Smart park building visual management method and system based on BIM technology

Abstract

The invention relates to a building model visualization technology, and discloses an intelligent park building visualization management method and system based on a BIM technology, and the method comprises the steps: collecting park building structure, equipment energy consumption and cable arrangement data through a sensor, building a BIM simulation model based on the data, the method comprises the following steps: generating a multi-level simulation model comprising an equipment topology layer and an energy consumption flow layer, constructing an equipment abnormal energy consumption identification map by combining equipment topology and energy consumption data, identifying a park abnormal energy consumption event and outputting an identification result according to the equipment abnormal energy consumption identification map, and if abnormity exists, performing equipment traceability and positioning a problem source according to abnormal point information and an energy consumption flow layer view. And finally, a control instruction is sent to source equipment determined by traceability through an Internet of Things interface, so that closed-loop management and control of abnormal energy consumption are realized. According to the invention, the efficiency and accuracy of equipment energy consumption abnormity identification in the target building can be improved.

Description

Technical Field

[0001] This invention relates to the field of building model visualization technology, and in particular to a smart park building visualization management method and system based on BIM technology. Background Technology

[0002] With the deepening development of smart city construction, refined energy management in smart parks has become a crucial issue for improving operational efficiency and achieving sustainable development. Currently, the industry's commonly used technical approach for monitoring and managing electricity consumption within parks is primarily based on a preliminary integration of Building Information Modeling (BIM) and the Internet of Things (IoT). Specifically, existing technologies typically involve deploying various sensors to collect energy consumption data and overlaying it onto a 3D BIM model for visualization, enabling monitoring of energy consumption by item, household, and time. Managers can intuitively view real-time energy consumption readings and historical curves for each area and device through a visual interface.

[0003] However, existing technologies have significant limitations in in-depth diagnosis and proactive management. For example, visualization functions are mostly limited to data display, simply mapping sensor readings to numerical values ​​or simple charts on a model, lacking in-depth analysis and visualization of the inherent correlations, propagation paths, and root causes of anomalies in energy consumption data. When abnormal energy consumption occurs, the system often only alarms and displays the abnormal value, unable to automatically trace the source of the anomaly and its impact path, resulting in low troubleshooting efficiency, reliance on manual experience, and reduced efficiency and accuracy in identifying abnormal energy consumption. Summary of the Invention

[0004] This invention provides a smart park building visualization management method and system based on BIM technology. Its main purpose is to solve the problem that existing smart park building visualization management methods cannot identify abnormal equipment energy consumption.

[0005] To achieve the above objectives, this invention provides a smart park building visualization management method based on BIM technology, comprising: The system acquires building structure data and equipment energy consumption data of the target park based on preset sensors, as well as cable layout data of the target park. Based on the building structure data, the equipment energy consumption data, and the cable layout data, BIM simulation is performed to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park. Based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, an abnormal energy consumption identification map of the equipment is constructed. Abnormal energy consumption events of the target park are identified according to the abnormal energy consumption identification map, and abnormal energy consumption event identification results are obtained. When it is determined that there is an abnormal energy consumption event in the target park based on the abnormal energy consumption event identification result, the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model are used to trace the abnormal energy consumption equipment and obtain the equipment tracing result. The device tracing results are mapped back to the device abnormal energy consumption identification map. Based on the causal connection weights and abnormal propagation probabilities in the device abnormal energy consumption identification map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source device in the device tracing results in the multi-level simulation model. The confidence and severity level of the tracing path are encoded by pulse intensity, color and frequency to perform visual-guided fault localization and obtain the localization result. A first control strategy and a second control strategy are generated based on the positioning results. The multi-level simulation model is used to perform dynamic simulation based on the first control strategy and the second control strategy to obtain the simulation results. The optimal strategy among the first control strategy and the second control strategy is confirmed based on the simulation results. Control commands are generated based on the optimal strategy, and then sent to the source device in the target park corresponding to the positioning result via a preset IoT interface.

[0006] Optionally, the acquisition of building structure data and equipment energy consumption data of the target park based on preset sensors includes: The point cloud data of the building structure of the target park is acquired using a preset three-dimensional laser sensor to obtain an initial point cloud dataset; The initial point cloud dataset is denoised to obtain a denoised point cloud dataset. The point cloud data in the denoised point cloud dataset is registered with a preset three-dimensional coordinate system to obtain the registered point cloud dataset. Energy consumption data of equipment in the target park is obtained based on the energy consumption sensor preset in each energy-consuming device; Location information for each energy consumption sensor is acquired via radio communication; The location parameters of each energy-consuming device are obtained based on the preset sensor-device mapping table and the location information of each energy-consuming sensor; The location information of the energy-consuming devices is added to the registered point cloud dataset based on the location parameters to obtain the building structure data.

[0007] Optionally, the step of performing BIM simulation based on the building structure data, the equipment energy consumption data, and the cable layout data to obtain a multi-level simulation model containing an equipment topology layer view and an energy consumption flow layer view of the target park includes: A BIM meta-model based on a semantic framework is constructed based on the building structure data, the equipment energy consumption data, and the cable layout data. The physical topology matrix between energy-consuming devices is constructed using the BIM meta-model based on the cable layout data; The BIM meta-model is used to generate a building structure layer view of the target park; Based on the physical topology matrix and the building structure layer view, a multi-level simulation model is constructed that includes the equipment topology layer view and energy consumption flow layer view of the target park.

[0008] Optionally, the step of constructing a multi-level simulation model containing a device topology layer view and an energy consumption flow layer view of the target park based on the physical topology relationship matrix and the building structure layer view includes: Construct the equipment topology layer view of the target park based on the physical topology relationship matrix and the building structure layer view; The hierarchical relationship between energy-consuming devices is identified based on the device energy consumption data and the physical topology matrix. Establish the energy flow relationship between energy-consuming devices based on the hierarchical relationship; Construct an energy consumption flow layer view of the target park based on the energy flow direction relationship and the physical topology relationship matrix; The building structure layer view, equipment topology layer view, and energy consumption flow layer view are integrated into the BIM meta-model to obtain a multi-level simulation model.

[0009] Optionally, the step of constructing a BIM meta-model based on a semantic framework according to the building structure data, the equipment energy consumption data, and the cable layout data includes: A semantic framework is constructed based on a pre-defined framework standard to obtain a standard semantic framework; The building structure data is semantically processed to obtain semantically encoded building structure data; Obtain the location data of energy-consuming equipment from the building structure data, and map the energy consumption data of the equipment to a preset BIM entity based on the location data of the energy-consuming equipment to obtain the equipment semantic model; Based on the physical connection relationships in the cable layout data, the energy transmission direction and topology between energy-consuming devices are extracted to obtain a cable semantic model. The semantic building structure data, the equipment semantic model, and the cable semantic model are integrated into the standard semantic framework to obtain the BIM meta-model.

[0010] Optionally, the construction of an abnormal energy consumption identification map based on the device topology layer view of the multi-level simulation model and the device energy consumption data includes: Obtain the operating status log of each energy-consuming device in the target park, and obtain the environmental data of the target park; A multi-dimensional feature matrix is ​​constructed by aligning the operating status log, the environmental data, and the device energy consumption data. Transform the device topology layer view into a device relationship diagram that includes the connection relationships between energy-consuming devices; An abnormal energy consumption identification map of devices is constructed based on the multi-dimensional feature matrix and the device relationship diagram.

[0011] Optionally, constructing an abnormal energy consumption identification map of devices based on the multi-dimensional feature matrix and the device relationship graph includes: Construct causal connection weights between energy-consuming devices in the device relationship graph based on the multi-dimensional feature matrix; Calculate the connection correlation between energy-consuming devices in the device relationship diagram based on the multi-dimensional feature matrix; Obtain historical anomaly data for each energy-consuming device in the target park, and calculate the anomaly propagation probability between energy-consuming devices in the device relationship diagram based on the historical anomaly data; Based on the causal connection weights, connection correlations, and anomaly propagation probabilities, causal connection edges, correlation connection edges, and anomaly propagation edges are constructed between energy-consuming devices in the device relationship graph, respectively, to obtain the device abnormal energy consumption identification map.

[0012] Optionally, the step of tracing the abnormal energy consumption devices based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model to obtain the device tracing result includes: Identify the abnormal event characteristics of the abnormal energy consumption event identification results; Generate a source tracing path table based on the energy consumption flow layer view; The abnormal sub-device is identified based on the abnormal energy consumption event identification results; Based on the abnormal sub-device and the source tracing path table, multi-level reverse tracing is performed to obtain a multi-level source tracing path tree; Identify the key nodes in the multi-level tracing path tree to obtain a list of key nodes; Based on the list of key nodes and the multi-level traceability path tree, trace the abnormal energy consumption equipment to obtain the equipment traceability results.

[0013] To address the aforementioned problems, the present invention also provides a smart park building visualization management system based on BIM technology, the system comprising: The data acquisition module is used to acquire building structure data and equipment energy consumption data of the target park based on preset sensors, as well as cable layout data of the target park; The model building module is used to perform BIM simulation based on the building structure data, the equipment energy consumption data and the cable layout data to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park. An anomaly identification module is used to construct an abnormal energy consumption identification map based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, identify abnormal energy consumption events in the target park according to the abnormal energy consumption identification map, and obtain abnormal energy consumption event identification results. The anomaly tracing module is used to trace the abnormal energy consumption equipment when an abnormal energy consumption event is determined to exist in the target park based on the abnormal energy consumption event identification result. This is done by tracing the abnormal energy consumption equipment based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model. The device tracing result is then mapped back to the device abnormal energy consumption identification map. Based on the causal connection weights and anomaly propagation probabilities in the device abnormal energy consumption identification map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source device in the device tracing result in the multi-level simulation model. The confidence level and anomaly severity level of the tracing path are encoded by pulse intensity, color, and frequency to perform visually guided fault location and obtain the location result. The instruction sending module is used to generate a first control strategy and a second control strategy based on the positioning result, perform dynamic simulation based on the first control strategy and the second control strategy using the multi-level simulation model to obtain the simulation result, confirm the optimal strategy among the first control strategy and the second control strategy based on the simulation result, generate control instructions based on the optimal strategy, and send the control instructions to the source device in the target park corresponding to the positioning result based on a preset IoT interface.

[0014] This invention provides a precise, multi-source data foundation for constructing a high-fidelity digital twin of a target park by acquiring building structure data, equipment energy consumption data, and cable layout data of the target park using preset sensors. Based on the building structure data, equipment energy consumption data, and cable layout data, BIM simulation is performed to obtain a multi-level simulation model containing a topology view and an energy flow view of the target park. This enables a visual understanding of the relationship between energy flow and equipment. An abnormal energy consumption identification map is constructed based on the equipment topology view and equipment energy consumption data of the multi-level simulation model. This integrates the physical connections between equipment, energy consumption causality, and historical anomaly patterns into a reasonable knowledge network, providing core support for intelligent diagnosis. Abnormal energy consumption events in the target park are identified based on the abnormal energy consumption identification map, yielding abnormal energy consumption event identification results. When an abnormal energy consumption event is determined to exist in the target park based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification results and the energy flow layer of the multi-level simulation model, further analysis is conducted. The system uses visual simulation to trace the source of abnormal energy consumption devices, improving fault diagnosis efficiency. The traceability results are mapped back to an abnormal energy consumption identification map. Based on the causal connection weights and anomaly propagation probabilities in the map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source device in the traceability results within a multi-level simulation model. The confidence level and severity of the anomaly are encoded by pulse intensity, color, and frequency to perform visually guided fault location, improving the accuracy of fault device location. A first and second control strategy are generated based on the location results. The multi-level simulation model dynamically extrapolates the first and second control strategies to obtain extrapolation results. The optimal strategy between the first and second control strategies is confirmed based on the extrapolation results, improving the stability of device operation in the target area. Control commands are generated based on the optimal strategy and sent to the source device corresponding to the location results in the target area via a preset IoT interface, improving the efficiency and accuracy of identifying abnormal energy consumption. Attached Figure Description

[0015] Figure 1 A flowchart illustrating a smart park building visualization management method based on BIM technology provided in an embodiment of the present invention; Figure 2 A functional module diagram of a smart park building visualization management system based on BIM technology provided in an embodiment of the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] This application provides a smart campus building visualization management method based on BIM technology. The executing entity of the BIM-based smart campus building visualization management method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the BIM-based smart campus building visualization management method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0019] Reference Figure 1 The diagram shown is a flowchart illustrating a BIM-based smart park building visualization management method according to an embodiment of the present invention. In this embodiment, the BIM-based smart park building visualization management method includes: S1. Based on preset sensors, acquire building structure data and equipment energy consumption data of the target park, as well as cable layout data of the target park.

[0020] In this embodiment of the invention, the preset sensor may include a three-dimensional laser sensor and an energy consumption sensor.

[0021] In this embodiment of the invention, acquiring building structure data and equipment energy consumption data of the target park based on preset sensors includes: The point cloud data of the building structure of the target park is acquired using a preset three-dimensional laser sensor to obtain an initial point cloud dataset; The initial point cloud dataset is denoised to obtain a denoised point cloud dataset. The point cloud data in the denoised point cloud dataset is registered with a preset three-dimensional coordinate system to obtain the registered point cloud dataset. Energy consumption data of equipment in the target park is obtained based on the energy consumption sensor preset in each energy-consuming device; Location information for each energy consumption sensor is acquired via radio communication; The location parameters of each energy-consuming device are obtained based on the preset sensor-device mapping table and the location information of each energy-consuming sensor; The location information of the energy-consuming devices is added to the registered point cloud dataset based on the location parameters to obtain the building structure data.

[0022] In detail, the process of acquiring point cloud data of the building structure of the target park using preset 3D laser sensors to obtain an initial point cloud dataset is achieved by deploying 3D laser sensors according to a preset scanning station location plan. Simultaneously, each scanning station ensures at least 30% overlap with adjacent stations. After scanning begins, the 3D laser sensors at each station sequentially complete a 360° panoramic scan, recording the 3D coordinates (X, Y, Z) and reflection intensity (I) of each laser reflection point. The raw scan data from each station is then transmitted to a preset central processing server via a local area network to form the initial point cloud dataset.

[0023] In detail, the denoising process of the initial point cloud dataset to obtain a denoised point cloud dataset is performed by applying a statistical outlier removal algorithm. A neighborhood search radius of 0.05 meters is set, and the average distance between each point in the initial point cloud dataset and its 50 nearest neighbors is calculated. Outliers (such as noise points caused by people or temporary obstacles) whose distances are more than three standard deviations from the mean are identified and removed using a pre-defined Gaussian distribution model. A radius filtering method is then used to identify and remove points with fewer than three points within a 0.02-meter radius as isolated noise. The remaining point cloud is then smoothed using moving least squares, fitting a local surface within a 0.03-meter neighborhood to eliminate scanning jitter errors, ultimately resulting in the denoised point cloud dataset.

[0024] In detail, the process of registering the point cloud data in the denoised point cloud dataset with a preset three-dimensional coordinate system to obtain a registered point cloud dataset involves establishing a global coordinate system with the center of the main entrance of the park as the origin (X-axis due east, Y-axis due north, Z-axis vertically upward). At least four control points with known global coordinates (such as building corners or permanent landmarks) are manually selected from the denoised point cloud dataset. Then, an iterative nearest-point algorithm is used for coarse registration. The rotation matrix and translation vector are calculated through singular value decomposition to initially align the point cloud data to the three-dimensional coordinate system. Next, based on the geometric features such as planes and edges extracted from the point cloud data, the Levenberg-Marquardt nonlinear optimization algorithm is used for fine registration to minimize the feature distance error. Finally, the solved precise transformation matrix is ​​applied to transform all the point cloud data to the preset three-dimensional coordinate system, resulting in a registered point cloud dataset with unified coordinates.

[0025] In detail, the acquisition of location information for each energy consumption sensor based on radio communication is achieved by deploying a positioning system within the park, setting up a positioning network covering the entire park with four or more positioning base stations. Each energy consumption sensor has a built-in positioning device that transmits a pulse signal at a frequency of 1Hz, and each base station calculates the signal propagation time using a time difference of arrival (TDOA) algorithm. The positioning engine receives the timestamp data from each base station and uses a trilateration algorithm to parse the location information of each energy consumption sensor.

[0026] In detail, the position parameters of each energy-consuming device are obtained according to the preset sensor-device mapping table and the position information of each energy-consuming sensor. The sensor-device mapping table clearly records the membership relationship between each energy-consuming sensor ID and the corresponding device ID. By obtaining the energy-consuming sensor ID, the corresponding device ID is found in the mapping table, and the measured coordinates of the energy-consuming sensor are used as the initial position value of the corresponding device.

[0027] In detail, the step of adding the location information of energy-consuming devices to the registered point cloud dataset according to the location parameters to obtain building structure data involves extracting the precise spatial coordinates of each energy-consuming device based on the location parameters, mapping the extracted precise spatial coordinates to the unified three-dimensional coordinate system of the registered point cloud dataset through a spatial transformation matrix, and using an octree-based spatial indexing algorithm to intelligently align and fuse the three-dimensional models of the devices with the corresponding point cloud regions, forming multi-level, interactive building structure data that simultaneously contains building geometry, spatial semantic information, and device distribution locations.

[0028] S2. Perform BIM simulation based on the building structure data, the equipment energy consumption data, and the cable layout data to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park.

[0029] In this embodiment of the invention, the step of performing BIM simulation based on the building structure data, the equipment energy consumption data, and the cable layout data to obtain a multi-level simulation model containing an equipment topology layer view and an energy consumption flow layer view of the target park includes: A BIM meta-model based on a semantic framework is constructed based on the building structure data, the equipment energy consumption data, and the cable layout data. The physical topology matrix between energy-consuming devices is constructed using the BIM meta-model based on the cable layout data; The BIM meta-model is used to generate a building structure layer view of the target park; Based on the physical topology matrix and the building structure layer view, a multi-level simulation model is constructed that includes the equipment topology layer view and energy consumption flow layer view of the target park.

[0030] In detail, the construction of a semantic framework-based BIM metamodel based on the building structure data, equipment energy consumption data, and cable routing data involves establishing a semantic framework extension system based on the IFC standard to define unified semantic labels and attribute templates for building components, equipment entities, and cable systems. The building structure point cloud data is identified as component entities such as walls, columns, and slabs using point cloud segmentation algorithms (such as RANSAC and region growing), and assigned IFC standard type labels. Each piece of equipment in the equipment energy consumption data is instantiated as an intelligent entity with dynamic attributes, including equipment ID, type, rated power, and real-time energy consumption. The cable routing data is converted into connection relationships in IFC using an automatic pipeline identification algorithm. Finally, these three types of data are uniformly encoded into the BIM metamodel.

[0031] In detail, the process involves constructing a physical topology matrix between energy-consuming devices using the BIM meta-model based on the cable layout data, extracting connection point data from the BIM meta-model and using these as nodes in the graph, and then establishing edges between nodes based on pipeline routing and connection relationships in the BIM meta-model. For the electrical system, a depth-first search algorithm is used to traverse the hierarchical structure of distribution boxes-circuit-equipment, ultimately generating the physical topology matrix.

[0032] In detail, generating the building structure layer view of the target park using the BIM meta-model involves extracting the geometric data and semantic attributes of building components from the BIM meta-model and constructing a three-dimensional visualization scene using a preset WebGL rendering engine.

[0033] In this embodiment of the invention, the step of constructing a multi-level simulation model containing a device topology layer view and an energy flow layer view of the target park based on the physical topology relationship matrix and the building structure layer view includes: Construct the equipment topology layer view of the target park based on the physical topology relationship matrix and the building structure layer view; The hierarchical relationship between energy-consuming devices is identified based on the device energy consumption data and the physical topology matrix. Establish the energy flow relationship between energy-consuming devices based on the hierarchical relationship; Construct an energy consumption flow layer view of the target park based on the energy flow direction relationship and the physical topology relationship matrix; The building structure layer view, equipment topology layer view, and energy consumption flow layer view are integrated into the BIM meta-model to obtain a multi-level simulation model.

[0034] In detail, the step of constructing the equipment topology layer view of the target park based on the physical topology relationship matrix and the building structure layer view involves spatially aligning the physical topology relationship matrix with the building structure layer view, and then superimposing the spatially aligned topology relationship matrix onto the building structure layer view.

[0035] In detail, the process of identifying the hierarchical relationship between energy-consuming devices based on the device energy consumption data and the physical topology matrix involves constructing a device energy transfer matrix T[i,j], where T[i][j] represents the proportion of energy flowing from device i to device j. Then, combining the actual power data and operating time of each device, the energy contribution of each device is calculated. A hierarchical clustering algorithm (such as AGNES clustering) is used to divide the devices into three levels: primary energy conversion devices (such as transformers), secondary distribution devices (such as distribution cabinets), and tertiary terminal devices (such as lighting fixtures and air conditioning terminals), ultimately yielding the hierarchical relationship between energy-consuming devices.

[0036] In detail, the establishment of the energy flow relationship between energy-consuming devices based on the hierarchical relationship is achieved by using the nodal voltage method to calculate the current direction of each power branch, summarizing the current directions of all energy-consuming devices in the same line, and obtaining the energy flow relationship.

[0037] In detail, the construction of the energy flow layer view of the target park based on the energy flow direction relationship and the physical topology relationship matrix is ​​an example of transforming the energy flow direction relationship into a dynamic visualization effect based on the equipment topology layer view. A preset particle system is used to simulate energy flow: each particle represents a certain unit of energy, and colors encode the energy type (yellow for electricity, blue for water, and red for heat). The particles move along the equipment connecting pipelines, with their speed proportional to the energy flow rate and their density proportional to the energy flow volume.

[0038] In this embodiment of the invention, the step of constructing a BIM meta-model based on a semantic framework according to the building structure data, the equipment energy consumption data, and the cable layout data includes: A semantic framework is constructed based on a pre-defined framework standard to obtain a standard semantic framework; The building structure data is semantically processed to obtain semantically encoded building structure data; Obtain the location data of energy-consuming equipment from the building structure data, and map the energy consumption data of the equipment to a preset BIM entity based on the location data of the energy-consuming equipment to obtain the equipment semantic model; Based on the physical connection relationships in the cable layout data, the energy transmission direction and topology between energy-consuming devices are extracted to obtain a cable semantic model. The semantic building structure data, the equipment semantic model, and the cable semantic model are integrated into the standard semantic framework to obtain the BIM meta-model.

[0039] In detail, the construction of the semantic framework based on the preset framework standard to obtain the standard semantic framework is achieved by selecting the general IFC (Industry Foundation Classes) standard as the foundation and extending it to meet the energy consumption management needs of the park. By defining an ontology model, the classes, attributes, and relationships of the building components, equipment, and pipeline systems of the target park are formalized. At the same time, attribute set templates are established to encapsulate the dynamic attributes and constraint rules of various entities, ultimately generating the standard semantic framework.

[0040] In detail, the semantic processing of the building structure data to obtain semantic building structure data involves using point cloud segmentation algorithms (such as PointNet++) to identify building point cloud data into component instances such as walls, columns, and floor slabs, and further subdividing the component types based on geometric features (such as area and height) using a preset rule engine. Subsequently, each component is assigned an IFC standard semantic label (such as IfcWall, IfcSlab), and its geometric parameters, material properties, and spatial location information are extracted. Simultaneously, a building spatial topology is constructed, and the adjacency and containment relationships between rooms and floors are established using the Delaunay triangulation algorithm, ultimately forming semantic building structure data with complete type definitions, attribute descriptions, and hierarchical relationships.

[0041] In detail, the semantic building structure data, the equipment semantic model, and the cable semantic model are integrated into the standard semantic framework to obtain a BIM metamodel. Redundant entities are eliminated through entity matching algorithms (based on GUIDs or spatial locations), and cross-model relationships are established (e.g., equipment installed in space, cables connected to equipment). Data consistency is verified using rules defined in the semantic framework, such as energy conservation checks and topological connectivity checks. Finally, the integrated BIM metamodel is obtained.

[0042] S3. Based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, construct an abnormal energy consumption identification map of the equipment. Identify abnormal energy consumption events of the target park according to the abnormal energy consumption identification map and obtain the abnormal energy consumption event identification result.

[0043] In this embodiment of the invention, the construction of an abnormal energy consumption identification map of the equipment based on the device topology layer view of the multi-level simulation model and the device energy consumption data includes: Obtain the operating status log of each energy-consuming device in the target park, and obtain the environmental data of the target park; A multi-dimensional feature matrix is ​​constructed by aligning the operating status log, the environmental data, and the device energy consumption data. Transform the device topology layer view into a device relationship diagram that includes the connection relationships between energy-consuming devices; An abnormal energy consumption identification map of devices is constructed based on the multi-dimensional feature matrix and the device relationship diagram.

[0044] In detail, the acquisition of the operating status logs of each energy-consuming device in the target park, as well as the acquisition of environmental data of the target park, is achieved by using the pre-set PLC controllers or smart gateways of each energy-consuming device to read the device's operating status logs at preset time intervals (e.g., 1 minute), including structured data such as start / stop status, operating mode, and load rate. Simultaneously, real-time environmental data, including indoor and outdoor temperature and humidity, light intensity, and CO2 concentration, is acquired through an environmental monitoring sensor network.

[0045] In detail, the step of aligning the operation status log, environmental data, and device energy consumption data to construct a multi-dimensional feature matrix involves aligning the operation status log, environmental data, and device energy consumption data over time, using the same time interval (e.g., 15 minutes) as a baseline, and employing linear interpolation to complete missing data. Then, multi-dimensional features are extracted for each energy-consuming device: statistical features (mean, variance, skewness, kurtosis), time-series features (autocorrelation coefficient, trend component), and frequency domain features (major frequency components) are extracted from the energy consumption data; state transition features (start / stop frequency, runtime) and operating condition features (load distribution) are extracted from the operation status log; and influencing factor features (temperature and humidity deviation, light intensity variation rate) are extracted from the environmental data.

[0046] In detail, the step of converting the device topology layer view into a device relationship graph containing the connection relationships between energy-consuming devices involves extracting the node and connection relationship data of the device topology layer view and converting it into a graph data structure.

[0047] In this embodiment of the invention, constructing an abnormal energy consumption identification map of devices based on the multi-dimensional feature matrix and the device relationship graph includes: Construct causal connection weights between energy-consuming devices in the device relationship graph based on the multi-dimensional feature matrix; Calculate the connection correlation between energy-consuming devices in the device relationship diagram based on the multi-dimensional feature matrix; Obtain historical anomaly data for each energy-consuming device in the target park, and calculate the anomaly propagation probability between energy-consuming devices in the device relationship diagram based on the historical anomaly data; Based on the causal connection weights, connection correlations, and anomaly propagation probabilities, causal connection edges, correlation connection edges, and anomaly propagation edges are constructed between energy-consuming devices in the device relationship graph, respectively, to obtain the device abnormal energy consumption identification map.

[0048] In detail, the step of constructing the causal connection weights between energy-consuming devices in the device relationship graph based on the multi-dimensional feature matrix involves using a vector autoregression model for the time series data of each pair of energy-consuming devices to examine whether the past value of one device has predictive power for the current value of another device, and calculating the causal strength. The direction of the causal connection edge is set from cause to effect, and the weight value is the causal strength.

[0049] In detail, the connection correlation between energy-consuming devices in the device relationship graph is calculated based on the multi-dimensional feature matrix. For each pair of devices, the multi-dimensional feature vector is first standardized, then the joint probability distribution and marginal probability distribution are calculated based on kernel density estimation, and then the mutual information value is calculated to obtain the connection correlation.

[0050] In detail, the step of obtaining historical abnormal data for each energy-consuming device in the target park and calculating the probability of abnormal propagation between energy-consuming devices in the device relationship diagram based on the historical abnormal data is to calculate the conditional probability that when one device experiences an abnormality in the historical abnormal data, the other device subsequently experiences an abnormality for each pair of adjacent energy-consuming devices.

[0051] In this embodiment of the invention, the step of identifying abnormal energy consumption events in the target park based on the abnormal energy consumption identification map and obtaining abnormal energy consumption event identification results involves comparing the equipment energy consumption data with the normal energy consumption behavior patterns and dynamic energy consumption thresholds defined in the abnormal energy consumption identification map, triggering initial anomaly detection based on rules and statistical models, and obtaining abnormal energy consumption event identification results.

[0052] S4. When it is determined that there is an abnormal energy consumption event in the target park based on the abnormal energy consumption event identification result, the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model are used to trace the abnormal energy consumption equipment and obtain the equipment tracing result.

[0053] In this embodiment of the invention, the step of tracing the abnormal energy consumption devices based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model to obtain the device tracing result includes: Identify the abnormal event characteristics of the abnormal energy consumption event identification results; Generate a source tracing path table based on the energy consumption flow layer view; The abnormal sub-device is identified based on the abnormal energy consumption event identification results; Based on the abnormal sub-device and the source tracing path table, multi-level reverse tracing is performed to obtain a multi-level source tracing path tree; Identify the key nodes in the multi-level tracing path tree to obtain a list of key nodes; Based on the list of key nodes and the multi-level traceability path tree, trace the abnormal energy consumption equipment to obtain the equipment traceability results.

[0054] In detail, the abnormal event features for identifying the abnormal energy consumption event identification results are obtained by reading all energy consumption point data marked as abnormal from the abnormal identification results, including the set of device IDs, the timestamp of the abnormal occurrence, the duration of the abnormality, and the abnormal intensity value (such as the percentage exceeding the benchmark).

[0055] In detail, the generation of the source tracing path table based on the energy consumption flow layer view is achieved by executing a graph traversal algorithm (such as breadth-first search), starting from each energy-consuming device node, searching along the opposite edge of the energy inflow direction (i.e., the reverse flow direction), and recording all possible "upstream device -> downstream device" path segments.

[0056] In detail, the multi-level reverse tracing based on the abnormal sub-device and the tracing path table to obtain a multi-level tracing path tree involves initiating an independent tracing process for each abnormal sub-device. Starting from the device ID, all its direct upstream devices are searched in the tracing path table, serving as the first-level parent nodes. Then, using these upstream devices as new starting points, the search continues to find their respective upstream devices, forming the second-level nodes. This process iterates repeatedly until the stopping condition is met: the park-level energy access point (such as the mains power connection point) is found.

[0057] In detail, the identification of key nodes in the multi-level tracing path tree and the acquisition of a key node list are achieved by: 1) calculating the number of other nodes connected to each device node to obtain a centrality index; 2) calculating the frequency of each device node appearing on any two tracing paths to obtain a mediating index; and 3) filtering out device nodes whose centrality index and mediating index are both greater than a preset threshold to obtain a key node list.

[0058] In this embodiment of the invention, the step of tracing abnormal energy consumption devices based on the key node list and the multi-level tracing path tree to obtain device tracing results includes: Based on the list of key nodes and the energy consumption data of the equipment, anomaly time series analysis is performed on each tracing path of the multi-level tracing path tree to obtain the time series analysis results; Based on the time series analysis results, the time series confidence of each tracing path in the multi-level tracing path tree is calculated. A preset number of tracing paths are selected from the multi-level tracing path tree in descending order of time series confidence to obtain a path set. Based on the abnormal energy consumption event identification results, the abnormal time point is confirmed, and detailed energy consumption data of each energy-consuming device at the abnormal time point is obtained from the device energy consumption data; Based on the detailed energy consumption data, the ratio of the total energy output by the upstream device to the total energy output by the downstream device at the abnormal time point in each path of the path set is calculated to obtain the abnormal contribution of each path. The path with the highest abnormal contribution is identified as the abnormal path, and the source device in the abnormal contribution is identified as the final device tracing result.

[0059] In detail, the step of performing anomaly time series analysis on each tracing path of the multi-level tracing path tree based on the key node list and the equipment energy consumption data to obtain time series analysis results involves extracting the complete path from each key node to the downstream abnormal device in the multi-level tracing path tree based on the key node list. For each extracted path, energy consumption time series data of all energy-consuming devices on the path are obtained within a specific time window before and after the occurrence of the abnormal event. Time series analysis methods are used to calculate the cross-correlation between the energy consumption sequences of upstream and downstream devices, identify whether there are significant correlation peaks and corresponding time lags, and statistically determine whether changes in the energy consumption of upstream devices can predict abnormal fluctuations in downstream devices. By analyzing the transmission time series of abnormal signals on the path, it is determined whether the abnormality follows a propagation order from upstream to downstream, and finally, time series analysis results containing the significance of time series relationships and time lag parameters are obtained.

[0060] In detail, the step of calculating the temporal confidence of each tracing path in the multi-level tracing path tree based on the temporal analysis results is to obtain the temporal confidence by weighted summation of the significance of the temporal relationship and the time lag parameter in the temporal analysis results.

[0061] S5. Map the device tracing results back to the device abnormal energy consumption identification map. Based on the causal connection weights and abnormal propagation probabilities in the device abnormal energy consumption identification map, initiate a dynamic pulse wave from the abnormal energy consumption point to the source device in the device tracing results in the multi-level simulation model. Then, use the pulse intensity, color, and frequency to encode the confidence level and abnormal severity level of the tracing path to perform visually guided fault location and obtain the location result.

[0062] In this embodiment of the invention, mapping the device tracing results back to the device abnormal energy consumption identification map, and based on the causal connection weights and abnormal propagation probabilities in the device abnormal energy consumption identification map, initiating a dynamic pulse wave from the abnormal energy consumption point to the source device in the device tracing results in the multi-level simulation model, involves extracting the corresponding nodes of the source device and the abnormal energy consumption point in the device tracing results in the abnormal energy consumption identification map. Then, along the direction of the causal connection edges in the abnormal energy consumption identification map, the optimal or highest probability propagation path from the source node to the abnormal node is searched and confirmed. Finally, in the three-dimensional space of the multi-level simulation model, the obtained propagation path is mapped to a specific geometric coordinate sequence, and a visual pulse wave is dynamically calculated and generated based on the causal weights and propagation probabilities of each segment on the path. The pulse wave takes the abnormal point as the visual starting point and is emitted sequentially and cyclically towards the source device along the pipeline or spatial path in the multi-level simulation model. Its propagation speed, halo width, and hue (e.g., from high-confidence red to low-confidence yellow) encode the causal strength and abnormal propagation risk level of the path segment in real time.

[0063] In this embodiment of the invention, the method of using pulse intensity, color, and frequency to encode the confidence level and severity level of the source tracing path for visual guidance to obtain the location result involves mapping the calculated source tracing path confidence level (e.g., 0.85) to the pulse wave intensity (high confidence corresponds to a strong halo), mapping the severity level of the abnormal event (e.g., "emergency") to the pulse wave color (e.g., red represents emergency, orange represents high risk), and mapping the urgency or historical frequency of the abnormal propagation to the pulse wave flashing frequency (e.g., high-frequency flashing indicates immediate action is required). Using a preset visual recognition model based on these dynamically encoded visual signals, the most reliable and severe abnormal propagation path can be intuitively identified, thereby quickly locating the physical equipment and pipelines that should be prioritized for investigation in the multi-level simulation model, and obtaining the location result.

[0064] S6. Generate a first control strategy and a second control strategy based on the positioning results. Use the multi-level simulation model to perform dynamic simulation based on the first control strategy and the second control strategy to obtain the simulation results. Confirm the optimal strategy among the first control strategy and the second control strategy based on the simulation results.

[0065] In this embodiment of the invention, the generation of the first control strategy and the second control strategy based on the positioning results involves calling a preset strategy knowledge base to generate two control strategies with different orientations, based on the source device, abnormal propagation path, and abnormal severity level confirmed by the positioning results: the first control strategy is a radical strategy, the core logic of which is to directly shut down or isolate the located source device to quickly cut off the abnormal energy consumption flow; the second control strategy is a regulatory strategy, the core logic of which is to intelligently adjust the upstream supply parameters (such as reducing the power supply voltage, reducing the water supply flow) or the operating status of downstream related devices (such as adjusting the air volume of the air conditioning terminal, shutting down non-critical circuits) of the source device based on the energy consumption flow layer view and the device topology layer view while maintaining the operation of the source device, thereby suppressing the abnormality while maintaining the local function of the system as much as possible.

[0066] In this embodiment of the invention, the dynamic simulation based on the first and second control strategies using the multi-level simulation model to obtain the simulation results involves loading the first and second control strategies as input conditions into the multi-level simulation model. A forward-looking simulation is then performed in a digital twin environment by calling an energy consumption calculation engine that integrates physical rules and historical data. The simulation process calculates and visualizes the dynamic energy consumption change curves of the entire affected system, the state sequences of key node devices, and the overall system stability indicators in real time, based on the energy transmission path in the energy flow layer view and the control association in the device topology layer view, within a set future time period (e.g., the next 2 hours) after implementing each strategy. The simulation results include the quantified value of the expected energy-saving effect corresponding to each strategy, the scope and degree of impact on system functions, and the estimated time required for the system to return to normal operation, providing a decision-making basis combining quantification and visualization for strategy optimization.

[0067] In this embodiment of the invention, the step of determining the optimal strategy among the first control strategy and the second control strategy based on the simulation results involves assigning differentiated weights to the various evaluation indicators (including expected energy saving value, system stability impact index, and estimated recovery time) in the simulation results for the first control strategy and the second control strategy, performing normalized scoring, calculating the comprehensive performance score of each of the first control strategy and the second control strategy, and selecting the strategy with the higher comprehensive score as the optimal strategy by comparing the comprehensive scores of the two strategies.

[0068] S7. Generate control commands according to the optimal strategy, and send the control commands to the source device in the target park corresponding to the positioning result based on the preset IoT interface.

[0069] In this embodiment of the invention, the step of generating control instructions based on the optimal strategy is to parse the type and specific parameters of the optimal strategy, and dynamically generate standardized structured control instruction data packets based on the target device identifier, control action (such as shutdown, adjustment) and set value specified in the strategy, combined with the communication protocol of the device in the Internet of Things (such as Modbus address, BACnet object identifier).

[0070] In this embodiment of the invention, the step of sending control commands to the source device in the target park corresponding to the positioning result based on a preset IoT interface is achieved by calling a preset IoT interface (such as MQTT Broker or Modbus TCP gateway) that matches the communication protocol of the source device. The generated structured control command data packet is then sent via a dedicated frequency band wireless network in the target park to the smart terminal or controller physically bound to the source device confirmed by the positioning result.

[0071] like Figure 2 The diagram shown is a functional module diagram of a smart park building visualization management system based on BIM technology provided in an embodiment of the present invention.

[0072] The BIM-based smart park building visualization management system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the BIM-based smart park building visualization management system 100 may include a data acquisition module 101, a model construction module 102, an anomaly identification module 103, an anomaly tracing module 104, and an instruction sending module 105. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0073] In this embodiment, the functions of each module / unit are as follows: The data acquisition module 101 is used to acquire building structure data and equipment energy consumption data of the target park based on preset sensors, as well as cable layout data of the target park. The model building module 102 is used to perform BIM simulation based on the building structure data, the equipment energy consumption data and the cable layout data to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park. The anomaly identification module 103 is used to construct an abnormal energy consumption identification map based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, identify abnormal energy consumption events in the target park according to the abnormal energy consumption identification map, and obtain abnormal energy consumption event identification results. The anomaly tracing module 104 is used to trace the abnormal energy consumption equipment when it is determined that there is an abnormal energy consumption event in the target park based on the abnormal energy consumption event identification result. This is done by tracing the abnormal energy consumption equipment based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model. The equipment tracing result is then mapped back to the abnormal energy consumption identification map. Based on the causal connection weights and anomaly propagation probabilities in the abnormal energy consumption identification map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source equipment in the equipment tracing result in the multi-level simulation model. The confidence level and anomaly severity level of the tracing path are encoded by pulse intensity, color, and frequency to perform visually guided fault location and obtain the location result. The instruction sending module 105 is used to generate a first control strategy and a second control strategy based on the positioning result, perform dynamic simulation based on the first control strategy and the second control strategy using the multi-level simulation model to obtain the simulation result, confirm the optimal strategy among the first control strategy and the second control strategy based on the simulation result, generate a control instruction based on the optimal strategy, and send the control instruction to the source device in the target park corresponding to the positioning result based on a preset Internet of Things interface.

[0074] In detail, the modules of the BIM-based smart park building visualization management system 100 described in this embodiment of the invention adopt the same usage as described above. Figure 1 The method used is the same as the BIM-based smart park building visualization management method described in the article, and can produce the same technical effects, so it will not be elaborated here.

[0075] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0076] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0078] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0079] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0080] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0081] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim may also be implemented by a single unit or system through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart park building visualization management method based on BIM technology, characterized in that, The method includes: The system acquires building structure data and equipment energy consumption data of the target park based on preset sensors, as well as cable layout data of the target park. Based on the building structure data, the equipment energy consumption data, and the cable layout data, BIM simulation is performed to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park. Based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, an abnormal energy consumption identification map of the equipment is constructed. Abnormal energy consumption events of the target park are identified according to the abnormal energy consumption identification map, and abnormal energy consumption event identification results are obtained. When it is determined that there is an abnormal energy consumption event in the target park based on the abnormal energy consumption event identification result, the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model are used to trace the abnormal energy consumption equipment and obtain the equipment tracing result. The device tracing results are mapped back to the device abnormal energy consumption identification map. Based on the causal connection weights and abnormal propagation probabilities in the device abnormal energy consumption identification map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source device in the device tracing results in the multi-level simulation model. The confidence and severity level of the tracing path are encoded by pulse intensity, color and frequency to perform visual-guided fault localization and obtain the localization result. A first control strategy and a second control strategy are generated based on the positioning results. The multi-level simulation model is used to perform dynamic simulation based on the first control strategy and the second control strategy to obtain the simulation results. The optimal strategy among the first control strategy and the second control strategy is confirmed based on the simulation results. Control commands are generated based on the optimal strategy, and then sent to the source device in the target park corresponding to the positioning result via a preset IoT interface.

2. The smart park building visualization management method based on BIM technology as described in claim 1, characterized in that, The acquisition of building structure data and equipment energy consumption data of the target park based on preset sensors includes: The point cloud data of the building structure of the target park is acquired using a preset three-dimensional laser sensor to obtain an initial point cloud dataset; The initial point cloud dataset is denoised to obtain a denoised point cloud dataset. The point cloud data in the denoised point cloud dataset is registered with a preset three-dimensional coordinate system to obtain the registered point cloud dataset. Energy consumption data of equipment in the target park is obtained based on the energy consumption sensor preset in each energy-consuming device; Location information for each energy consumption sensor is acquired via radio communication; The location parameters of each energy-consuming device are obtained based on the preset sensor-device mapping table and the location information of each energy-consuming sensor; The location information of the energy-consuming devices is added to the registered point cloud dataset based on the location parameters to obtain the building structure data.

3. The smart park building visualization management method based on BIM technology as described in claim 1, characterized in that, The BIM simulation based on the building structure data, equipment energy consumption data, and cable layout data yields a multi-level simulation model containing an equipment topology layer view and an energy consumption flow layer view of the target park, including: A BIM meta-model based on a semantic framework is constructed based on the building structure data, the equipment energy consumption data, and the cable layout data. The physical topology matrix between energy-consuming devices is constructed using the BIM meta-model based on the cable layout data; The BIM meta-model is used to generate a building structure layer view of the target park; Based on the physical topology matrix and the building structure layer view, a multi-level simulation model is constructed that includes the equipment topology layer view and energy consumption flow layer view of the target park.

4. The smart park building visualization management method based on BIM technology as described in claim 2, characterized in that, The construction of a multi-level simulation model based on the physical topology matrix and the building structure layer view, including the equipment topology layer view and energy consumption flow layer view of the target park, includes: Construct the equipment topology layer view of the target park based on the physical topology relationship matrix and the building structure layer view; The hierarchical relationship between energy-consuming devices is identified based on the device energy consumption data and the physical topology matrix. Establish the energy flow relationship between energy-consuming devices based on the hierarchical relationship; Construct an energy consumption flow layer view of the target park based on the energy flow direction relationship and the physical topology relationship matrix; The building structure layer view, equipment topology layer view, and energy consumption flow layer view are integrated into the BIM meta-model to obtain a multi-level simulation model.

5. The smart park building visualization management method based on BIM technology as described in claim 2, characterized in that, The step of constructing a BIM meta-model based on a semantic framework using the building structure data, the equipment energy consumption data, and the cable layout data includes: A semantic framework is constructed based on a pre-defined framework standard to obtain a standard semantic framework; The building structure data is semantically processed to obtain semantically encoded building structure data; Obtain the location data of energy-consuming equipment from the building structure data, and map the energy consumption data of the equipment to a preset BIM entity based on the location data of the energy-consuming equipment to obtain the equipment semantic model; Based on the physical connection relationships in the cable layout data, the energy transmission direction and topology between energy-consuming devices are extracted to obtain a cable semantic model. The semantic building structure data, the equipment semantic model, and the cable semantic model are integrated into the standard semantic framework to obtain the BIM meta-model.

6. The smart park building visualization management method based on BIM technology as described in claim 1, characterized in that, The construction of an abnormal energy consumption identification map based on the device topology layer view of the multi-level simulation model and the device energy consumption data includes: Obtain the operating status log of each energy-consuming device in the target park, and obtain the environmental data of the target park; A multi-dimensional feature matrix is ​​constructed by aligning the operating status log, the environmental data, and the device energy consumption data. Transform the device topology layer view into a device relationship diagram that includes the connection relationships between energy-consuming devices; An abnormal energy consumption identification map of devices is constructed based on the multi-dimensional feature matrix and the device relationship diagram.

7. The smart park building visualization management method based on BIM technology as described in claim 1, characterized in that, The step of constructing an abnormal energy consumption identification map of devices based on the multi-dimensional feature matrix and the device relationship graph includes: Construct causal connection weights between energy-consuming devices in the device relationship graph based on the multi-dimensional feature matrix; Calculate the connection correlation between energy-consuming devices in the device relationship diagram based on the multi-dimensional feature matrix; Obtain historical anomaly data for each energy-consuming device in the target park, and calculate the anomaly propagation probability between energy-consuming devices in the device relationship diagram based on the historical anomaly data; Based on the causal connection weights, connection correlations, and anomaly propagation probabilities, causal connection edges, correlation connection edges, and anomaly propagation edges are constructed between energy-consuming devices in the device relationship graph, respectively, to obtain the device abnormal energy consumption identification map.

8. The smart park building visualization management method based on BIM technology as described in claim 1, characterized in that, The step of tracing the abnormal energy consumption devices based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification results and the energy consumption flow layer view of the multi-level simulation model, to obtain the device tracing results, includes: Identify the abnormal event characteristics of the abnormal energy consumption event identification results; Generate a source tracing path table based on the energy consumption flow layer view; The abnormal sub-device is identified based on the abnormal energy consumption event identification results; Based on the abnormal sub-device and the source tracing path table, multi-level reverse tracing is performed to obtain a multi-level source tracing path tree; Identify the key nodes in the multi-level tracing path tree to obtain a list of key nodes; Based on the list of key nodes and the multi-level traceability path tree, the abnormal energy consumption equipment is traced to obtain the equipment traceability results.

9. The smart park building visualization management method based on BIM technology as described in claim 8, characterized in that, The step of tracing abnormal energy consumption devices based on the key node list and the multi-level tracing path tree to obtain device tracing results includes: Based on the list of key nodes and the energy consumption data of the equipment, anomaly time series analysis is performed on each tracing path of the multi-level tracing path tree to obtain the time series analysis results; Based on the time series analysis results, the time series confidence of each tracing path in the multi-level tracing path tree is calculated. A preset number of tracing paths are selected from the multi-level tracing path tree in descending order of time series confidence to obtain a path set. Based on the abnormal energy consumption event identification results, the abnormal time point is confirmed, and detailed energy consumption data of each energy-consuming device at the abnormal time point is obtained from the device energy consumption data; Based on the detailed energy consumption data, the ratio of the total energy output by the upstream device to the total energy output by the downstream device at the abnormal time point in each path of the path set is calculated to obtain the abnormal contribution of each path. The path with the highest abnormal contribution is identified as the abnormal path, and the source device in the abnormal contribution is identified as the final device tracing result.

10. A smart park building visualization management system based on BIM technology, characterized in that, The system includes: The data acquisition module is used to acquire building structure data and equipment energy consumption data of the target park based on preset sensors, as well as cable layout data of the target park; The model building module is used to perform BIM simulation based on the building structure data, the equipment energy consumption data and the cable layout data to obtain a multi-level simulation model that includes the equipment topology layer view and the energy consumption flow layer view of the target park. An anomaly identification module is used to construct an abnormal energy consumption identification map based on the equipment topology layer view of the multi-level simulation model and the equipment energy consumption data, identify abnormal energy consumption events in the target park according to the abnormal energy consumption identification map, and obtain abnormal energy consumption event identification results. The anomaly tracing module is used to trace the abnormal energy consumption equipment when an abnormal energy consumption event is determined to exist in the target park based on the abnormal energy consumption event identification result. This is done by tracing the abnormal energy consumption equipment based on the abnormal energy consumption point information contained in the abnormal energy consumption event identification result and the energy consumption flow layer view of the multi-level simulation model. The device tracing result is then mapped back to the device abnormal energy consumption identification map. Based on the causal connection weights and anomaly propagation probabilities in the device abnormal energy consumption identification map, a dynamic pulse wave is initiated from the abnormal energy consumption point to the source device in the device tracing result in the multi-level simulation model. The confidence level and anomaly severity level of the tracing path are encoded by pulse intensity, color, and frequency to perform visually guided fault location and obtain the location result. The instruction sending module is used to generate a first control strategy and a second control strategy based on the positioning result, perform dynamic simulation based on the first control strategy and the second control strategy using the multi-level simulation model to obtain the simulation result, confirm the optimal strategy among the first control strategy and the second control strategy based on the simulation result, generate control instructions based on the optimal strategy, and send the control instructions to the source device in the target park corresponding to the positioning result based on a preset IoT interface.

Images