Electric power engineering digital visual supervision method and system based on BIM (Building Information Modeling) technology

Abstract

The invention relates to the technical field of electric power engineering visual supervision, in particular to an electric power engineering digital visual supervision method and system based on a BIM (Building Information Modeling) technology. The method comprises the following steps: acquiring electric power engineering design data, acquiring an electric power equipment configuration condition, and constructing a three-dimensional simulation model; based on the constructed three-dimensional simulation model, detecting a coupling disturbance deviation condition between the power equipment, and determining an electric energy output stability gradient degradation characteristic and a power grid output skewed distribution drift state; estimating a non-linear load increase trend of a power grid line, and judging a fatigue aggravation condition of equipment; according to the equipment fatigue trend, the decline change of the equipment function response and the overall operation risk growth trend are evaluated, space positioning processing is carried out on the operation risk, and the risk positioning result is uploaded to the cloud platform to complete early warning release; according to the invention, more stable operation of the electric power engineering is realized through visual supervision of the electric power engineering.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power engineering visualized supervision, and particularly relates to a power engineering digital visualized supervision method and system based on BIM technology. BACKGROUND

[0002] The power engineering account book and the manual inspection means supervision mode have been difficult to meet the needs of modern power engineering for fine, visualized and real-time management. In the actual engineering management process, the power equipment configuration is unevenly distributed, the power line trend is complex, the running state changes frequently and other problems are common, which often leads to the problems of power equipment state change unable to be perceived in time, the unclear electrical disturbance conduction path, the difficult power system fault tracing and other technical bottlenecks, which seriously affect the safe operation and operation and maintenance efficiency of the power engineering. The BIM technology can realize the accurate mapping of the power equipment and the line in the three-dimensional space, and combined with the real-time running data, a multi-dimensional and high-correlation power engineering simulation model can be constructed, which provides structured support for subsequent disturbance detection, risk prediction and intelligent early warning. However, the traditional power engineering visualized supervision has the problems of inaccurate power grid output skewness distribution drift state detection and inaccurate power engineering equipment fatigue aggravation condition detection. SUMMARY

[0003] Therefore, it is necessary to provide a power engineering digital visualized supervision method and system based on BIM technology to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a power engineering digital visualized supervision method based on BIM technology comprises the following steps: Step S1: acquiring power engineering design data; collecting power engineering power equipment configuration conditions according to the power engineering design data; constructing a power engineering three-dimensional simulation model based on the power engineering design data and the power engineering power equipment configuration conditions; Step S2: detecting power equipment coupling disturbance deviation conditions according to the power engineering three-dimensional simulation model; determining power energy output stability gradient degradation features based on the power equipment coupling disturbance deviation conditions; detecting power grid output skewness distribution drift states according to the power energy output stability gradient degradation features and the power equipment coupling disturbance deviation conditions; Step S3: determining power grid line nonlinear load growth conditions based on the power grid output skewness distribution drift states; determining power engineering equipment fatigue aggravation conditions according to the power grid line nonlinear load growth conditions; Step S4: detecting the function response degradation trend of the power engineering equipment according to the power engineering equipment fatigue aggravation condition, evaluating the power engineering operation risk growth trend based on the function response degradation trend of the power engineering equipment, and performing power engineering risk positioning processing according to the power engineering operation risk growth trend to obtain power engineering risk positioning data and upload the power engineering risk positioning data to the cloud platform for risk early warning.

[0005] The application realizes the spatial fusion and structural expression of power engineering design data and power equipment configuration information by constructing a BIM-based three-dimensional simulation model, which helps to improve the identification accuracy of the operation linkage state between equipment. With the help of the power equipment coupling disturbance deviation identification method, the dynamic tracking ability of the abnormal propagation path of multi-node cooperation is enhanced, thereby realizing the fine evaluation of the stability degradation trend of power output and improving the timeliness of early detection of operation abnormalities. Based on the skew distribution drift detection, the composite characteristics such as electromagnetic interference diffusion and power supply fluctuation anomaly can be reflected, and the visual monitoring ability of the abnormal evolution process of power grid output is improved. Combined with the correlation analysis of nonlinear load growth and fatigue aggravation state, the identification ability of the damage mechanism of key components is enhanced, which provides support for the spatio-temporal dynamic evaluation of line deformation, stress amplification and crack propagation trend. On this basis, by constructing the quantitative correlation mechanism of function response degradation and operation risk growth, the prediction accuracy of the failure trend of the power engineering and the partition risk delimiting ability are improved, which guarantees the traceability, positioning and early warning of risk data. Therefore, the application optimizes the traditional power engineering visualization supervision, solves the problems of inaccurate skew distribution drift state detection of power grid output and inaccurate fatigue aggravation condition detection of power engineering equipment in the traditional power engineering visualization supervision method, and improves the accuracy of skew distribution drift state detection of power grid output and the accuracy of fatigue aggravation condition detection of power engineering equipment.

[0006] The application also provides a BIM technology-based power engineering digital visualization supervision system for executing the BIM technology-based power engineering digital visualization supervision method as described above, which comprises: A model construction module is configured to acquire power engineering design data, collect power engineering power equipment configuration conditions according to the power engineering design data, and construct a power engineering three-dimensional simulation model based on the power engineering design data and the power engineering power equipment configuration conditions. A skew distribution drift detection module is configured to detect power equipment coupling disturbance deviation conditions according to the power engineering three-dimensional simulation model, determine power output stability gradient degradation characteristics based on the power equipment coupling disturbance deviation conditions, and detect power grid output skew distribution drift states according to the power output stability gradient degradation characteristics and the power equipment coupling disturbance deviation conditions. The fatigue aggravation determination module is used for determining the nonlinear load growth of the power grid line based on the power grid output skew distribution drift state; and the fatigue aggravation state of the power engineering equipment is determined according to the nonlinear load growth of the power grid line. The risk early warning module is used for detecting the functional response recession trend of the power engineering equipment according to the fatigue aggravation state of the power engineering equipment; the power engineering operation risk growth trend is evaluated based on the functional response recession trend of the power engineering equipment; the power engineering risk positioning processing is performed according to the power engineering operation risk growth trend, the power engineering risk positioning data is obtained, and the power engineering risk positioning data is uploaded to the cloud platform for risk early warning.

[0007] The BIM technology-based power engineering digital visualized supervision system of the application can realize any BIM technology-based power engineering digital visualized supervision method of the application, is used as a medium for joint operation and signal transmission between modules, and is used for completing the BIM technology-based power engineering digital visualized supervision method. The modules in the system cooperate with each other, multi-source data fusion and multi-dimensional risk dynamic perception of the whole life cycle operation state of the power engineering are realized, and the power engineering risk identification, accurate positioning and online early warning capability are improved. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 It is a step flowchart of a BIM technology-based power engineering digital visualized supervision method. Figure 2 It is a step flowchart of a BIM technology-based power engineering digital visualized supervision method. Figure 1 It is a detailed implementation step flowchart of step S3. Figure 3 It is a detailed implementation step flowchart of step S3. Figure 1 It is a detailed implementation step flowchart of step S4. The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0009] The technical method of the application will be described clearly and completely in combination with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the application.

[0010] Furthermore, the accompanying drawings are included to provide a further understanding of the present application, and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings:

[0011] It should be understood that, although terms such as "first", "second", and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element without departing from the scope of the example embodiments. The term "and / or" as used herein encompasses any and all combinations of one or more of the associated associated items.

[0012] To achieve the above object, there is provided Figures 1 to 3 A power engineering digital visualization supervision method based on BIM technology, comprising the following steps: Step S1: acquiring power engineering design data; collecting power engineering power equipment configuration status according to the power engineering design data; constructing a three-dimensional simulation model of the power engineering based on the power engineering design data and the power engineering power equipment configuration status; In the embodiment of the present application, a design database corresponding to a power engineering project in a building information modeling (BIM) platform is called, and a design data set corresponding to an engineering number is extracted, the design data including model data in CAD format and IFC format such as a high-voltage substation primary equipment layout diagram, a cable trench path layout diagram, a power transmission line direction diagram, and an electrical main wiring diagram. API interface in Revit software is used for data analysis and processing, and device position information, device model (such as 500kV transformer, GIS switch, bus system), rated voltage level, installation height, protection configuration parameters and other information are collected item by item, and an attribute mapping table is established. Then, according to the obtained power equipment configuration condition, different types of equipment are numbered and classified and bound with three-dimensional model elements by establishing an equipment classification coding system. Navisworks software is used to align and register the above-mentioned two-dimensional electrical arrangement information and the BIM three-dimensional structure model, call the collision detection and space integration module, realize the physical positioning of the power equipment configuration in the spatial three-dimensional model. Through parameter-driven rule construction logic, each power equipment configuration parameter (such as rated load, resistance, reactance, short-circuit capacity) is input into the spatial model and associated with its operating position, and the three-dimensional simulation model construction facing the whole life cycle of the power engineering is completed, providing structure and attribute support for subsequent equipment operation analysis.

[0013] Step S2: detecting power equipment coupling disturbance deviation condition according to the power engineering three-dimensional simulation model; determining power output stability gradient degradation feature based on the power equipment coupling disturbance deviation condition; detecting power grid output skew distribution drift state according to the power output stability gradient degradation feature and the power equipment coupling disturbance deviation condition; In the embodiment of the present application, the power engineering three-dimensional simulation model generated in step S1 is imported into the Matpower or E simulation environment, combined with the real-time operation data of the equipment collected in the field operation log database (including main transformer voltage fluctuation record, circuit breaker opening and closing time sequence, cable temperature rise curve, power flow distribution data, etc.), and the electrical coupling disturbance simulation between the equipment is carried out. The node admittance matrix method is used to analyze the power flow change trend caused by instantaneous load fluctuation between different electrical nodes, and the current coupling rate between adjacent equipment is calculated. If the coupling disturbance exceeds 0.2 p.u., it is marked as a deviation node. Extract all node combinations with coupling disturbance greater than the set threshold and count the disturbance direction and change rate. According to the disturbance slope calculation result, the change gradient of output voltage or current is analyzed by using the curve fitting method, and the electrical energy output stability gradient degradation characteristic curve is further obtained. The coupling disturbance deviation data and the output stability change trend are processed by double variable mapping, the drift dominant factor is identified by principal component analysis (PCA), and the output value probability distribution graph is constructed. The Kullback-Leibler divergence is calculated with the historical normal distribution characteristics. If the divergence value exceeds 0.05, it is determined that the power grid output is in a skew distribution drift state. The above process realizes the closed-loop deduction from the structural model to the disturbance identification and output stability evaluation.

[0014] Step S3: determining the non-linear load growth of the power grid line based on the skew distribution drift state of the power grid output, and determining the fatigue aggravation condition of the power engineering equipment according to the non-linear load growth of the power grid line; In the embodiment of the present application, for the skew distribution drift state of the power grid output identified in step S2, the historical power flow record, load current data and temperature monitoring data of all transmission lines in the simulation model are retrieved, and the frequency domain load response change of each line at different times is analyzed by combining short-time Fourier transform. By trend analysis on the cable current density curve, the non-linear load growth behavior is identified. Specifically, if the current peak growth rate exceeds 5% / h, and the non-linear load growth lasts for more than 2h, it is recorded as an abnormal load growth line. At the same time, the derivative of the line reactance with respect to time is calculated, which is used to judge the enhancement trend of electromagnetic transient coupling effect. Further, the non-linear load growth line is mapped to the device nodes in the topological structure constructed in step S1, and the historical operation frequency, voltage drop record, overload alarm information, etc. of the devices connected to the line are analyzed. If the device has three or more short-time voltage drops in the past 48 hours, it is determined as a fatigue aggravation node. All fatigue aggravation nodes are grouped and clustered to extract the fatigue influence conduction path. This step realizes the establishment of causal relationship between the statistical characteristics of skew distribution drift and electrical load behavior and equipment fatigue mechanism.

[0015] Step S4: detecting the functional response degradation trend of the power engineering equipment according to the fatigue aggravating condition of the power engineering equipment; evaluating the power engineering operation risk growth trend based on the functional response degradation trend of the power engineering equipment; performing power engineering risk positioning processing according to the power engineering operation risk growth trend, obtaining power engineering risk positioning data, and uploading to the cloud platform for risk early warning.

[0016] In the embodiment of the application, the device operation log corresponding to the fatigue aggravating node identified in step S3 is called, and data including switch response time, protection device delay response, secondary system alarm delay and the like are collected to construct a device functional response index system. The hierarchical clustering method is used to analyze the similarity and degradation trend of the device functional parameters. If the response time is delayed by more than 20 ms relative to the initial calibration value and the duration is more than 12 hours, the functional response degradation trend device is calibrated. The functional parameters of all degradation trend devices are input into a multiple linear regression model, and the regression coefficient change trend is used as a function variable of risk growth to obtain a power engineering operation risk growth trend function curve. Then, the inflection point position of the curve is used to determine the risk acceleration growth period, and the geographical mapping is performed according to the node space position to generate a risk heat distribution map. The distribution map is transmitted to the cloud platform through the middleware interface, received and stored by the AWS IoT Core platform. Automatic labeling and early warning push processing are performed in combination with the risk level evaluation strategy in the platform to form power engineering risk positioning data and for real-time early warning linkage control.

[0017] Preferably, step S1 comprises the following steps: Step S11: obtaining power engineering design data; In the embodiment of the application, the full amount of design data corresponding to the project number is obtained by calling the preset design database in the power engineering BIM system. The design data includes project construction drawings, system wiring diagrams, electrical primary wiring diagrams, load distribution diagrams, power transmission line section diagrams, substation structure plan diagrams, and terrain and landscape diagrams, and the like, all of which are stored in IFC format, DWG format, and CSV structured information. Using the data interface provided by the Revit platform, the above-mentioned files are parsed by an embedded data calling function, and the structural members, power transmission paths, and cable trenches are extracted and classified according to modules. Each item of information involved in the design data is provided with a property parameter field, including device number, rated voltage, operation time, electrical connection relationship, spatial coordinate value, installation elevation, operation mode, power supply line scheme, and the like. By reading the XML configuration file, the data contents in different formats are uniformly encoded and loaded into the engineering view configuration table of the BIM system, which opens up the data entry for subsequent device configuration and path analysis. In this process, the structural data interpretation script is used to standardize the field of different drawing formats (such as DWG, IFC) and output a uniformly named data set, which is labeled as “power engineering design basic data set” and named according to the engineering naming rules and imported into the database of the BIM platform.

[0018] Step S12: collecting power equipment configuration status of the power engineering according to the power engineering design data; In the embodiment of the application, according to the “power engineering design basic data set” imported in step S11, the device recognition and configuration extraction module of the BIM platform is called to batch extract the power equipment information in the design drawings. By analyzing the correspondence between the symbol elements and the symbol coding table in the primary main wiring diagram, the voltage level, device category, and device connection node are recognized, and the device position in the design drawing is automatically located. Using the three-dimensional component geometric information extraction logic, the spatial profile, physical position (X, Y, Z three-dimensional coordinates), installation surface orientation, base size, and the like of each device are written into the attribute field. The system gives a unique code identification to each recognized power equipment, and establishes the connection topology relationship between the devices. The device configuration status includes but is not limited to: transformer model, circuit breaker type, bus arrangement, cable laying path, bus segmentation position, and the like. The device configuration data is output in the form of a table, which contains device code, function description, voltage level, connection element, running node number, and spatial positioning information fields, generates a “power equipment configuration table”, and is structurally associated with the design basic data set. The data table will serve as an input data support source for building a three-dimensional model of the electrical system.

[0019] Step S13: obtaining power transmission line distribution of the power engineering according to the power engineering design data; In this embodiment of the invention, topographic maps, profile views, and transmission line route maps related to the transmission lines are retrieved from the design base dataset and spatially interpreted. Using the ArcGIS spatial analysis module, the tower location coordinates marked on the design drawings are extracted in batches to generate a tower location set. Simultaneously, the line numbers and elevation data from the transmission route design drawings are retrieved, and combined with the terrain model in the BIM system, the spatial path of the transmission lines is fitted. The line distribution includes tower types (e.g., tension towers, straight-line towers), overhead line routes, cable laying methods (direct burial, cable trenches, cable trays, etc.), conductor types (e.g., LGJ-400 / 50), and route span and clearance data. The route height is assessed using a digital elevation model (DEM) to obtain the changes in the vertical distance between the route and the ground, and the tower placement positions and line sag are calculated accordingly. The above data combination forms a "Power Engineering Transportation Line Distribution Dataset," which provides data support for the accurate layout of line components in the subsequent 3D model. This distribution dataset is connected to the equipment configuration table through a spatial topological logical structure, providing complete equipment and line layout elements for the model construction stage.

[0020] Step S14: Construct a three-dimensional simulation model of the power engineering based on the distribution of power engineering transmission lines and the configuration of power equipment in the power engineering.

[0021] In this embodiment of the invention, based on the power equipment configuration table and the power engineering transportation line distribution dataset, the model building function is called in the BIM platform to execute the component layout logic. Using family component templates defined in the Revit or Navisworks environment, components such as substation equipment, transmission towers, switchgear, and cable trenches are instantiated according to equipment model, installation location, and spatial coordinates. Each component is bound to attribute parameters obtained from the configuration table and arranged in three-dimensional space according to path planning. For example, the main transformer in a substation is arranged in the core location of the station using the naming principle of "equipment number-model-coordinates," and the wiring path is drawn as a pipeline according to the topological relationship in the wiring diagram and connected to each piece of equipment. Overhead transmission lines use tower point sets to generate spatial polylines, and conductor components are laid out based on tower spacing and conductor type; cable lines are laid at a specified depth below the terrain surface, and the bending direction is controlled by path nodes. The entire model building process uses a LOD300 or higher accuracy standard to ensure complete structural hierarchy, complete component information, and visible topological connections. After completion, a complete 3D simulation model of the power engineering is generated and exported in the IFC4 standard format, serving as the structural basis for subsequent power equipment operation analysis and risk assessment.

[0022] Preferably, step S14 includes the following steps: Step S141: Determine the route of the power engineering lines based on the distribution of power engineering transportation lines; In this embodiment of the invention, the input data on the distribution of power engineering transportation lines is parsed. This data is provided in CAD format or GIS vector map form and includes the spatial direction of the line, laying type (overhead or cable), altitude, and the zone number to which the line belongs. The spatial coordinate recognition module in the BIM integration platform is used to parse the geometric information of the line and identify the spatial direction coordinate information of each line segment (e.g., latitude, longitude, and elevation coordinate triplets). After classifying the data according to the line number, the main direction angle of each line is calculated based on the difference between the coordinates of the line's starting and ending points (e.g., the deflection angle relative to true north is calculated using the arctangent function), and the power engineering line direction information is output, forming a set of standard direction data tables, which serve as the basis for subsequent node distribution and network topology construction.

[0023] Step S142: Determine the distribution of power engineering connection nodes based on the distribution of power engineering transportation lines; In this embodiment of the invention, based on the power engineering transmission line distribution obtained above, and combined with the spatial location files of electrical facilities such as stations, substations, and transmission towers input from the BIM platform, the geographical coordinates of all physical nodes are extracted. Spatial clustering methods (such as the DBSCAN density clustering algorithm) are used to cluster the node coordinates, and the start and end point coordinates of each line are matched with the actual equipment locations to determine the physical node numbers connected to the start and end points of each line, establishing a mapping relationship between node numbers and spatial locations. Node information includes node number, equipment type, coordinate location, and the corresponding transmission path number, outputting the distribution of power engineering connection nodes for topology construction.

[0024] Step S143: Construct the power transmission network topology based on the distribution of power engineering connection nodes and the route of power engineering lines; In this embodiment of the invention, the route information obtained in step S141 and the node distribution information obtained in step S142 are fused. During the establishment of the power transmission network topology, nodes are used as vertices of the graph structure, and transmission lines are used as edges. If any two nodes are connected by a transmission line, a directed edge is established in the graph, with the edge weight labeled as the line length (in meters), and the directionality derived from the route. The topology is stored using an adjacency matrix or adjacency list from graph theory. After construction, connectivity analysis is performed to verify the graph's integrity and connectivity, and a power transmission network topology file is output, containing the upstream and downstream nodes connected to each node, path numbers, edge weights, and spatial direction attributes.

[0025] Step S144: Identify the operating mode data of power equipment based on the configuration status of power equipment in power engineering; In this embodiment of the invention, based on the configuration of power equipment in the power engineering project, the basic parameters (such as equipment type, power level, voltage level, operating status, etc.) of each power device are read. Equipment operating mode classification standards (such as load operation, standby operation, maintenance status, overload status) are used for comparison and classification. Based on SCADA historical data or operation log data, parameters such as the operating frequency, start-stop count, and overload duration of each device over the past month are extracted. Combined with the operating status code, the current operating mode is automatically identified to form a power equipment operating mode data table, recording the equipment number, operating mode classification number, and associated operating parameters as input for performance evaluation.

[0026] Step S145: Evaluate the operating performance parameters of the power equipment based on the configuration status and operating mode data of the power equipment in the power engineering project; In this embodiment of the invention, based on the power equipment operation mode data obtained in step S144 and combined with the basic design parameters provided in the power equipment configuration status, the Fault Tree Analysis (FTA) method and equipment life cycle model are used to evaluate the performance degradation coefficient of various types of equipment. Specifically, this includes: calculating the ratio of the number of switching operations to the switching life of switchgear to obtain switch fatigue; calculating the load factor (i.e., the ratio of current load to rated load) and historical temperature rise level of transformers to predict the percentage of insulation life loss; and calculating the current carrying capacity and conductor temperature rise of line equipment to evaluate thermal stress. All performance evaluation results are output in numerical quantification to form a power equipment operation performance parameter data table.

[0027] Step S146: Perform power engineering correlation matching processing on the power equipment operating performance parameters and the power transmission network topology to obtain power engineering correlation matching data; In this embodiment of the invention, the power transmission network topology constructed in step S143 and the power equipment operating performance parameters obtained in step S145 are fused together. Using node numbers as the primary key, performance parameters are bound to corresponding nodes in the topology, forming a topology graph with enhanced node attributes. Subsequently, nodes with performance anomalies or degradation are identified based on a matching algorithm, and the upstream and downstream lines and equipment connected to them are identified and marked as potential risk-related paths. After completing the power engineering association matching process, power engineering association matching data is generated, including equipment parameters, topology association relationships, and anomaly propagation path markings for each node.

[0028] Step S147: Perform three-dimensional spatial mapping processing based on the power engineering correlation matching data to obtain the three-dimensional spatial mapping data of the power engineering; In this embodiment of the invention, based on associated matching data, a BIM 3D engine is invoked for spatial reconstruction. The spatial coordinate information of each node is used to map associated attributes to a 3D spatial structure. The specific processing includes: converting nodes in the 2D topology into 3D spatial points in the BIM coordinate system, and converting edges into spatial line segments; loading corresponding component models (such as power towers, distribution boxes, etc.) from the standard BIM component family library according to the node type, and identifying different operating states through material parameters. Upon completion, 3D spatial mapping data for the power engineering is output, including component entity data, spatial connection information, and an operating parameter mapping table.

[0029] Step S148: Construct a three-dimensional simulation model of the power engineering based on the three-dimensional spatial mapping data of the power engineering and the operating performance parameters of the power equipment.

[0030] In this embodiment of the invention, based on the three-dimensional spatial mapping data of the power engineering generated in step S147, the BIM visualization modeling module is invoked to construct a complete three-dimensional simulation model of the power engineering. This process includes three parts: spatial geometric modeling, logical connection modeling, and operational attribute association modeling. The model data is organized using the IFC standard structure, and coordinate registration is performed using a GIS spatial reference system to ensure that all equipment components and their logical connections accurately correspond in the three-dimensional environment. Simultaneously, operational performance parameters and historical operational data are loaded, achieving a deep fusion of the three-dimensional visualization structure and performance data. The resulting three-dimensional simulation model includes complete spatial structure, topological logic, operational performance, operational mode, and real-time status mapping data, which can be used for subsequent coupling disturbance analysis, skewness distribution detection, and other functional modules.

[0031] Preferably, step S2, which involves detecting the coupling disturbance deviation of power equipment based on the three-dimensional simulation model of the power engineering, includes: Acquire power engineering operation log data, and collect power equipment operation disturbance parameters based on the power engineering operation log data; In this embodiment of the invention, real-time operation log data of equipment is obtained from the power engineering operation data center. The data sources include sensor measurement modules of transformers, circuit breakers, cables, and switchgear. Sensors collect multi-dimensional operating indicators such as voltage, current, frequency, and power factor through high-frequency sampling interfaces, with a sampling frequency of 1kHz or higher to ensure that the data time resolution meets the requirements for dynamic disturbance capture. The collected raw data is uploaded to the data processing server via a communication network. The server performs time synchronization on the raw log data to ensure that the timestamps of all equipment data are aligned. Subsequently, filtering algorithms (such as bandpass filters) are used to remove background noise and external electromagnetic interference. Anomaly detection is performed on the data to remove sudden noise and invalid samples. Next, based on a disturbance feature extraction algorithm, disturbance parameters are calculated from the cleaned data, including voltage drop amplitude, short-term frequency fluctuation, load change rate, and transient current peak value, forming a structured disturbance parameter database for subsequent coupled analysis. This database not only contains the disturbance amplitude but also records the disturbance duration, start and end times, and waveform characteristic parameters, ensuring a comprehensive presentation of the dynamic characteristics of the disturbance in subsequent analysis.

[0032] Based on the three-dimensional simulation model of power engineering, the collaborative evolution analysis between power equipment is carried out to obtain the collaborative relationship data between power equipment; In this embodiment of the invention, a multiphysics coupling simulation framework is constructed. Based on the accurate spatial coordinates and structural attributes of each device in the BIM 3D model of the power engineering project, the physical coupling effect between devices is analyzed. Electromagnetic field finite element analysis (FEA) software is used to model electromagnetic interference between devices, calculate electromagnetic field strength and coupling coefficients, and quantitatively describe the electromagnetic influence between different device nodes. Secondly, based on a thermodynamic model, the heat transfer process of the devices is simulated, and the thermal coupling conduction coefficient is calculated to reflect the interrelationship of temperature changes between devices. Using a mechanical vibration analysis model, combined with the structure's natural frequency and excitation force, the vibration propagation path and coupling strength of the devices are analyzed. The above three coupling coefficients are summarized to form a multidimensional coupling matrix. Subsequently, a weighted co-evolution calculation method is used to synthesize the multiphysics coupling data to obtain the co-evolution index between device nodes, with a value range of 0 to 1. A larger value indicates a tighter coupling relationship. The calculation basis of the co-evolution index includes node physical distance, coupling strength, and disturbance propagation path. The output co-evolution relationship data is stored in matrix form, providing accurate data support for the subsequent identification of multi-node interaction mechanisms.

[0033] When the inter-power equipment coordination relationship data exceeds 0.6, the multi-node interaction mechanism of power equipment is determined; In this embodiment of the invention, a threshold screening algorithm is used to identify node pairs with a co-evolution index greater than 0.6, which are considered as key device combinations with strong coupling effects. Using graph theory methods, these key nodes and their co-connections are constructed into a weighted undirected graph, where nodes represent devices and edge weights represent coupling strength. The graph structure is used to determine coupling paths, key conduction nodes, and multi-node interaction loops in the network through topology analysis. Furthermore, a community partitioning algorithm (such as the modularity maximization algorithm) is employed to identify multi-node groups and reveal the mechanisms of complex coupling. These mechanisms include electromagnetic interference coupling links, thermal conduction coupling clusters, and mechanical vibration resonance networks. This multi-node interaction network provides the system structure foundation for subsequent disturbance propagation simulations and identifies the scope of influence and key coupling regions, ensuring that the simulation process accurately reflects the complex multi-node mutual influence relationships.

[0034] Based on the operating disturbance parameters of power equipment, the full-process response evolution of power equipment is simulated according to the multi-node interaction mechanism of power equipment, and the full-process response evolution data of power equipment is obtained. In this embodiment of the invention, based on the aforementioned multi-node coupling structure and the collected disturbance parameters, a time-domain dynamic simulation method is used to simulate the disturbance process. The disturbance parameters serve as the initial excitation input, and the model solves the coupled dynamic equations of the electromagnetic field, thermal field, and mechanical vibration through numerical integration, calculating in real time the propagation of the disturbance along the node network and the device response. The simulation time step is set to be smaller than the characteristic period of the disturbance signal to ensure detailed capture. During the simulation, the system records the voltage, current, temperature, and vibration amplitude of each node at each time step, forming high-resolution time-series response data. Through the data storage management module, a full-process response evolution dataset is output, including the time sequence of node responses, peak data, and response duration, laying the data foundation for subsequent time-series and amplitude analysis.

[0035] Based on the whole process response evolution data of power equipment, the time series analysis of the response of power equipment nodes is carried out to obtain the time series data of power equipment node response. In this embodiment of the invention, time series analysis technology is applied to the entire process response data to identify the response start time, peak time, and end time of each node. Specific methods include response signal envelope detection and peak detection algorithms, which, combined with derivative information of the response data, accurately determine the response inflection points. A response time-series curve for each node is constructed, clearly describing the propagation order and temporal relationships of the disturbance signal in the network. The time-series data is presented in tabular form, including node ID, response start time, peak time, and response end time, ensuring a standardized data structure and facilitating further analysis. This time-series data reveals the time delays and interaction relationships of the responses of each device node, providing a fundamental temporal basis for subsequent disturbance propagation path identification.

[0036] Extract the power equipment response delay distribution characteristics based on the power equipment node response time sequence data; In this embodiment of the invention, the time difference between the response start time of each node and the disturbance start time is calculated to form a set of device response delays. Statistical analysis methods are used to calculate the mean, variance, and distribution density of the response delays, and a response delay distribution map is plotted. The response delay distribution reflects the disturbance propagation speed, path, and system conduction characteristics. By comparing the delay distribution with historical normal states, nodes with abnormal delays can be identified, revealing potential coupling anomalies or propagation obstacles. This characteristic data provides quantitative indicators for identifying abnormal disturbance paths and assessing network stability, ensuring a comprehensive understanding of the dynamic response process.

[0037] Extract the amplitude variation trend of power equipment based on the time series data of power equipment node response; In this embodiment of the invention, based on the time-series response peak data, a trend analysis algorithm is used to calculate the rate of change of the response amplitude of each node. A linear regression method is used to fit the amplitude change curve over time to obtain a trend parameter indicating amplitude increase or decrease. The trend parameter value is used to determine the enhancement or decay of the disturbance. Nodes with amplitude change trends exceeding ±30 volts are marked as anomalous disturbance nodes, indicating significant energy increases or decreases at these nodes. The amplitude change trend data is stored in both curve and numerical form, providing a quantitative basis for subsequent multi-node propagation path construction and reflecting the spatial variation of disturbance intensity in the network.

[0038] When the amplitude variation trend of power equipment exceeds ±30V, the multi-node cooperative disturbance propagation path data is determined based on the power equipment response delay distribution characteristics. In this embodiment of the invention, key response nodes with an absolute value of amplitude change trend greater than 30 volts are selected through threshold screening. Combining the node response delay distribution, path search algorithms (such as shortest path search and breadth-first search) are used to identify the propagation path of the disturbance in the multi-node network. Path construction incorporates node spatial coordinates and response timing to ensure spatial and temporal continuity. The multi-node propagation path is represented in the form of node sequences and path weight matrices, clearly revealing the main transmission link and key coupling points of the disturbance signal, providing detailed data for analyzing the disturbance's impact range and propagation mechanism.

[0039] Detection of coupling disturbance deviation in power equipment based on multi-node collaborative disturbance propagation path data.

[0040] In this embodiment of the invention, multi-node propagation path data is compared and analyzed with real-time monitored disturbance response data. Deviation indices between the actual response path and the ideal propagation path are calculated, including path node offset, response delay difference, and amplitude variation deviation. A deviation analysis algorithm is used to quantify the anomaly degree of the coupled disturbance, identifying the deviation nodes and their corresponding abnormal amplitudes and delays. The deviation results generate a deviation detection report, which details the deviation location, amplitude, and propagation characteristics, providing accurate risk location data for power engineering operation and maintenance, and supporting subsequent risk warning and fault handling.

[0041] Preferably, the determination of the power output stability gradient degradation characteristics based on the coupling disturbance deviation of power equipment in step S2 includes: Determine the impact of abnormal power equipment status based on the coupling disturbance deviation of power equipment; In this embodiment of the invention, the power equipment coupling disturbance deviation data obtained in the aforementioned steps is used as the basic input, including disturbance amplitude deviation, time delay deviation, and deviation spatial distribution. Anomaly detection algorithms are employed to perform spatiotemporal pattern recognition on the deviation data, identifying abnormal deviation clusters and their corresponding equipment nodes. Data preprocessing includes normalization to eliminate differences in data dimensions between different devices. Based on statistical methods (such as cluster analysis and anomaly detection), abnormal coupling disturbance deviation nodes are screened, and their corresponding power equipment state anomalies are identified. The impact of state anomalies is specifically reflected through changes in equipment electrical characteristics, such as decreased insulation resistance, severe voltage fluctuations, and excessive frequency deviations. Historical health data of the equipment is used to compare the state characteristics of abnormal nodes, and an anomaly impact index is quantitatively calculated. This index reflects the intensity of interference between the deviation and the normal operation of the equipment. A dataset of power equipment state anomaly impacts is output, including a list of abnormal equipment, anomaly severity level, and impact range, providing a basis for subsequent performance degradation trend estimation.

[0042] Based on the coupling disturbance deviation of power equipment and the impact of abnormal power equipment status, the trend of power equipment performance degradation is estimated; In this embodiment of the invention, a power equipment performance degradation prediction model is constructed by combining coupled disturbance deviation data with the impact of equipment state anomalies. A time-series regression analysis method is employed, using disturbance deviation amplitude, frequency, and state anomaly impact index as input variables, and outputting the rate of change of equipment performance indicators. Performance indicators cover equipment power output, energy efficiency ratio, voltage stability, and load-bearing capacity. The performance degradation trend is expressed as a percentage, representing the proportion of performance decline per unit time. Using historical equipment performance maintenance records, a combination of multivariate linear regression and machine learning regression trees is employed to fit the performance degradation trend function, ensuring accurate estimation of the complex impact of multiple factors. The model uses cross-validation to ensure predictive stability. The model outputs power equipment operating performance degradation trend data; when the degradation trend exceeds 1%, it enters the subsequent efficiency reduction detection stage.

[0043] When the performance degradation trend of power equipment is >1%, the reduction in the operating efficiency of power equipment is detected. In this embodiment of the invention, based on the determination that the performance degradation trend exceeds 1%, real-time operating efficiency data of the equipment is further collected, mainly including the equipment's power conversion efficiency, load response efficiency, and loss rate. Real-time efficiency data is acquired through measurement modules embedded in the equipment, including power factor sensors, current transformers, and voltage sensors. The data undergoes high-frequency sampling and filtering. Using the efficiency calculation formula, combined with the collected current, voltage, and power data, the current equipment efficiency value is accurately calculated. The current efficiency value is compared with the normal operating baseline efficiency to calculate the percentage reduction in efficiency. Equipment with an efficiency reduction exceeding 5% is included in the abnormal efficiency reduction range. The efficiency reduction data is stored in time series format, indicating the start and end times and magnitude of the efficiency reduction, serving as a key input for subsequent health degradation status assessment.

[0044] The health status of power equipment is assessed when the performance degradation trend of power equipment and the reduction in power equipment operating efficiency exceeds 5%. In this embodiment of the invention, a weighted comprehensive evaluation method is used to assess the health degradation status of equipment by considering both performance degradation trends and efficiency reduction. A Health Index (HI) calculation model is employed, with the performance degradation trend weighted at 0.6 and efficiency reduction weighted at 0.4. The HI value is calculated through linear weighting, ranging from 0 to 1, with higher values ​​indicating worse health. Multi-source data fusion technology is utilized to integrate equipment maintenance history, fault records, and real-time monitoring data to ensure a comprehensive health degradation assessment. Spatial data analysis is used to assist the assessment by combining the spatial location and operating environment information of the equipment in the BIM model, revealing the impact of the local environment on health degradation. The assessment results are output as health degradation status levels, clearly distinguishing between normal, mild degradation, moderate degradation, and severe degradation, laying a data foundation for predicting the growth trend of fault frequency.

[0045] Predict the growth trend of equipment failure frequency based on the decline in the operational health status of power equipment. In this embodiment of the invention, based on equipment health degradation data, a fault frequency growth trend is calculated using fault statistical analysis methods. Historical fault records and corresponding health status data are compiled to establish a fault probability model. Survival analysis methods (such as Kaplan-Meier estimation and Cox proportional hazards model) are employed to analyze the impact of health status on the probability of fault occurrence and to predict future fault frequency trends. Input variables include health index, equipment operating years, maintenance interval, and load change rate. The output is the equipment fault frequency growth trend, specifically the expected percentage increase in the number of faults per unit time. Trend data is stored in time series format to support subsequent risk analysis and maintenance plan development. This step ensures a quantitative prediction of future equipment fault risks, providing a basis for assessing the risk of sudden accidents.

[0046] The increasing trend of equipment failure frequency and the declining health status of power equipment are used to determine the increasing trend of equipment sudden accident risk. In this embodiment of the invention, a risk assessment matrix method is used to determine the increasing trend of equipment sudden accident risk by combining the fault frequency growth trend and the operational health status. The risk matrix dimensions are the fault frequency growth rate and the health decay level, and their values ​​are mapped to risk level ranges after standardization. Combining a historical accident case database, a Bayesian inference method is used to quantify the joint impact of fault frequency and health status on the probability of accident occurrence, outputting an indicator of the increasing trend of equipment sudden accident risk, expressed as a risk probability value and its rate of change as a time function. Through risk trend curve analysis, high-risk growth nodes and risk outbreak periods are identified, providing dynamic early warning references for power system safe operation monitoring. The risk data storage structure supports subsequent multi-dimensional risk linkage analysis.

[0047] Determine the fluctuation status of power supply quality based on the increasing trend of equipment accident risk; In this embodiment of the invention, power quality fluctuations are identified by mapping the trend of sudden accident risks to power quality indicators. Power quality indicators include voltage deviation rate, frequency fluctuation amplitude, harmonic distortion, and power outage frequency. Correlation analysis is performed between power quality data collected by the field monitoring system and accident risk trend data. Time series correlation analysis and regression models are used to determine the degree of impact of risk growth on each power quality parameter. Based on the impact model, a power quality fluctuation metric is calculated, which expresses the degree of power stability decline in the form of a score or grade. The analysis process employs data fusion technology to unify the processing of multi-source monitoring data and risk prediction data, ensuring a comprehensive and accurate reflection of power quality fluctuations. The results serve as the basis data for the gradient degradation characteristics of power output stability.

[0048] The gradient degradation characteristics of power output stability are determined based on the fluctuation of power supply quality of power equipment.

[0049] In this embodiment of the invention, based on power quality fluctuation data, a gradient analysis method is used to quantify the degradation characteristics of power output stability. Spatial-temporal gradient calculations are performed on the time series data of power quality indicators to reveal the spatial distribution trend and temporal evolution characteristics of power output stability. Finite difference method and numerical differentiation techniques are used to calculate the gradient to ensure accuracy. Subsequently, combined with equipment spatial distribution data in the BIM model, the gradient information is mapped to three-dimensional space to achieve a visual representation of power stability degradation. Degradation characteristic data is output in the form of numerical matrices and spatial distribution maps, reflecting the differences in power output stability levels in different regions and equipment. This data supports the dynamic monitoring and anomaly diagnosis functions of the subsequent digital visualization monitoring system, realizing global power stability management based on BIM technology.

[0050] Preferably, step S2, which involves detecting the grid output skewness distribution drift state based on the power output stability gradient degradation characteristics and the coupling disturbance deviation of power equipment, includes: The nonlinear variation of the magnetic field distribution is estimated based on the characteristics of the gradient degradation of power output stability and the coupling disturbance deviation of power equipment. In this embodiment of the invention, the power output stability gradient degradation characteristic data and power equipment coupling disturbance deviation data obtained in the previous step are used as input parameters to perform an estimation operation of the nonlinear change of the magnetic field distribution. This operation is based on high-precision electric / magnetic field joint monitoring data, calls the three-dimensional magnetic flux density real-time distribution map, and extracts the magnetic field vector change gradient through differential processing algorithm; in each monitoring unit grid, with an interval of 0.1T, the consistency coefficient of the magnetic flux density vector gradient direction in unit space is calculated, and the dynamic change rate of the magnetic flux density vector field is calculated through the difference matrix between adjacent time points. When the consistency of the magnetic flux density direction in adjacent areas decreases by more than 20% and the change rate is greater than 0.15T / ms, it is identified as a region with obvious nonlinear change of the magnetic field, and a distribution map of nonlinear change of the magnetic field is output.

[0051] Detecting the uneven growth of electromagnetic interference intensity based on the nonlinear changes in magnetic field distribution; In this embodiment of the invention, based on the aforementioned nonlinear magnetic field variation distribution map, the spatial discrete electromagnetic data is deconstructed using the Fourier time-frequency transform method to extract the distribution of non-stationary disturbance frequency band signals. Based on the density dispersion trend of the disturbance signal intensity in different frequency bands, it is determined whether the electromagnetic interference intensity exhibits a spatially uneven growth state. Specifically, the main harmonic interference signals within the frequency range of 10~1000kHz are selected, and the interference energy density of each node is normalized using a beam directivity factor. When the difference in electromagnetic interference energy density between adjacent devices exceeds 12dB, it is confirmed that the electromagnetic interference intensity is growing unevenly.

[0052] The superposition trend of harmonic components in power output is determined based on the uneven growth of electromagnetic interference intensity. In this embodiment of the invention, based on the uneven growth of electromagnetic interference intensity and the frequency spectrum of the disturbance signal, a frequency superposition trend analysis algorithm is used to evaluate the superposition trend of harmonic components in the output power. By retrieving transient harmonic response data of the power equipment, the total harmonic distortion (THD) of the first five harmonics is extracted, and its coupling characteristics with the fundamental frequency are analyzed. When the THD value increases by more than 1.5% for two consecutive cycles and the proportion of high-frequency harmonics (>500Hz) shows a significant upward trend, it is determined that there is a superposition trend of harmonic components in the power output.

[0053] Predicting the diffusion effect of feedback disturbance in power output based on the superposition trend of harmonic components in power output and the uneven growth of electromagnetic interference intensity. In this embodiment of the invention, based on the superposition trend of harmonic components in power output and the uneven growth of electromagnetic interference intensity, a disturbance propagation causal propagation map is constructed to accurately trace the propagation trajectory of the disturbance source in the power system after its generation. This map is based on the connection relationships between power equipment and incorporates their spatial distribution in the BIM 3D structure for topological encoding, forming a complete node network mapping structure. On this basis, time-series response data of voltage, current, and high-frequency disturbance energy of each key node are extracted. A continuous wavelet transform algorithm is used to extract high-frequency components and calculate frequency band energy, identifying the frequency domain characteristic change trend after the disturbance occurs. Subsequently, a feedback disturbance propagation path identification algorithm based on the principle of maximum information flow is invoked. The specific process includes: initiating an information flow at the disturbance source node, defining a propagation flux function based on the physical connection weight, electrical coupling strength, and time series similarity between nodes, maximizing the propagation flow along the topology, and searching for the set of paths with the largest information flow in the entire network; secondly, for each node in these paths, calculating the signal response synchronization index between it and the upstream node, if the synchronization decrease between any two nodes is greater than 10%, the average delay change value of the response signal is higher than 8ms, and the average frequency band energy spread value corresponding to the path segment exceeds 20%, then the path is determined to be an effective disturbance feedback diffusion path; finally, all paths that meet the above conditions are integrated into the disturbance diffusion causal propagation map, and highlighted in the BIM visualization environment using color grading, while labeling the path number, propagation direction, key node location, frequency band energy change value, and response delay and other index parameters.

[0054] The growth trend of power output fluctuations is determined based on the diffusion effect of power output feedback disturbances. In this embodiment of the invention, after confirming the existence of the power output feedback disturbance diffusion effect, the potential impact of disturbance diffusion on the overall power output fluctuation trend is quantitatively estimated based on the propagation intensity, propagation path length, and number of path coupling nodes from the disturbance source to each output node. A disturbance diffusion path index table is established, which includes the starting node, terminal node, path length (in terms of the number of transmission nodes), coupling intensity of nodes along the path, propagation delay duration, and disturbance intensity attenuation factor for each path. Subsequently, by retrieving the voltage sampling data sequence of each output port in the disturbance-affected area, with a sampling time interval of no more than 1 second, the difference between the maximum and minimum voltage values ​​of each output port within a unit time (with a period of 5 minutes) is calculated to determine the voltage fluctuation range. Simultaneously, the standard deviation of the voltage data for each period is calculated based on the sliding window method, and the rate of change of the standard deviation within consecutive periods is calculated to obtain the dynamic evolution trend of voltage fluctuation under the influence of disturbance for each port. If, within three consecutive 5-minute periods, the rate of change of the standard deviation of the voltage at a given output port exceeds 2%, and the average increase in the voltage fluctuation range exceeds ±15V (relative to the baseline period before the disturbance), it is determined that the port exhibits a decreasing stability trend, confirming the formation of a power output fluctuation growth trend. This determination not only records the specific range of voltage fluctuation changes but also simultaneously records the disturbance propagation path number, the corresponding output node number, the associated feedback disturbance source characteristics, and the propagation impact range within the determination period, used to generate a fluctuation growth trend assessment report. All output ports meeting the fluctuation growth trend determination criteria will be visually identified in the BIM power simulation model and uniformly summarized into the "Power Output Fluctuation Growth Trend Dataset".

[0055] Based on the growth trend of power output fluctuations and the diffusion effect of power output feedback disturbances, a normal distribution analysis of power output is performed to obtain normal distribution data of power output fluctuations. In this embodiment of the invention, when conducting a normal distribution analysis of power output based on the power output fluctuation growth trend and the power output feedback disturbance diffusion effect, the target variables need to be clearly defined as the time series fluctuation values ​​of power output voltage and current. By extracting voltage and current amplitude change data every 5 minutes over the most recent 72 consecutive hours from the power output fluctuation growth trend curve obtained in the previous stage, and combining this with the output waveform morphology variation rate data recorded in the feedback disturbance diffusion effect, a statistical distribution fitting technique is used to test the normality of this type of fluctuation. Specifically, the Shapiro-Wilk test and the Anderson-Darling test are used, two types of normality statistical methods. By calculating the skewness coefficient and kurtosis index of the original fluctuation sample, it is determined whether it follows a Gaussian distribution. When the skewness is greater than 0.8 or the kurtosis is greater than 3.5, it is considered that there is a significant normality shift. To quantify the degree of normality deviation, a standard normal distribution model is constructed using the mean (μ) and standard deviation (σ) as core parameters. The actual fluctuation data is then Z-normalized. The degree of deviation is assessed by comparing the Kullback-Leibler divergence between the standard distribution curve and the actual frequency distribution curve. If the divergence exceeds 0.15, the power output is considered to have a non-standard normal distribution. The resulting "Power Output Fluctuation Normal Distribution Data," which includes skewness, kurtosis, Z-score distribution maps, and a divergence coefficient matrix, is used as input in the subsequent grid output skewness drift identification process.

[0056] Determine the offset of the normal distribution of power fluctuations based on the normal distribution data of power output fluctuations; In this embodiment of the invention, when performing normal distribution analysis of power output, the power output fluctuation growth trend data and power output feedback disturbance diffusion effect data obtained in the previous stage are jointly input into the normal distribution analysis module. This module employs an embedded data preprocessing mechanism and fluctuation pattern discrimination process. The input data includes the voltage and current time series recorded by each power output node within a specified operating cycle, while the feedback disturbance diffusion effect data includes parameters such as disturbance source location, disturbance diffusion direction, propagation range, and propagation delay. Before analysis, the voltage and current series undergo preliminary processing, including outlier removal, missing value completion, and normalization to ensure analysis consistency. Then, the Shapiro-Wilk normality test method is used to identify the statistical distribution pattern of the voltage and current data of each power node. For each node, the overall distribution pattern of its waveform data within a given time period is calculated, focusing on two statistical indicators: skewness and kurtosis, i.e., assessing the symmetry of the data distribution and the sharpness of the peaks. If the analysis results show that the absolute value of the skewness of a node exceeds 0.8, or the kurtosis value exceeds 3.5, the power output data of that node is determined to no longer conform to the normal distribution characteristics. During the determination process, all data nodes deviating from the normal distribution standard will be automatically identified and output to the "Power Output Fluctuation Normal Distribution Data" set. This dataset specifically includes the abnormal node number, time window information, voltage or current data type, skewness value, kurtosis value, normality test statistics, and the classification results based on the judgment criteria. This data will then be linked to the power engineering BIM 3D spatial structure, generating visual markers at the corresponding node locations in the power grid 3D model. This displays the spatial distribution and statistical anomaly characteristics of power output fluctuations in a layered overlay format, providing complete and quantitative data support for subsequent identification of power fluctuation deviations and detection of skewed distribution drift.

[0057] The skewed distribution drift of the power grid output is detected based on the deviation of the normal distribution of power fluctuations and the diffusion effect of power output feedback disturbances.

[0058] In this embodiment of the invention, after identifying the normal distribution deviation of power output fluctuations, based on the deviation and the previously obtained path data of power output feedback disturbance diffusion effects, the identification and processing of the skewed distribution drift state of the power grid output is carried out. By performing node-level spatial positioning on the power fluctuation normal distribution deviation results, all abnormal deviation nodes are mapped to the three-dimensional BIM power engineering simulation model, and an influence chain between nodes is established based on the calibrated disturbance diffusion propagation path data. This chain clarifies the deviation response transmission relationship, propagation direction, and propagation lag time between each node and its preceding and following neighboring nodes. Subsequently, based on this chain relationship, the entire power grid output structure is spatially partitioned, and a skewed drift clustering identification algorithm is used to perform cluster identification and analysis on the output node data. The analysis target is the voltage or current output endpoints of each outgoing circuit of the power grid, specifically taking the substation as the clustering unit, and independently identifying the ports of its outgoing circuits. This clustering identification process introduces multi-dimensional indicators such as voltage deviation direction consistency, deviation magnitude, deviation duration, and spatial propagation path overlap rate as clustering factors. The judgment criteria are set as follows: when at least three ports in any substation's outgoing circuit exhibit unidirectional offset (i.e., positive or negative offset), and these ports are connected by disturbance propagation paths, forming a continuous propagation link, and the average skew drift value of each node in the resulting skewed region exceeds a set threshold (the threshold is defined as the percentage of time periods with voltage offset exceeding ±10V exceeding 0.2%), then the region is automatically determined to have a grid output skewed distribution drift state. This state is recorded in the grid output skewed distribution drift state result set, and a detailed drift structure diagram is output, indicating the offset node location, propagation path, offset direction, and duration. A set of data feature indicators is also generated, including parameters such as the maximum offset value, average offset rate, drift duration period, and propagation delay with upstream disturbance nodes for each node, to support subsequent anomaly analysis and risk warning model invocation for grid operation.

[0059] Preferably, step S3 includes the following steps: Step S31: Estimate the intensification of electrical shocks in power engineering based on the drift state of the skewed distribution of the power grid output; In this embodiment of the invention, the power grid output skewness distribution drift data generated in step S2 is called to estimate the enhanced electrical impact condition of the power project based on the power grid output skewness distribution drift state. This data includes node voltage offset values, current fluctuation frequency change data, and the corresponding node's skewness index and extreme value amplitude. By constructing a node electrical response evolution function, the node voltage mutation rate and power output slope fluctuation range per unit time are calculated. It is then determined whether the maximum voltage change exceeds 15V and the current fluctuation frequency increase exceeds 10Hz within 5 minutes. If the above boundary conditions are met, it is determined that an enhanced electrical impact state exists at that node. The corresponding timestamp, node number, voltage mutation slope value, and power change amplitude are output as enhanced electrical impact condition data for use in step S32.

[0060] Step S32: Determine the nonlinear load growth of the power grid lines based on the intensification of electrical impulses in the power engineering. In this embodiment of the invention, based on the electrical impact enhancement data output in step S31, the degree of impact on the nonlinear load of the power grid lines is further analyzed. Real-time power transmission data and historical operating load curves of the power grid lines are acquired, and the load change trends of the lines within the same time period before and after the impact are compared. A load growth index calculation method is used: the rate of change of line load power per unit time is divided by its historical average. If the growth index is greater than 1.2 for three consecutive periods, it is determined that the line has experienced nonlinear load growth. Simultaneously, the line number, load growth index value, and the time period of nonlinear growth are extracted as data on the nonlinear load growth of the power grid lines, providing input for step S33.

[0061] Step S33: Predict the aggravation of power equipment losses based on the nonlinear load growth of power grid lines and the intensification of electrical impacts in power engineering. In this embodiment of the invention, the aggravation of power equipment losses is jointly assessed based on the aforementioned nonlinear load growth and increased electrical impact. Typical equipment such as transformers, circuit breakers, and switchgear connected to the nonlinear load line are selected, and the number of current switching operations, conductor temperature rise, and infrared thermal images of the equipment surface are collected within 24 hours before and after the load increase. The collected temperature rise data is compared with the equipment's rated heat dissipation capacity parameters. If the temperature rise increases by more than 15%, the equipment's heat dissipation pressure is determined to be increased; if the switching frequency increases by more than 20%, the contact wear rate is determined to be accelerated. The temperature rise increase ratio, the switching frequency increase ratio, and the proportion of high-temperature areas in the thermal image are used as quantitative indicators of aggravated equipment losses and output to step S34 for use.

[0062] Step S34: Determine the fatigue aggravation status of power engineering equipment based on the aggravation status of power engineering equipment losses and the nonlinear load growth of power grid lines.

[0063] In this embodiment of the invention, the fatigue level of equipment is quantified by correlating the power equipment loss aggravation data output in step S33 with the line nonlinear load growth data in step S32. During the analysis, the equipment loss indicators are uniformly normalized, and a comprehensive evaluation function for equipment fatigue indicators is constructed. This function uses parameters such as a temperature rise index weight of 0.4, a switching frequency weight of 0.3, and a thermal image abnormal hot zone proportion weight of 0.3 to score the fatigue level of all equipment. If the comprehensive fatigue score of a certain piece of equipment exceeds 0.75, and the load growth index of the corresponding connected line remains above 1.2 for more than four cycles, then the equipment is confirmed to be in a state of accelerated fatigue. The fatigue aggravation results are output, including the equipment number, fatigue score, fatigue duration, corresponding line number, and load growth index, providing a basis for subsequent risk warning and maintenance planning.

[0064] Preferably, step S31 includes the following steps: Step S311: Determine the dynamic weakening of grid stability based on the grid output skew distribution drift state; In this embodiment of the invention, determining the dynamic weakening of grid stability based on the grid output skewness distribution drift requires collecting time-series data of key parameters such as voltage and current during actual grid operation, and continuously sampling the grid output waveform using high-precision power monitoring equipment. For the collected grid output data, skewness distribution drift features are extracted, and skewness indices of the voltage waveform, including skewness and kurtosis, are calculated using statistical analysis methods. The difference between the current data and historical benchmark data is compared to determine the degree of drift. Furthermore, using the quantitative indices of skewness drift combined with dynamic system theory, a time-series analysis model of grid stability is constructed. Based on this model, it is determined whether there is a gradual downward trend in grid stability. In this determination process, a method combining frequency domain analysis and time domain response characteristics is used. Multi-band filters separate different frequency components of the grid signal, assessing the attenuation of low-frequency components and their impact on stability, outputting quantitative indices of dynamic weakening of grid stability for input in subsequent steps.

[0065] Step S312: Detect the loss of the grid's steady-state balance capability based on the dynamic weakening of grid stability; In this embodiment of the invention, the loss of steady-state balance capability of the power grid is detected based on the dynamic weakening of power grid stability. Specifically, the operation includes analyzing the quantitative index of dynamic weakening of power grid stability output in step S311 in conjunction with the steady-state operating point data of the power grid. A steady-state operating model of the power grid is established by real-time acquisition of load current and node voltage data, and the power balance error of each node is calculated. The trend of error change is monitored over time; if the power balance error continuously increases, it indicates a weakening of the steady-state balance capability of the power grid. A nonlinear dynamics method is used to evaluate the system's response elasticity under current load conditions, and a static margin index is calculated. By comparing this index with a set safety threshold, it is determined whether the steady-state balance capability has been lost. This detection result forms steady-state balance capability decay status data, which serves as the basis for estimating the power grid's suppression and buffering capacity in the next step.

[0066] Step S313: Estimate the attenuation of the grid's suppression and buffering capacity based on the loss of the grid's steady-state balance capability and the dynamic weakening of grid stability; In this embodiment of the invention, the attenuation of the grid's suppression and buffering capacity is estimated based on the loss of the grid's steady-state balance capability and the dynamic weakening of grid stability. During implementation, steady-state balance capability loss data from step S312 and dynamic stability weakening indicators from step S311 are acquired. A grid electrical characteristic model is established by combining the physical parameters such as capacitance and inductance of each major node in the grid, and time response analysis is used to simulate the buffering response behavior of the grid under disturbance conditions. The changing trend of the grid's suppression and buffering capacity is quantified using the measured node voltage fluctuations and current harmonic content. The damping ratio of key nodes and its change over time are calculated; if the damping ratio is lower than a preset threshold, it indicates a significant attenuation of the buffering capacity. Based on the above analysis, grid suppression and buffering capacity attenuation data is generated as input for subsequent voltage burst growth trend detection.

[0067] Step S314: Detect the sudden increase trend of grid voltage based on the attenuation of grid suppression and buffering capacity; In this embodiment of the invention, the sudden voltage surge trend of the power grid is detected based on the attenuation of the power grid's suppression and buffering capacity. Specifically, the method involves real-time acquisition of voltage signals from key nodes in the power grid and the use of high-frequency sampling technology to capture voltage surge events. Combined with the attenuation data of the suppression and buffering capacity obtained in step S313, the amplitude and frequency characteristics of voltage fluctuations are analyzed. A threshold judgment method is used to compare the voltage fluctuation amplitude with the historical maximum normal fluctuation range. If it exceeds a set threshold and is consistent with the attenuation trend of the buffering capacity, a sudden voltage surge trend is determined. Through a trend analysis algorithm, the voltage growth rate and duration are calculated to generate a sudden voltage surge trend index, which is used for the next step of estimating the intensification of electrical shock conditions.

[0068] Step S315: Estimate the intensity of electrical shocks in power engineering based on the sudden increase trend of grid voltage.

[0069] In this embodiment of the invention, the intensification of electrical shocks in power engineering is estimated based on the sudden increase trend of grid voltage. The operation process includes inputting the sudden increase trend data of voltage and the load change information during grid operation in step S314. Using an electrical shock evaluation model, the instantaneous impact of rapid voltage fluctuations on power equipment and systems is analyzed, and the shock energy and its transmission path are calculated. Combining the rated load-bearing capacity of the equipment and the frequency of electrical shocks, an electrical shock intensity index is quantified. This index reflects the degree of electrical shock intensification and serves as an important parameter for subsequent equipment fatigue and risk assessment in power engineering, outputting electrical shock intensification data to support comprehensive monitoring and risk early warning in digital visualization supervision of power engineering.

[0070] Of particular importance, step S32 includes the following steps: Step S321: Determine the degree of electrical shock energy accumulation based on the intensification of electrical shock in power engineering; In this embodiment of the invention, an analysis of the intensification of electrical shock in power engineering is performed. Based on the time-varying periods of rapid voltage rise and current amplitude fluctuation in the cable line, it is determined whether there are energy-intensive behavioral units in the electrical shock process. When the voltage product exceeds 800V and a gradual current exceeding 80A undergoes a rapid change within 30ms, an electrical shock energy accumulation state can be determined. Simultaneously, based on the input voltage pattern classification values ​​(such as current-time function and capacitance shrinkage value) and the distribution of the affected area in the database, the system outputs data on the degree of electrical shock energy accumulation, thereby providing an entry point for subsequent thermal oscillation analysis and loss estimation.

[0071] Step S322: Determine the magnitude of the increase in line current fluctuation based on the nonlinear load growth of the power grid lines; In this embodiment of the invention, the input current output time data of all major operating circuits in the power engineering are used to perform difference analysis and amplitude statistics on the current input and output waveforms of each node within the same time period, calculating the fluctuation coefficient and fluctuation amplitude. When the coefficient ratio exceeds 1.2 and the amplitude increases by more than 20% compared to the past time period, it is diagnosed as a significant increase in line current fluctuation. By focusing on the analysis of the difference between the maximum cable current and the connection current at the switching point, a dataset corresponding to the fluctuation amplitude index of the operating node is obtained, providing a real-time benchmark for subsequent heat loss assessment.

[0072] Step S323: Estimate the increase in thermal fluctuation of power engineering equipment based on the magnitude of line current fluctuation and the degree of electrical intermediate energy accumulation; In this embodiment of the invention, based on the timed acquisition of current waveform expansion sequences and voltage series, the analysis focuses on the impact of changes exceeding a certain threshold on system temperature. Furthermore, through statistical analysis of the correlation between power consumption processing time and user time periods, thermal oscillations are analyzed to form quantitative indicators. When the thermal oscillation data shows a significant time-dependent increase and internal coordinate hotspots, the thermal oscillation growth of the equipment is determined, laying the foundation for further analysis of subsequent heat loss.

[0073] Step S324: Detect the local heat loss of the power engineering project based on the growth of thermal fluctuations in the power engineering equipment; In this embodiment of the invention, the diagnosed thermal oscillation growth area is analyzed for heat loss in a fixed region based on the actual equipment distribution structure and sampling level in the scenario. The focus is on monitoring the energy overflow heat value and thermal image mapping comparison value at connection points, seams, and tortuous lines. When the temperature difference exceeds 15°C and the mapped area shows visible directionality, it is diagnosed as a localized heat loss situation, providing a benchmark for subsequent analysis of increased total power loss.

[0074] Step S325: Determine the nonlinear load growth of the power grid lines based on the local heat loss of the power engineering project and the heat fluctuation growth of the power engineering equipment.

[0075] In this embodiment of the invention, the local heat loss data obtained in step S324 and the heat fluctuation growth data obtained in step S323 are subjected to bivariate spatial superposition analysis. Specifically, each equipment component is used as a spatial carrier to establish a "heat fluctuation-heat loss" coupled index matrix. When the same component simultaneously exhibits a heat fluctuation rate greater than the previous average by 20% and a heat loss power increase of more than 10W within the same time period, it is determined that the component is in the nonlinear amplification stage of load stress. Subsequently, combined with the cable connection path information in the BIM platform, the propagation path from the hot component to the upstream load is deduced to identify whether there is a cascading diffusion trend. When multiple series-connected devices exhibit the above characteristics, it is determined that the current load on the path is in a nonlinear growth trend. The nonlinear load growth of the power grid line is output, including the line number, abnormal component path, heat loss value of each component and its heat fluctuation rate, for subsequent equipment fatigue state assessment steps.

[0076] Of particular importance, step S34 includes the following steps: Step S341: Determine the deterioration status of the metal structure of the power engineering project based on the aggravated losses of power engineering equipment and the nonlinear load growth of power grid lines; In this embodiment of the invention, the data on "equipment thermal fluctuation growth," "local heat loss," and "line nonlinear load growth" output in steps S323 and S325 are read. For each equipment connection component (such as busbar clamps, steel supports, connecting bolts, etc.), the correlation strength between the maximum heat loss value of the connected cable or busbar and the load current fluctuation value is analyzed. The heat loss power, temperature wave growth slope, and connection line current fluctuation amplitude of each component are compared with the time sequence in a tabular manner, and the synchronous increase data of the changes during the same period are extracted. The results are input into the equipment library, and a thermo-mechanical integrated feature matching is established by using the component material properties (such as the fatigue limit of steel, coefficient of thermal expansion) and the thermal stress increment curve. If the same connection component shows a synchronous change phenomenon of heat loss growth exceeding 10W and current amplitude growth exceeding 20% ​​within a specified period (e.g., 24 hours), it is determined that the component has entered the metal structure deterioration state, and the deterioration index of the component is output, including the degree of deterioration, component number, and timestamp.

[0077] Step S342: Determine the crack growth trend of the metal structure of the power engineering project based on the deterioration of the metal structure; In this embodiment of the invention, the list of deteriorated components and their corresponding deterioration indices determined in step S341 are retrieved. These deteriorated components are then subjected to non-destructive testing using an ultrasonic guided wave detector. The device scans along the length of the component or the surface of the weld, and acquires the waveform and intensity of the ultrasonic echo signal in real time. Based on the peak amplitude and time delay of the echo signal, the location and size of early microcracks in the component are deduced. Repeated testing of the same component at different time points yields crack length or area growth curves. If the test records show that the crack length increases by more than 0.1 mm / day (per day) or the crack projected area increases by more than 5 mm... 2 / D will generate a record of the crack growth trend and output the crack growth rate, crack initiation location coordinates and component number for subsequent deformation state detection.

[0078] Step S343: Detect the deformation of power equipment lines based on the crack growth trend of the metal structure in the power engineering. In this embodiment of the invention, for components where crack growth has been identified in step S342, deformation detection is performed using a laser rangefinder or a structural deformation sensor network. Fixed reflective tags are installed on the components, and a laser scanning device records the distance changes of the two ends and the center position along the crack in a spatial coordinate system, calculating the bending angle or offset of the component. If the average deformation exceeds 0.5mm over a 50mm length range, deformation is immediately determined; accordingly, a deformation data report is generated, including the deformation amount, deformation rate (mm / day), direction vector, and coordinates of the deformation area. This report is input into the BIM 3D model, highlighting the deformation area with deformation arrows or color anomalies to ensure accurate spatial mapping and provide a basis for stress condition analysis.

[0079] Step S344: Determine the stress growth status of the power line based on the deformation of the power line. In this embodiment of the invention, the deformation and deformation rate data obtained in step S343 are used, combined with the component's own cross-sectional information (such as section modulus, cross-sectional area, and moment of inertia) and material mechanical properties (such as Young's modulus and yield strength), to calculate the internal stress change value on the component using static stress calculation formulas. For example, the increase in bending stress caused by the change in deformation radius can be obtained by stress = E·deformation / radius of curvature; the torsional stress can be calculated using the maximum shear stress formula. The calculated stress value is compared with the allowable stress range of the component material. If the stress increase exceeds 15% of the original stress, it is recorded as a high-stress area, and the stress increase data, including the stress value increase (MPa), stress direction, component number, and time label, is output for fatigue assessment.

[0080] Step S345: Determine the fatigue aggravation status of power engineering equipment based on the stress growth status of power engineering lines and the crack growth trend of power engineering metal structures.

[0081] In this embodiment of the invention, the crack growth rate data from step S342 and the stress growth data from step S344 are correlated at the same component level. Fatigue parameters, such as the relative ratio between crack growth rate and stress fluctuation amplitude, are calculated for each cracked component. If the same component simultaneously meets the following conditions: crack growth rate greater than 0.1 mm / day; stress periodic change amplitude exceeding 10% of the increment; and cumulative stress cycle count exceeding 20% ​​of the expected fatigue limit value, then the equipment is determined to be in a state of fatigue aggravation. A fatigue aggravation dataset is output, including component number, crack growth rate, peak and valley stress amplitude, fatigue index value, detection time window, and spatial location number, and is synchronously visualized in the BIM 3D model, providing an accurate basis for risk assessment and maintenance planning.

[0082] Preferably, step S4 includes the following steps: Step S41: Predict the growth trend of equipment component failure based on the fatigue intensification status of power engineering equipment; In this embodiment of the invention, predicting the failure growth trend of power engineering equipment components based on the fatigue intensification status requires acquiring monitoring data related to fatigue intensification, including parameters such as stress, strain, temperature, and vibration during equipment operation. Sensor networks are used to collect these parameters in real time, and time-series data analysis techniques are used to calculate the cumulative fatigue value. Based on the cumulative fatigue value, fracture mechanics and material fatigue life theory are used to quantitatively assess the damage evolution process of key components. Combining historical equipment fault records and on-site monitoring data, probabilistic statistical methods are used to estimate the time window and growth rate of component failure. This prediction process, through a data-driven algorithm model, outputs parameters of the failure growth trend of equipment components, providing input data for subsequent detection of equipment functional response degradation, achieving a complete connection from fatigue indicators to failure trends.

[0083] Step S42: Detect the functional response degradation trend of power engineering equipment based on the failure growth trend of equipment components and the fatigue aggravation of power engineering equipment; In this embodiment of the invention, the functional response degradation trend of power engineering equipment is detected based on the damage growth trend of equipment components and the intensification of fatigue in power engineering equipment. Specifically, the operation includes analyzing the performance changes of key functional components of the equipment based on the damage growth trend parameters and cumulative fatigue values ​​obtained in step S41. Through signal processing technology, features are extracted from data such as operating vibration signals and current waveforms collected by equipment sensors to identify characteristic indicators of functional degradation. Combined with component damage models, the magnitude of response performance degradation at different fatigue stages is quantified. By constructing a functional state evolution curve of the equipment, the time-varying trend of functional response is tracked, the time nodes of significant functional response decline are identified, and the equipment functional response degradation trend data is output, providing basic data support for power engineering operation risk assessment.

[0084] Step S43: Assess the growth trend of power engineering operation risk based on the functional response degradation trend of power engineering equipment; In this embodiment of the invention, the growth trend of operational risks in power engineering is assessed based on the functional response degradation trend of power engineering equipment. Specifically, the equipment functional response degradation trend data output in step S42 is input, and combined with the overall operating parameters of the power engineering and environmental factors, the operational risks are dynamically assessed. A multi-dimensional risk analysis framework is adopted, combining the degree of equipment functional degradation with the importance indicators of key system nodes to calculate the potential impact of equipment failures on the overall operational safety of the power engineering. A risk probability distribution model is used to analyze the probability of system failures and the scope of accident spread caused by equipment functional degradation. Based on a historical risk event database, a risk growth trend prediction model is established using machine learning algorithms to predict future operational risk trends. The power engineering operational risk growth trend index is output as input for risk positioning, achieving a quantitative description of the risk situation.

[0085] Step S44: Based on the growth trend of power engineering operation risks, perform power engineering risk location processing to obtain power engineering risk location data, and upload it to the cloud platform for risk warning.

[0086] In this embodiment of the invention, power engineering risk location processing is performed based on the growth trend of power engineering operation risks to obtain power engineering risk location data, which is then uploaded to a cloud platform for risk warning. Specifically, the operation risk growth trend index output in step S43 is combined with the geospatial information of each piece of equipment in the power engineering project. Using spatial analysis technology and the three-dimensional geometric data of the BIM model, high-risk areas are accurately located. Geographic Information System (GIS) and BIM integration technology are used to complete the three-dimensional visualization of the risk areas. During the risk location processing, spatial overlay analysis is used to identify risk concentration areas and potential risk diffusion paths, generating detailed location data including risk level and risk category. This location data is transmitted to the cloud-based risk management platform in real time, enabling remote access and multi-terminal collaborative monitoring. Based on the received risk location data, the cloud platform triggers a multi-level risk warning mechanism, pushing risk information to relevant management systems to support timely countermeasures and ensure the safe operation of the power engineering project.

[0087] This invention also provides a BIM-based digital visualization monitoring system for power engineering projects, used to execute the BIM-based digital visualization monitoring method for power engineering projects as described above. The BIM-based digital visualization monitoring of power engineering projects includes: The model building module is used to acquire power engineering design data; collect the configuration status of power equipment in power engineering based on the power engineering design data; and build a three-dimensional simulation model of the power engineering based on the power engineering design data and the configuration status of power equipment. The skewed distribution drift detection module is used to detect the coupling disturbance deviation of power equipment based on the three-dimensional simulation model of power engineering; determine the gradient degradation characteristics of power output stability based on the coupling disturbance deviation of power equipment; and detect the skewed distribution drift state of the power grid output based on the gradient degradation characteristics of power output stability and the coupling disturbance deviation of power equipment. The fatigue aggravation determination module is used to determine the nonlinear load growth of power grid lines based on the drift state of the skewed distribution of power grid output; and to determine the fatigue aggravation status of power engineering equipment based on the nonlinear load growth of power grid lines. The risk warning module is used to detect the functional response decline trend of power engineering equipment based on the fatigue aggravation condition of the equipment; assess the growth trend of power engineering operation risk based on the functional response decline trend; perform power engineering risk location processing based on the power engineering operation risk growth trend, obtain power engineering risk location data, and upload it to the cloud platform for risk warning.

[0088] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the 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 invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A digital visualization monitoring method for power engineering based on BIM technology, characterized in that, Includes the following steps: Step S1: Obtain power engineering design data; collect information on the configuration of power equipment in the power engineering based on the power engineering design data; construct a three-dimensional simulation model of the power engineering based on the power engineering design data and the configuration of power equipment in the power engineering. Step S2: Detect the coupling disturbance deviation of power equipment based on the three-dimensional simulation model of power engineering; determine the gradient degradation characteristics of power output stability based on the coupling disturbance deviation of power equipment; detect the skewed distribution drift state of power grid output based on the gradient degradation characteristics of power output stability and the coupling disturbance deviation of power equipment. Step S3: Determine the nonlinear load growth of the power grid lines based on the skewed distribution drift state of the power grid output; determine the fatigue aggravation status of power engineering equipment based on the nonlinear load growth of the power grid lines; Step S4: Detect the functional response degradation trend of power engineering equipment based on the fatigue aggravation status of the power engineering equipment; Assess the growth trend of power engineering operation risk based on the functional response degradation trend of power engineering equipment; perform power engineering risk location processing based on the power engineering operation risk growth trend to obtain power engineering risk location data, and upload it to the cloud platform for risk warning.

2. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain power engineering design data; Step S12: Collect information on the configuration of power equipment in the power engineering project based on the power engineering design data; Step S13: Obtain the distribution of power engineering transmission lines based on power engineering design data; Step S14: Construct a three-dimensional simulation model of the power engineering based on the distribution of power engineering transmission lines and the configuration of power equipment in the power engineering.

3. The power engineering digital visualization supervision method based on BIM technology according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Determine the route of the power engineering lines based on the distribution of power engineering transportation lines; Step S142: Determine the distribution of power engineering connection nodes based on the distribution of power engineering transportation lines; Step S143: Construct the power transmission network topology based on the distribution of power engineering connection nodes and the route of power engineering lines; Step S144: Identify the operating mode data of power equipment based on the configuration status of power equipment in power engineering; Step S145: Evaluate the operating performance parameters of the power equipment based on the configuration status and operating mode data of the power equipment in the power engineering project; Step S146: Perform power engineering correlation matching processing on the power equipment operating performance parameters and the power transmission network topology to obtain power engineering correlation matching data; Step S147: Perform three-dimensional spatial mapping processing based on the power engineering correlation matching data to obtain the three-dimensional spatial mapping data of the power engineering; Step S148: Construct a three-dimensional simulation model of the power engineering based on the three-dimensional spatial mapping data of the power engineering and the operating performance parameters of the power equipment.

4. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S2, which involves detecting the coupling disturbance deviation of power equipment based on the three-dimensional simulation model of the power engineering, includes: Acquire power engineering operation log data, and collect power equipment operation disturbance parameters based on the power engineering operation log data; Based on the three-dimensional simulation model of power engineering, the collaborative evolution analysis between power equipment is carried out to obtain the collaborative relationship data between power equipment; When the inter-power equipment coordination relationship data exceeds 0.6, the multi-node interaction mechanism of power equipment is determined; Based on the operating disturbance parameters of power equipment, the full-process response evolution of power equipment is simulated according to the multi-node interaction mechanism of power equipment, and the full-process response evolution data of power equipment is obtained. Based on the whole process response evolution data of power equipment, the time series analysis of the response of power equipment nodes is carried out to obtain the time series data of power equipment node response. Extract the power equipment response delay distribution characteristics based on the power equipment node response time sequence data; Extract the amplitude variation trend of power equipment based on the time series data of power equipment node response; When the amplitude variation trend of power equipment exceeds ±30V, the multi-node cooperative disturbance propagation path data is determined based on the power equipment response delay distribution characteristics. Detection of coupling disturbance deviation in power equipment based on multi-node collaborative disturbance propagation path data.

5. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S2, which determines the gradient degradation characteristics of power output stability based on the coupling disturbance deviation of power equipment, includes: Determine the impact of abnormal power equipment status based on the coupling disturbance deviation of power equipment; Based on the coupling disturbance deviation of power equipment and the impact of abnormal power equipment status, the trend of power equipment performance degradation is estimated; When the performance degradation trend of power equipment is >1%, the reduction in the operating efficiency of power equipment is detected. The health status of power equipment is assessed when the performance degradation trend of power equipment and the reduction in power equipment operating efficiency exceeds 5%. Predict the growth trend of equipment failure frequency based on the decline in the operational health status of power equipment. The increasing trend of equipment failure frequency and the declining health status of power equipment are used to determine the increasing trend of equipment sudden accident risk. Determine the fluctuation status of power supply quality based on the increasing trend of equipment accident risk; The gradient degradation characteristics of power output stability are determined based on the fluctuation of power supply quality of power equipment.

6. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S2, which detects the grid output skewness distribution drift state based on the power output stability gradient degradation characteristics and the coupling disturbance deviation of power equipment, includes: The nonlinear variation of the magnetic field distribution is estimated based on the characteristics of the gradient degradation of power output stability and the coupling disturbance deviation of power equipment. Detecting the uneven growth of electromagnetic interference intensity based on the nonlinear changes in magnetic field distribution; The superposition trend of harmonic components in power output is determined based on the uneven growth of electromagnetic interference intensity. Predicting the diffusion effect of feedback disturbance in power output based on the superposition trend of harmonic components in power output and the uneven growth of electromagnetic interference intensity. The growth trend of power output fluctuations is determined based on the diffusion effect of power output feedback disturbances. Based on the growth trend of power output fluctuations and the diffusion effect of power output feedback disturbances, a normal distribution analysis of power output is performed to obtain normal distribution data of power output fluctuations. Determine the offset of the normal distribution of power fluctuations based on the normal distribution data of power output fluctuations; The skewed distribution drift of the power grid output is detected based on the deviation of the normal distribution of power fluctuations and the diffusion effect of power output feedback disturbances.

7. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Estimate the intensification of electrical shocks in power engineering based on the drift state of the skewed distribution of the power grid output; Step S32: Determine the nonlinear load growth of the power grid lines based on the intensification of electrical impulses in the power engineering. Step S33: Predict the aggravation of power equipment losses based on the nonlinear load growth of power grid lines and the intensification of electrical impacts in power engineering. Step S34: Determine the fatigue aggravation status of power engineering equipment based on the aggravation status of power engineering equipment losses and the nonlinear load growth of power grid lines.

8. The power engineering digital visualization supervision method based on BIM technology according to claim 7, characterized in that, Step S31 includes the following steps: Step S311: Determine the dynamic weakening of grid stability based on the grid output skew distribution drift state; Step S312: Detect the loss of the grid's steady-state balance capability based on the dynamic weakening of grid stability; Step S313: Estimate the attenuation of the grid's suppression and buffering capacity based on the loss of the grid's steady-state balance capability and the dynamic weakening of grid stability; Step S314: Detect the sudden increase trend of grid voltage based on the attenuation of grid suppression and buffering capacity; Step S315: Estimate the intensity of electrical shocks in power engineering based on the sudden increase trend of grid voltage.

9. The power engineering digital visualization supervision method based on BIM technology according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Predict the growth trend of equipment component failure based on the fatigue intensification status of power engineering equipment; Step S42: Detect the functional response degradation trend of power engineering equipment based on the failure growth trend of equipment components and the fatigue aggravation of power engineering equipment; Step S43: Assess the growth trend of power engineering operation risk based on the functional response degradation trend of power engineering equipment; Step S44: Based on the growth trend of power engineering operation risks, perform power engineering risk location processing to obtain power engineering risk location data, and upload it to the cloud platform for risk warning.

10. A digital visualization monitoring system for power engineering based on BIM technology, characterized in that, The method for implementing the BIM-based digital visualization supervision of power engineering as described in claim 1, wherein the BIM-based digital visualization supervision of power engineering includes: The model building module is used to acquire power engineering design data; collect the configuration status of power equipment in power engineering based on the power engineering design data; and build a three-dimensional simulation model of the power engineering based on the power engineering design data and the configuration status of power equipment. The skewed distribution drift detection module is used to detect the coupling disturbance deviation of power equipment based on the three-dimensional simulation model of power engineering; determine the gradient degradation characteristics of power output stability based on the coupling disturbance deviation of power equipment; and detect the skewed distribution drift state of the power grid output based on the gradient degradation characteristics of power output stability and the coupling disturbance deviation of power equipment. The fatigue aggravation determination module is used to determine the nonlinear load growth of power grid lines based on the drift state of the skewed distribution of power grid output; and to determine the fatigue aggravation status of power engineering equipment based on the nonlinear load growth of power grid lines. The risk warning module is used to detect the functional response decline trend of power engineering equipment based on the fatigue aggravation condition of the equipment; assess the growth trend of power engineering operation risk based on the functional response decline trend; perform power engineering risk location processing based on the power engineering operation risk growth trend, obtain power engineering risk location data, and upload it to the cloud platform for risk warning.

Images