a certain sample point within the radius neighborhood reaches or exceeds the minimum number of sample points, these sample points are divided into a cluster, and the spatial area corresponding to the cluster is the corona environment disturbance area. The spatial coordinate range of each disturbance area, the power facility components contained, and the average smoothness disturbance value and other information are recorded to generate corona environment disturbance area data.

[0169] Furthermore, step S5 includes the following steps:

[0170] Step S51: performing disturbance dislocation superposition depth analysis on the corona environment disturbance area data to generate disturbance dislocation superposition depth data;

[0171] In an embodiment of the present invention, spatial geometric overlay and hierarchical analysis methods are used to perform a depth analysis of corona environmental disturbance area data. The corona environmental disturbance area data includes information such as the spatial coordinate ranges of multiple disturbance areas and the power facility components involved. Each disturbance area is abstracted as a three-dimensional geometric shape, such as a cuboid or irregular polyhedron, and its specific position and size in the Cartesian coordinate system are determined based on its coordinate range. For multiple disturbance areas, the spatial overlap between them is calculated. Three-dimensional Boolean operations, such as intersection, are used to determine the geometric shapes where different disturbance areas overlap. Overlapping areas are hierarchically divided according to the degree of disturbance. For example, the portion with the highest degree of disturbance within the overlapping area is assigned the first layer, and the layers are then divided downwards. Each layer is assigned a corresponding depth value, which is positively correlated with the degree of disturbance. For example, two disturbance areas around a substation: one caused by high humidity, resulting in abnormal insulator corona, and the other caused by strong wind-induced transmission line vibration, exacerbating corona losses. Spatial geometric operations are used to determine the overlapping area between the two areas, and then quantitative indicators of the degree of humidity and wind speed impact are used. For example, the overlapping area can be divided into three layers: the innermost layer (depth value 3) corresponds to the area with strong influence from both humidity and wind speed, the middle layer (depth value 2) corresponds to the area with strong influence from a single factor, and the outer layer (depth value 1) corresponds to the area with weak influence. The layer division, depth value, and disturbance factors involved in each overlapping area are recorded to generate disturbance dislocation stacking depth data.

[0172] Step S52: performing disturbance error calculation based on the disturbance misalignment superposition depth data to generate disturbance error data;

[0173] In an embodiment of the present invention, the disturbance error is calculated using the root mean square error (RMSE) combined with the relative error calculation method. First, for each disturbance area, the disturbance range, degree and other data predicted by the model are compared with the actual detected data. The actual data can be determined by information such as corona loss and electric field strength collected by on-site sensors, while the model prediction data comes from the environment-power facility fusion model. The root mean square error calculation formula is: Where n is the number of data points, is the i-th actual detection data, The predicted data for the i-th model is calculated. The root mean square error of each disturbance region is calculated to measure the numerical deviation between the model prediction value and the actual value. At the same time, the relative error is calculated as follows: The error is expressed as a percentage relative to the actual value. For disturbance areas with superimposed dislocations, the depth values ​​of different layers are comprehensively considered and the errors of each layer are weighted. The higher the depth value, the greater the weight.

[0174] Step S53: performing three-dimensional reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstructed model of the environment-power facility.

[0175] In an embodiment of the present invention, a 3D reconstruction of the integrated environment-power facility model is performed using mesh deformation and parameter correction techniques based on disturbance error data. For areas with large disturbance errors, the corresponding power facility components and environmental scene sections are located in the 3D model. The model surface is divided into a fine triangular mesh, and the coordinates of the mesh vertices are adjusted to achieve deformation of the model shape. Targeted adjustments are made to the model based on the direction and magnitude of the deviation reflected in the disturbance error data. For example, if the error indicates that the actual corona loss of a certain transmission line section is higher than the model prediction, and the deviation is primarily reflected in the electric field intensity distribution on the line surface, finite element analysis is used to recalculate the electric field distribution under actual operating conditions for the line. Based on the calculated results, the mesh vertices on the line model surface are adjusted to better reflect the corona loss caused by the actual electric field distribution. For the environmental model, such as disturbance errors caused by wind speed, the wind speed field distribution parameters in the model are adjusted to re-simulate the effects of wind on the power facility. Simultaneously, parameters related to corona loss in the model, such as conductor surface roughness and the dielectric constant of the insulator material, are updated to more accurately reflect actual conditions. The entire model is optimized for texture mapping and light and shadow rendering to ensure that the appearance and physical properties of the model can accurately reflect the actual corona environmental disturbance, and finally generate a three-dimensional reconstruction model of the environment and power facilities.

[0176] Furthermore, the present invention also provides a three-dimensional reconstruction system for the surrounding environment of an electric power facility, which is used to execute the above-mentioned three-dimensional reconstruction method for the surrounding environment of an electric power facility. The three-dimensional reconstruction system for the surrounding environment of an electric power facility includes:

[0177] The power facility 3D construction module is used to obtain power facility data, perform power facility spatial layout structure analysis based on the power facility data, generate power facility spatial layout structure data; and construct a power facility 3D model based on the power facility spatial layout structure data.

[0178] A dynamic evolution model building module is used to obtain power facility environmental data; perform dynamic environmental evolution based on the power facility environmental data to generate dynamic environmental evolution data; and build a dynamic environmental evolution model for the power facility environment based on the dynamic environmental evolution data;

[0179] A fusion model rendering and embedding module is used to render the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; and perform model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model;

[0180] The electromagnetic disturbance area detection module is used to detect the corona loss fluctuation of power facilities based on the environment-power facility fusion model and generate corona fluctuation loss data; analyze the environmental fluctuation factor based on the dynamic environment evolution data and generate environmental fluctuation factor data; and detect the corona environment disturbance area based on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate the corona environment disturbance area data.

[0181] The model reconstruction module is used to calculate the disturbance error based on the corona environment disturbance area data and generate disturbance error data; based on the disturbance error data, the environment-power facility fusion model is subjected to corona environment disturbance reconstruction processing to generate a three-dimensional reconstruction model of the environment-power facility.

[0182] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced within the present invention.

[0183] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for three-dimensional reconstruction of the surrounding environment of power facilities, characterized in that: The following steps are involved: Step S1: Acquire power facility data, perform power facility layout structure analysis based on the power facility data, and generate power facility layout structure data; construct a three-dimensional model of the power facility based on the power facility spatial layout structure data; Step S2: Acquire power facility environmental data; perform dynamic environmental evolution according to the power facility environmental data to generate dynamic environmental evolution data; and construct a power facility environmental dynamic evolution model based on the dynamic environmental evolution data; Step S3: Rendering the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; performing model alignment and embedding processing on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model; Step S4: performing corona loss fluctuation detection on power facilities according to the environment-power facility fusion model to generate corona fluctuation loss data; Perform environmental fluctuation factor analysis based on dynamic environmental evolution data to generate environmental fluctuation factor data; Based on the corona fluctuation data and environmental impact fluctuation factor data, the environment-power facility fusion model is used to detect the corona environmental disturbance area and generate the corona environmental disturbance area data; Step S5: performing disturbance error calculation based on the corona environment disturbance area data to generate disturbance error data; performing corona environment disturbance reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstruction model of the environment-power facility.

2. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: acquiring power facility data, and performing power facility layout structure analysis based on the power facility data to generate power facility layout structure data; Step S12: performing power facility spatial architecture analysis based on the power facility layout structure data to generate power facility spatial architecture data; Step S13: performing power facility interaction node analysis on the power facility spatial architecture data to generate power facility interaction node data; Step S14: constructing a three-dimensional model of the power facility based on the power facility interaction node data and the power facility spatial architecture data.

3. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: acquiring power facility environmental data, and performing power facility environmental feature analysis based on the power facility environmental data to generate power facility environmental feature data; Step S22: Calculating the environmental change cycle of the power facility environmental data based on the power facility environmental characteristic data to generate environmental change cycle data; Step S23: performing a power facility environmental characteristic differentiation analysis based on the power facility environmental characteristic data and the environmental change cycle data to generate power facility environmental characteristic differentiation data; Step S24: performing power facility environment change chain analysis based on the power facility environment feature differentiation data to generate power facility environment change chain data; Step S25: performing dynamic environmental evolution based on the environmental change cycle data and the power facility environmental change chain data to generate dynamic environmental evolution data; Step S26: constructing a power facility environment dynamic evolution model based on the dynamic environment evolution data.

4. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Analyze meteorological impact factors based on the dynamic evolution model of the power facility environment to generate meteorological impact factor data; Step S32: performing a structural deformation mapping correlation process on the power facility according to the meteorological impact factor data to generate meteorological-deformation correlation factor data; Step S33: Rendering the three-dimensional model of the power facility based on the weather-deformation correlation factor data to generate a rendered three-dimensional model of the power facility; Step S34: performing model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model.

5. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing power facility magnetic field wave frequency analysis based on the environment-power facility fusion model to generate power facility magnetic field wave frequency data; Step S42: performing corona loss fluctuation detection based on the magnetic field wave frequency data of the power facility to generate corona fluctuation loss data; Step S43: performing environmental fluctuation factor analysis based on the dynamic environmental evolution data to generate environmental fluctuation factor data; Step S44: performing corona environmental disturbance area detection on the environment-power facility fusion model based on the corona fluctuation loss data and the environmental fluctuation factor data to generate corona environmental disturbance area data.

6. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 5, characterized in that: Step S42 includes the following steps: Step S421: performing magnetic field wave-frequency interaction analysis based on the magnetic field wave-frequency data of the power facility to generate wave-frequency interaction data; Step S422: performing resonance mapping spectrum processing on the power facility magnetic field wave frequency data based on the wave frequency interaction data to generate resonance mapping spectrum data; Step S423: performing electromagnetic medium jump response spectrum analysis according to the resonance mapping spectrum data to generate electromagnetic medium jump response spectrum data; Step S424: performing corona loss fluctuation detection on the power facility magnetic field wave frequency data based on the electromagnetic medium jump response spectrum data to generate corona fluctuation loss data.

7. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 6, characterized in that: Step S424 includes the following steps: Conduct corona disturbance hierarchy analysis based on electromagnetic medium jump response spectrum data to generate corona disturbance hierarchy data; Performing corona medium ionization shower mapping processing based on corona disturbance hierarchy data to generate corona medium ionization shower data; Calculate the corona medium oscillation coefficient based on the corona medium ionizing shower data to generate the corona medium oscillation coefficient; Based on the corona medium oscillation coefficient, the corona stratum ionization attenuation analysis is performed on the corona disturbance stratum data to generate the corona stratum ionization attenuation data; Based on the corona layer ion attenuation data, the corona loss fluctuation detection is performed on the magnetic field wave frequency data of the power facility to generate the corona fluctuation loss data.

8. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 5, characterized in that: Step S44 includes the following steps: Step S441: performing corona wave frequency analysis based on the corona wave loss data to generate corona wave frequency data; Step S442: performing corona wave frequency resonance processing on the corona wave frequency data based on the environmental fluctuation factor data to generate corona wave frequency resonance data; Step S443: performing corona amplitude deviation analysis based on the corona wave frequency resonance data to generate corona amplitude deviation data; Step S444: performing smoothness disturbance calculation on the corona wave frequency data according to the corona amplitude deviation data to generate smoothness disturbance data; Step S445: performing corona environment disturbance area detection on the environment-power facility fusion model based on the smoothness disturbance data to generate corona environment disturbance area data.

9. The method for 3D reconstruction of the surrounding environment of electric power facilities according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: performing disturbance dislocation superposition depth analysis on the corona environment disturbance area data to generate disturbance dislocation superposition depth data; Step S52: performing disturbance error calculation based on the disturbance misalignment superposition depth data to generate disturbance error data; Step S53: performing three-dimensional reconstruction processing on the environment-power facility fusion model based on the disturbance error data to generate a three-dimensional reconstructed model of the environment-power facility.

10. A three-dimensional reconstruction system for the surrounding environment of power facilities, characterized in that: For executing the method for 3D reconstruction of the surrounding environment of electric power facilities as claimed in claim 1, the 3D reconstruction system for the surrounding environment of electric power facilities comprises: The power facility 3D construction module is used to obtain power facility data, perform power facility spatial layout structure analysis based on the power facility data, generate power facility spatial layout structure data; and construct a power facility 3D model based on the power facility spatial layout structure data. A dynamic evolution model building module is used to obtain power facility environmental data; perform dynamic environmental evolution based on the power facility environmental data to generate dynamic environmental evolution data; and build a dynamic environmental evolution model for the power facility environment based on the dynamic environmental evolution data; A fusion model rendering and embedding module is used to render the three-dimensional model of the power facility based on the dynamic evolution model of the power facility environment to generate a rendered three-dimensional model of the power facility; and perform model alignment and embedding processing based on the rendered three-dimensional model of the power facility and the dynamic evolution model of the power facility environment to generate an environment-power facility fusion model; The electromagnetic disturbance area detection module is used to detect the corona loss fluctuation of power facilities based on the environment-power facility fusion model and generate corona fluctuation loss data; analyze the environmental fluctuation factor based on the dynamic environment evolution data and generate environmental fluctuation factor data; and detect the corona environment disturbance area based on the environment-power facility fusion model based on the corona fluctuation data and the environmental impact fluctuation factor data to generate the corona environment disturbance area data. The model reconstruction module is used to calculate the disturbance error based on the corona environment disturbance area data and generate disturbance error data; based on the disturbance error data, the environment-power facility fusion model is subjected to corona environment disturbance reconstruction processing to generate a three-dimensional reconstruction model of the environment-power facility.

Images