A park global multi-dimensional real-time digital twin collaborative management and control system and method

Abstract

The application discloses a kind of park global multidimensional real-time digital twin collaborative management and control system and method, belong to wisdom park technical field, its system includes equipment mapping unit, data processing unit, BIM model updating unit, instruction correction unit, collaborative management and control unit and exception report generation unit;Equipment mapping unit is used to construct space-time coding mapping table and material library;Data processing unit is used to real-time acquisition and filter IoT data;BIM model updating unit is used to dynamically update BIM model;Instruction correction unit is used to generate and correct preliminary collaborative instruction;Collaborative management and control unit is used to obtain final control instruction set;Exception report generation unit is used to generate fault root cause report as collaborative control result.The application realizes that fault location delay drops, red line violation rate drops, effectively solves the pain points of prior art data fragmentation, response delay and false alarm.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of smart park, and particularly relates to a park global multi-dimensional real-time digital twin collaborative management system and method. BACKGROUND

[0002] At present, with the in-depth promotion of smart park construction, BIM (BIM) and IoT (IoT) technologies are widely used in the planning, construction and operation management of the park. BIM provides accurate three-dimensional digital expression of the physical space of the park, including rich geometric, semantic and attribute information; IoT collects dynamic data such as environment, equipment operation, energy consumption and personnel activities in real time through a sensor network throughout the park. However, the existing technical solutions have significant technical bottlenecks and systematic defects in realizing the global, dynamic and collaborative fine management of the park, mainly in the following aspects:

[0003] 1. Deep data fragmentation and fusion failure.

[0004] Technical separation: the existing platform architecture usually regards BIM static model (stored in CAD / BIM platform or specific format file) and IoT real-time data stream (stored in time series database or message queue) as two independent data sources. They lack unified data model, semantic mapping mechanism and efficient real-time data channel.

[0005] Severe update delay: dynamic IoT data (such as sensor readings, equipment status) is difficult to drive the update of BIM model in time and automatically. Common batch processing or polling methods cause the model state to be seriously out of sync with the physical world, with an update delay of more than 10 minutes, even hours. This makes the situational awareness, analysis and decision-making based on the model (such as emergency evacuation simulation, fault location) lose timeliness and accuracy.

[0006] Data value loss: the component-level semantic information (such as device model, material, spatial relationship) contained in the BIM model cannot effectively enable IoT data analysis (such as understanding which devices or building envelopes are related to the energy consumption anomaly of a certain area). Conversely, the real-time state of IoT cannot be intuitively and dynamically presented in the BIM model (such as real-time temperature cloud map superimposed on the BIM model).

[0007] "Static digital model" rather than "dynamic digital twin": this fragmentation makes the system essentially only a visualization platform or data dashboard, and cannot form a "digital twin" that truly reflects the real-time state of physical entities and supports prediction and optimization.

[0008] 2. Failure of coordinated scheduling of multi-energy flow systems in sub-regions.

[0009] Subsystem island operation: The park contains complex energy subsystems, such as distributed photovoltaic / wind power (microgrid), electric vehicle charging piles, energy storage systems (batteries, ice storage, etc.), and flexible loads (air conditioning, lighting). Existing management platforms often use a "chimney" architecture, with each subsystem (microgrid control system, charging pile management platform, building automation system) running independently, lacking a unified data interface and collaborative optimization mechanism.

[0010] Lack of global optimization perspective: Each subsystem only focuses on its own goals (such as ensuring charging completion for charging piles and maintaining local balance for microgrids), and cannot coordinate from the perspective of overall energy efficiency, economy (such as responding to time-of-use electricity prices), or stability (such as participating in grid demand response).

[0011] Safety and economy conflict: Lack of coordination may lead to local overload (such as multiple charging piles running at full power simultaneously causing transformer overload) or resource waste (such as photovoltaic power generation being abundant while energy storage is not charged in time).

[0012] 3. Large areas cannot support virtual power plant (virtual power plant) second-level response.

[0013] Virtual power plants require the aggregation of dispersed and heterogeneous distributed energy resources into a controllable whole to participate in power market auxiliary services or main grid dispatching. This requires second-level (even millisecond-level) coordination and control capabilities. Existing technologies cannot achieve fast and accurate collaborative control across systems (such as adjusting charging power, adjusting air conditioning set values, and charging and discharging energy storage) due to data fragmentation, system isolation, and decentralized decision-making, severely restricting the potential of parks to participate in the power market, improve energy income, and enhance flexibility. At the same time, for large parks with multiple land red lines, there are restrictions on cross-regional power transmission within different red line ranges.

[0014] In summary, existing park management platforms have serious deficiencies in the deep integration of BIM and IoT, real-time collaborative control of multi-source heterogeneous systems, and overall virtual power plant dispatching covering multiple red line areas.

[0015] In existing solutions, BIM and IoT data are separated due to storage architecture (BIM is stored in CAD platforms and IoT is stored in time series databases), resulting in: (1) update delay > 10 minutes, low fault location efficiency (average 35 minutes); (2) energy subsystems run independently and cannot respond to second-level virtual power plant dispatching; (3) lack of red line constraint mechanism for cross-plot power transmission, with a violation rate > 23%. SUMMARY

[0016] To solve the above problems, the present application proposes a park global multi-dimensional real-time digital twin collaborative management and control system and method.

[0017] The technical scheme of the present application is: a park global multi-dimensional real-time digital twin collaborative management and control system comprising a device mapping unit, a data processing unit, a BIM model updating unit, an instruction correction unit, a collaborative management and control unit, and an abnormality report generating unit;

[0018] The device mapping unit is used to construct a space-time coding mapping table and a material library.

[0019] The data processing unit is used to collect and filter IoT data in real time according to the cable material library.

[0020] The BIM model updating unit is used to dynamically update the BIM model according to the filtered IoT data.

[0021] The instruction correction unit is used to generate and correct preliminary collaborative instructions using federated learning according to the dynamically updated BIM model.

[0022] The collaborative management and control unit is used to obtain a final control instruction set according to the corrected preliminary collaborative instructions and the operation and maintenance cost of the park based on spatial accessibility.

[0023] The abnormality report generating unit is used to perform abnormality detection and root cause analysis on the collected IoT data, generate a fault root cause report, and take the final control instruction set and the fault root cause report as the collaborative management and control result.

[0024] Based on the above system, the present application further proposes a park global multi-dimensional real-time digital twin collaborative management and control method, comprising the following steps:

[0025] S1, constructing a space-time coding mapping table and a material library.

[0026] S2, collecting and filtering IoT data in real time according to the cable material library.

[0027] S3, dynamically updating the BIM model according to the filtered IoT data.

[0028] S4, generating and correcting preliminary collaborative instructions using federated learning according to the dynamically updated BIM model.

[0029] S5, obtaining a final control instruction set according to the corrected preliminary collaborative instructions and the operation and maintenance cost of the park based on spatial accessibility.

[0030] S6, performing abnormality detection and root cause analysis on the collected IoT data, generating a fault root cause report, and taking the final control instruction set and the fault root cause report as the collaborative management and control result.

[0031] Further, S1 comprises the following sub-steps:

[0032] S11. Assign spatial codes to each piece of equipment in the park, and construct the mapping relationship between equipment and BIM components based on the spatial codes;

[0033] S12. Calculate the equivalent power transmission distance based on the mapping relationship between the equipment and BIM components;

[0034] S13. Based on the equivalent transmission distance, construct a mapping table between the equipment and the BIM construction, and generate a cable material library.

[0035] Furthermore, in S12, the equivalent transmission distance The expression is:

[0036] ;

[0037] ;

[0038] ;

[0039] in, Indicates the number of path points. Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional ordinates of the points Indicates the first path The three-dimensional ordinates of the points Indicates the first path The three-dimensional vertical coordinates of each point Indicates the first path The three-dimensional vertical coordinates of each point Indicates impedance weight, This indicates the factor affecting the thermal resistance of the cable. Indicates the thermal resistance coefficient of the cable. Indicates the reference thermal resistance. Indicates the influence factor of bending angle. Indicates the maximum curvature angle of the path segment. Indicates the factors affecting spatial congestion. This indicates the number of devices within a 5m radius around the path segment. Indicates the density of the reference equipment. This indicates the aging sensitivity coefficient (0.02 / year for copper cable and 0.05 / year for aluminum cable). Indicates the service life (read from the BIM equipment attribute library). This indicates the material's baseline weight (0.4 for copper cable, 0.8 for aluminum cable).

[0040] Furthermore, S3 includes the following sub-steps:

[0041] S31. Obtain spatially tagged cleaning data from the filtered IoT data;

[0042] S32. Based on the clean data with spatial labels, delete the failed components of the BIM model using the spatiotemporal coding mapping table, call the inserted components of the BIM model using the spatiotemporal coding mapping table, complete the equipment update, and perform lightweight rendering to complete the dynamic update of the BIM model.

[0043] Furthermore, S4 includes the following sub-steps:

[0044] S41. Determine the photovoltaic impact factors based on the dynamically updated BIM model;

[0045] S42. Use the photovoltaic impact factor as the input to the plot-level integrated model and output the prediction vector for each plot; the plot-level integrated model adopts the Bagging model;

[0046] S43. Combine the predicted vectors of each plot with the BIM spatial features of the dynamically updated BIM model to output preliminary collaboration instructions.

[0047] S44. Parse the initial coordination instructions to obtain local real-time data;

[0048] S45. Calculate the number of times the ray crosses the red line boundary based on local real-time data;

[0049] S46. Based on the number of times the ray crosses the red line boundary, use federated learning to construct a pre-validated red line constraint;

[0050] S47. Use pre-verification red line constraints to intercept red line violation instructions in the park and complete the correction of the initial coordination instructions.

[0051] Bagging uses several weak machine learning models and aggregates their predictions to produce the best possible prediction.

[0052] Furthermore, in S45, the number of times the ray crosses the red line boundary. The expression is:

[0053] ;

[0054] ;

[0055] in, This indicates the number of vertices in the red-lined polygon. Represents the polygon with the land boundary line. The coordinates of the first vertex and the second vertex The relationship between the vertices Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the three-dimensional x-coordinate of the device to be verified. Represents the three-dimensional ordinate of the device to be verified. Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, This represents the minimum value operation. This represents the maximum value operation;

[0056] In S46, the pre-validation redline constraint The expression is:

[0057] ;

[0058] ;

[0059] in, This indicates the number of scheduling instructions being processed in the current batch. Indicates the first The predicted power value of the scheduling instruction. Indicates the first The actual schedulable power of each scheduling instruction Indicates the dynamic penalty coefficient. This represents a set of illegal instructions. Indicates equipment, This represents the three-dimensional spatial coordinate vector of the device. This indicates the coordinates of the nearest land boundary point to the equipment. Indicates the maximum permissible transmission distance. Indicates the initial penalty coefficient. Represents an exponential function. Indicates a penalty growth factor. Indicates time, Indicates training batch The number of violations.

[0060] Furthermore, S6 includes the following sub-steps:

[0061] S61. Use the K-Means clustering algorithm to detect outliers in the real-time IoT data collected in the park and mark abnormal devices and their timestamps.

[0062] S62. Based on the list of abnormal devices, query the device event logs of the abnormal devices and the BIM spatial topology relationship in the dynamically updated BIM model, and calculate the causal probability using the spatiotemporal fusion probability function.

[0063] S63. Generate a fault root cause report based on the maximum causal probability, and dynamically render the fault propagation path in the BIM model. Use the final control instruction set and the fault root cause report as the collaborative management and control results.

[0064] In S62, the spatiotemporal fusion probability function The expression is:

[0065] ;

[0066] ;

[0067] in, Indicates an event Caused the incident causal probability, Indicates an event The timestamp of the occurrence, Indicates an event The timestamp of the occurrence, Indicates the time decay coefficient. Indicates the strength of spatial association. Indicates the space normalization factor. This represents the first weighting coefficient. This represents the second weighting coefficient. Indicates the spatial distance between two anomalies. Indicates the reliability of the connector. Indicates the topology hop count. This represents an exponential function.

[0068] The beneficial effects of this invention are: This invention performs dynamic fusion of BIM-IoT data to achieve spatial coding, quantifies BIM attributes such as cable thermal resistance and bending angle into impedance weights, and reduces the error in power transmission loss calculation; This invention also dynamically verifies land use boundaries through the three-dimensional ray method, supporting collaborative scheduling of multiple plots in large parks. Attached Figure Description

[0069] Figure 1 A schematic diagram of the structure of the multi-dimensional real-time digital twin collaborative management and control system covering the entire park;

[0070] Figure 2The flowchart shows the multi-dimensional real-time digital twin collaborative management and control method for the entire park. Detailed Implementation

[0071] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0072] like Figure 1 As shown, the present invention provides a multi-dimensional real-time digital twin collaborative management and control system for the entire park, including an equipment mapping unit, a data processing unit, a BIM model updating unit, an instruction correction unit, a collaborative management and control unit, and an anomaly report generation unit;

[0073] The device mapping unit is used to construct a spatiotemporal coding mapping table and a material library;

[0074] The data processing unit is used to collect and filter IoT data in real time based on the cable material library;

[0075] The BIM model update unit is used to dynamically update the BIM model based on the filtered IoT data;

[0076] The instruction correction unit is used to generate and correct preliminary collaborative instructions based on the dynamically updated BIM model using federated learning.

[0077] The collaborative management and control unit is used to obtain the final control instruction set based on the revised preliminary collaborative instructions and the park's operation and maintenance costs based on spatial accessibility;

[0078] The anomaly report generation unit is used to perform anomaly detection and root cause analysis on the collected IoT data, generate a fault root cause report, and use the final control instruction set and fault root cause report as the result of collaborative management and control.

[0079] Based on the above systems, such as Figure 2 As shown, this invention also proposes a multi-dimensional real-time digital twin collaborative management and control method for the entire park, including the following steps:

[0080] S1. Construct a spatiotemporal coding mapping table and a material library;

[0081] S2. Collect and filter IoT data in real time based on the cable material library;

[0082] S3. Dynamically update the BIM model based on the filtered IoT data;

[0083] S4. Based on the dynamically updated BIM model, generate and revise preliminary collaborative instructions using federated learning;

[0084] S5. Based on the revised preliminary coordination instructions and the park's operation and maintenance costs based on spatial accessibility, the final control instruction set is obtained;

[0085] S6. Perform anomaly detection and root cause analysis on the collected IoT data, generate a fault root cause report, and use the final control instruction set and fault root cause report as the collaborative management and control results.

[0086] This invention achieves real-time synchronization and intelligent collaboration between physical parks and digital twins by constructing three closed loops: data-model, anomaly handling, and federated optimization. Core features include: millimeter-level binding of BIM models and IoT devices through a spatiotemporal coding engine; employing a federated learning framework with a dynamic penalty mechanism that grows exponentially with the number of violations to achieve collaborative scheduling across plots while protecting privacy; establishing a cable cluster temperature rise early warning model to quantify historical accumulation and mutually coupled thermal effects for accurate overheating risk warnings; and tracing the root causes of faults based on vector clocks and spatiotemporal probability functions. This invention reduces fault location latency and red-line violation rates, effectively addressing the pain points of existing technologies such as data fragmentation, response delays, and false alarms / missed alarms. Simultaneously, the spatiotemporal fusion probability function enables automated and accurate tracing of fault causal chains, overcoming the shortcomings of traditional rule engines that rely on manual thresholds and lack flexibility, thus improving the accuracy of fault root cause analysis.

[0087] In S2, IoT data streams are accessed via the MQTT / OPC-UA protocol, Kalman filtering is used to denoise the edge nodes, and spatial labels are added to output clean data with spatial labels.

[0088] In this embodiment of the invention, S1 includes the following sub-steps:

[0089] S11. Assign spatial codes to each piece of equipment in the park, and construct the mapping relationship between equipment and BIM components based on the spatial codes;

[0090] S12. Calculate the equivalent power transmission distance based on the mapping relationship between the equipment and BIM components;

[0091] S13. Based on the equivalent transmission distance, construct a mapping table between the equipment and the BIM construction, and generate a cable material library.

[0092] Convert the physical properties of the cable stored in BIM (outer diameter / conductor size / insulation material) into thermal resistance coefficient. For the first time, the thermal resistance of the cable was reduced. Bending angle and equipment density The three types of BIM attributes are uniformly quantified into a spatial impedance coefficient, which is used as a spatial impedance weighting factor to achieve coupled modeling of cable thermal characteristics and spatial path, enabling high-precision transmission loss prediction and prevention of high-voltage power loss. Cable overload.

[0093] In this embodiment of the invention, in S12, the equivalent transmission distance The expression is:

[0094] ;

[0095] ;

[0096] ;

[0097] in, Indicates the number of path points. Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional ordinates of the points Indicates the first path The three-dimensional ordinates of the points Indicates the first path The three-dimensional vertical coordinates of each point Indicates the first path The three-dimensional vertical coordinates of each point Indicates impedance weight, This indicates the factor affecting the thermal resistance of the cable. Indicates the thermal resistance coefficient of the cable. Indicates the reference thermal resistance. Indicates the influence factor of bending angle. Indicates the maximum curvature angle of the path segment. Indicates the factors affecting spatial congestion. This indicates the number of devices within a 5m radius around the path segment. Indicates the density of the reference equipment. This indicates the aging sensitivity coefficient (0.02 / year for copper cable and 0.05 / year for aluminum cable). Indicates the service life (read from the BIM equipment attribute library). This indicates the material's baseline weight (0.4 for copper cable, 0.8 for aluminum cable).

[0098] Bending angle extracted from BIM pipe connectors Adjust according to the aging condition of the cable. The value adaptively adjusts according to the cable material. Dynamic weighting is adaptive, with weighting coefficients changing in real-time with BIM attributes: bending angle. Increase, then impedance weight Increase; equipment density Increase, then impedance weight This approach enhances and ultimately achieves joint spatial and electrical modeling, establishing for the first time a mapping mechanism between "BIM physical attributes → spatial impedance weights." Through bending angle quantification, equipment density interference modeling, and dynamic coupling of thermal resistance in 3D, it addresses the transmission loss calculation errors caused by neglecting physical characteristics in traditional solutions. This model deeply mines BIM semantic information, providing precise spatial constraints for energy dispatching within the park.

[0099] In this embodiment of the invention, S3 includes the following sub-steps:

[0100] S31. Obtain spatially tagged cleaning data from the filtered IoT data;

[0101] S32. Based on the clean data with spatial labels, delete the failed components of the BIM model using the spatiotemporal coding mapping table, call the inserted components of the BIM model using the spatiotemporal coding mapping table, complete the equipment update, and perform lightweight rendering to complete the dynamic update of the BIM model.

[0102] In S32, the BIM model is dynamically updated and rendered based on clean data with spatial labels. The core of this step lies in the use of an event-triggered mechanism and performance optimization strategies, which ensures the real-time and smooth updates of the digital twin, and solves the technical bottlenecks of high latency and high resource consumption for loading the entire model in traditional polling methods.

[0103] In step S3, the event triggering mechanism is as follows: the edge gateway publishes the filtered IoT data to a specific MQTT topic, and the BIM model update service, as a subscriber, triggers a partial update only when the data changes. The specific implementation process and optimization strategies are as follows:

[0104] Event-triggered update mechanism (replacing polling)

[0105] Problem: Traditional solutions use periodic polling of the database to obtain updated data, which generally results in an update delay of more than 10 minutes, failing to meet real-time requirements.

[0106] Solution: This invention employs the Message Queuing Telemetry Transport (MQTT) protocol, using a publish / subscribe model for event triggering. After collecting IoT data and filtering it in step S2, the edge gateway immediately publishes the clean data with spatial tags as messages to a specific MQTT topic.

[0107] Results: The BIM model update service, acting as a subscriber, monitors these topics in real time. Once a message arrives (such as a sudden change in the current value of a device), the update service is immediately triggered, operating only on the relevant components that have changed. Real-world testing shows that this mechanism reduces model update latency from over 10 minutes in traditional methods to less than 2 seconds, achieving true real-time updates.

[0108] Lightweight rendering and asynchronous transaction processing

[0109] Problem: BIM models are usually huge. Loading and rendering the entire model every time there is an update can cause the client interface to lag, CPU usage to be extremely high (>80%), and user experience to be poor.

[0110] Solution: To ensure system smoothness, this invention adopts the following two optimization strategies:

[0111] a. Create a lightweight view template: In a BIM platform (such as Revit), pre-create a dedicated view template. This template only displays key component categories related to operation and maintenance management, such as electrical, HVAC, and piping, while hiding irrelevant components such as architectural and structural elements. Simultaneously, set the view's detail level to "Coarse" mode to reduce the graphic detail load.

[0112] b. Asynchronous Transaction Processing: To avoid blocking the main user interface thread during update operations, a non-blocking asynchronous transaction processing mechanism is employed. All model update requests (such as parameter modifications and device highlighting) are placed in a first-in-first-out (FIFO) task queue. These update requests are retrieved from the queue and processed one by one using the BIM platform's idling events or background worker threads.

[0113] Results: The above strategies significantly reduced the system rendering burden and interface lag. The interface response latency for a single update operation is less than 1 second, ensuring a smooth user experience during 3D interactions.

[0114] Under the protection of the above mechanism, specific update operations are performed:

[0115] Deleting invalid components: Using the spatiotemporal coding mapping table, locate and delete the BIM components corresponding to non-existent equipment through BIM API (such as the DeleteElement method of Revit API).

[0116] Inserting new components: Based on the mapping relationship, the corresponding family type (Family Symbol) is called from the preset BIM Family Library, and the new equipment component is inserted at the specified spatial coordinates through methods such as NewFamilyInstance.

[0117] Status synchronization and visualization: IoT data (such as current and temperature values) are written into the shared parameters corresponding to BIM components, and the appearance attributes of the components are dynamically modified (such as setting the color of overloaded equipment to red and flashing) to achieve status visualization.

[0118] Through the above technical solutions, this invention achieves efficient, real-time, and stable dynamic updates of the BIM model, providing an accurate digital twin base for subsequent collaborative management and control.

[0119] In this embodiment of the invention, S4 includes the following sub-steps:

[0120] S41. Determine the photovoltaic impact factors based on the dynamically updated BIM model;

[0121] S42. Use the photovoltaic impact factor as the input to the plot-level integrated model and output the prediction vector for each plot; the plot-level integrated model adopts the Bagging model;

[0122] S43. Combine the predicted vectors of each plot with the BIM spatial features of the dynamically updated BIM model to output preliminary collaboration instructions.

[0123] S44. Parse the initial coordination instructions to obtain local real-time data;

[0124] S45. Calculate the number of times the ray crosses the red line boundary based on local real-time data;

[0125] S46. Based on the number of times the ray crosses the red line boundary, use federated learning to construct a pre-validated red line constraint;

[0126] S47. Use pre-verification red line constraints to intercept red line violation instructions in the park and complete the correction of the initial coordination instructions.

[0127] Bagging employs several weak machine learning models and aggregates their predictions to produce the best possible forecast. Bagging ensemble: voting / averaging the results of the base model to generate site-level predictions (such as energy storage charging and discharging strategies).

[0128] In this embodiment of the invention, S45 is the number of times the ray crosses the red line boundary. The expression is:

[0129] ;

[0130] ;

[0131] in, This indicates the number of vertices in the red-lined polygon. Represents the polygon with the land boundary line. The coordinates of the first vertex and the second vertex The relationship between the vertices Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the three-dimensional x-coordinate of the device to be verified. Represents the three-dimensional ordinate of the device to be verified. Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, This represents the minimum value operation. This represents the maximum value operation;

[0132] In S46, the pre-validation redline constraint The expression is:

[0133] ;

[0134] ;

[0135] in, This indicates the number of scheduling instructions being processed in the current batch. Indicates the first The predicted power value of the scheduling instruction. Indicates the first The actual schedulable power of each scheduling instruction Indicates the dynamic penalty coefficient. This represents a set of illegal instructions. Indicates equipment, This represents the three-dimensional spatial coordinate vector of the device. This indicates the coordinates of the nearest land boundary point to the equipment. Indicates the maximum permissible transmission distance. Indicates the initial penalty coefficient. Represents an exponential function. Indicates a penalty growth factor. Indicates time, Indicates training batch The number of violations. This is a dimensionless system parameter (default 1000), which controls the basic penalty intensity. This is a dimensionless system parameter (default 0.3), and the exponential growth rate is adjusted based on the existing data range of [0.1, 0.5].

[0136] The spatial rule-differentiable transformation innovatively converts land use boundary constraints into continuously differentiable loss terms. / This normalization process preserves spatial relationships and is compatible with machine learning optimization. Compared to existing methods that only use 0 / 1 penalties, the method of this invention makes the gradient update direction of the model more accurate.

[0137] The penalty coefficient increases exponentially with the number of violations. When a plot of land frequently violates regulations, the penalty amplifies dramatically, forcing the model to converge quickly to a safe zone. This design addresses the problem of sluggish response from static weights. The core value of this function lies in transforming discrete spatial rules into differentiable mathematical constraints.

[0138] In S46, construct the pre-validation redline constraint. The constraint consists of two parts: a prediction accuracy loss term and a spatial violation penalty term. Its core innovation lies in the introduction of a dynamic penalty coefficient λ, which can adaptively and exponentially increase based on the number of historical violations, thereby solving the problem of slow response in traditional static penalty mechanisms.

[0139] Traditional methods often use Boolean logic (0 or 1) to verify land use boundaries, discarding any violations. This approach has two inherent drawbacks: First, it fails to provide gradient information for machine learning models, preventing them from learning the continuous concept that "the closer to the boundary, the greater the risk of violation," leading to aimless optimization. Second, using fixed penalty weights cannot distinguish between occasional and habitual violations, resulting in insufficient constraints on frequently transgressing land boundaries, slow model convergence, and a tendency to oscillate near violation boundaries.

[0140] The working principle and beneficial effects of the dynamic penalty mechanism of this invention are as follows:

[0141] Transformation of continuously differentiable spatial constraints: penalty term This transforms the discrete redline rule into a continuously differentiable function. (Equipment coordinates) Boundary point of the red line The closer the Euclidean distance, the larger the value, indicating a higher risk of violation. This allows the model to perceive the degree of violation through gradient descent, rather than just whether a violation has occurred, thus enabling optimization updates in the correct direction (i.e., away from the red line).

[0142] Adaptive exponential penalty: This is the core of this invention. The dynamic penalty coefficient λ is not a fixed value; its initial value is... It will vary depending on the specific plot in the training batch. Total number of violations in history The exponential growth factor increases exponentially (controlled by the exp function). Used to regulate the rate of growth.

[0143] Solving the problem of sluggish static punishment: This design completely solves the problem of sluggish static punishment response mentioned in the background art.

[0144] For sporadic violations: the number of historical violations is small, the λ value is small, and the model is subject to a mild penalty, which is enough to correct its direction but not to overreact.

[0145] For habitual violations: the cumulative number of historical violations causes the λ value to amplify dramatically, exerting a very strong penalty on the model. This is equivalent to giving the model a strong signal, forcing it to converge quickly to a safe and compliant solution space, thereby greatly accelerating the model's training and convergence speed and effectively avoiding repeated trials and oscillations near the compliance boundary.

[0146] Technical effect: This mechanism ensures that the federated learning model can not only learn the global energy scheduling rules while strictly protecting the data privacy of each plot, but also efficiently and firmly learn and abide by the spatial physical rules (land use boundary).

[0147] In this embodiment of the invention, S5 includes the following sub-steps:

[0148] S51. Based on the parameters in the cable material library, calculate the transformer capacity, cable current, total temperature rise, and corrected power as physical constraints.

[0149] S52. Based on physical constraints and the revised preliminary coordination instructions, obtain space compliance scheduling instructions;

[0150] S53. Calculate the operation and maintenance costs of the park based on spatial accessibility;

[0151] S54. Based on the space compliance scheduling instructions and the operation and maintenance costs based on space reachability, the final control instruction set is obtained.

[0152] In this embodiment of the invention, in S51, the transformer capacity... The expression is:

[0153] ;

[0154] in, Indicates the current load on the transformer. This indicates the change in power flowing into the transformer after the instruction is executed. This indicates the change in power flowing out of the transformer after the instruction is executed;

[0155] In S51, cable current The expression is:

[0156] ;

[0157] in, Indicates the active power transmitted. Indicates the transmitted reactive power. Indicates line voltage. Indicates the power factor;

[0158] In S51, dynamic temperature rise warning for cables, dynamic heat transfer in the space, and cable temperature rise are all included. The coupling coefficient is derived from the generation of thermal radiation. Outgoing cable The temperature increase is calculated by taking the increment of temperature, which is then used to obtain the total temperature increase. The expression is:

[0159] ;

[0160] ;

[0161] in, Indicates cable The effective value of the current, Indicates cable thermal resistance coefficient, Indicates cable The cumulative effect coefficient, Indicates cable exist The temperature rises over time, Indicates the current time step. Indicates an index. Indicates cable The heat dissipation rate coefficient, Indicates the sampling time interval. Indicates the total number of surrounding cables. Indicates cable exist The temperature rises over time, Indicates cable With cable thermal coupling coefficient, Indicates the effective contact area. Indicates cable With cable Spacing Represents an exponential function. Indicates the material attenuation factor. Indicates cable Insulation layer thickness;

[0162] Used as a basis for real-time early warning; It is the main source of fever; Determined by its own heat dissipation efficiency, derived from the BIM attribute library; Used to quantify historical temperature rise residue; To control the rate of temperature rise decay; Derived from the system clock (default 1s), these are time-varying model parameters; It belongs to the dimensionless category of BIM spatial topology calculation, and its innovation lies in quantifying the intensity of thermal interaction. Determine the coupling range; The calculation of physical contact area, cable outer diameter × parallel length, is innovative in that it quantifies the degree of physical contact. The closer the distance, the stronger the coupling.

[0163] In S51, the power correction The expression is:

[0164] ;

[0165] in, This indicates the original command power value. Indicates the maximum permissible transmission distance. This indicates the actual transmission distance.

[0166] In S53, the operational costs based on spatial reachability The expression is:

[0167] ;

[0168] ;

[0169] in, Indicates the total number of devices. Indicates the time taken for a single repair. This represents the labor cost per unit of time. Represents the three-dimensional accessibility score. This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the third weighting coefficient. This represents the path distance to the nearest entrance; the data comes from 3D path planning. Indicates the maximum depth of the park. Indicates the number of turns. Indicates the maximum number of turns allowed. Indicates the space security level.

[0170] In this embodiment of the invention, S6 includes the following sub-steps:

[0171] S61. Use the K-Means clustering algorithm to detect outliers in the real-time IoT data collected in the park and mark abnormal devices and their timestamps.

[0172] S62. Based on the list of abnormal devices, query the device event logs of the abnormal devices and the BIM spatial topology relationship in the dynamically updated BIM model, and calculate the causal probability using the spatiotemporal fusion probability function.

[0173] S63. Generate a fault root cause report based on the maximum causal probability, and dynamically render the fault propagation path in the BIM model. Use the final control instruction set and the fault root cause report as the collaborative management and control results.

[0174] In S62, the spatiotemporal fusion probability function The expression is:

[0175] ;

[0176] ;

[0177] in, Indicates an event Caused the incident causal probability, Indicates an event The timestamp of the occurrence, Indicates an event The timestamp of the occurrence, Indicates the time decay coefficient. Indicates the strength of spatial association. Indicates the space normalization factor. This represents the first weighting coefficient. This represents the second weighting coefficient. Indicates the spatial distance between two anomalies. Indicates the reliability of the connector. Indicates the topology hop count. This represents an exponential function.

[0178] Spatial normalization factor, dimensionless, derived from maximum device distance, used to balance dimensions. Connector reliability, derived from the electromechanical property library, used to quantify physical connection strength. Spatial distance from device A to B, derived from device coordinates, used to calculate stronger associations as distance increases. Topology hop count, dimensionless, derived from connectivity graph analysis, used to support indirect association analysis. The sum of the relative weights of the effects of time and space is 1.

[0179] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for multi-dimensional real-time digital twin collaborative management and control of the entire park, characterized in that, Includes the following steps: S1. Construct a spatiotemporal coding mapping table and a material library; S2. Collect and filter IoT data in real time based on the cable material library; S3. Dynamically update the BIM model based on the filtered IoT data; S4. Based on the dynamically updated BIM model, generate and revise preliminary collaborative instructions using federated learning; S5. Based on the revised preliminary coordination instructions and the park's operation and maintenance costs based on spatial accessibility, the final control instruction set is obtained; S6. Perform anomaly detection and root cause analysis on the collected IoT data, generate a fault root cause report, and use the final control instruction set and fault root cause report as the collaborative management and control results. S4 includes the following sub-steps: S41. Determine the photovoltaic impact factors based on the dynamically updated BIM model; S42. The photovoltaic impact factor is used as the input to the plot-level integrated model, and the prediction vectors of each plot are output; the plot-level integrated model adopts the Bagging model; S43. Combine the predicted vectors of each plot with the BIM spatial features of the dynamically updated BIM model to output preliminary collaboration instructions. S44. Parse the initial coordination instructions to obtain local real-time data; S45. Calculate the number of times the ray crosses the red line boundary based on local real-time data; S46. Based on the number of times the ray crosses the red line boundary, use federated learning to construct a pre-validated red line constraint; S47. Use pre-verification red line constraints to intercept red line violation instructions in the park and complete the correction of the initial coordination instructions; In S45, the number of times the ray crosses the red line boundary. The expression is: ； ； in, This indicates the number of vertices in the red-lined polygon. Represents the polygon with the land boundary line. The coordinates of the first vertex and the second vertex The relationship between the vertices Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the polygon with the land boundary line. The coordinates of the vertices, Represents the three-dimensional x-coordinate of the device to be verified. Represents the three-dimensional ordinate of the device to be verified. Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The y-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, Represents the polygon with the land boundary line. The x-coordinates of the vertices, This represents the minimum value operation. This represents the maximum value operation; In S46, the pre-verification redline constraint The expression is: ； ； in, This indicates the number of scheduling instructions being processed in the current batch. Indicates the first The predicted power value of the scheduling instruction. Indicates the first The actual schedulable power of each scheduling instruction Indicates the dynamic penalty coefficient. This represents a set of illegal instructions. Indicates equipment, This represents the three-dimensional spatial coordinate vector of the device. This indicates the coordinates of the nearest land boundary point to the equipment. Indicates the maximum permissible transmission distance. Indicates the initial penalty coefficient. Represents an exponential function. Indicates a penalty growth factor. Indicates time, Indicates training batch The number of violations.

2. The method for multi-dimensional real-time digital twin collaborative management and control of the entire park as described in claim 1, characterized in that, S1 includes the following sub-steps: S11. Assign spatial codes to each piece of equipment in the park, and construct the mapping relationship between equipment and BIM components based on the spatial codes; S12. Calculate the equivalent power transmission distance based on the mapping relationship between the equipment and BIM components; S13. Based on the equivalent transmission distance, construct a mapping table between the equipment and the BIM construction, and generate a cable material library.

3. The method for multi-dimensional real-time digital twin collaborative management and control of the entire park according to claim 2, characterized in that, In S12, the equivalent transmission distance The expression is: ； ； ； in, Indicates the number of path points. Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional x-coordinates of each point Indicates the first path The three-dimensional ordinates of each point Indicates the first path The three-dimensional ordinates of the points Indicates the first path The three-dimensional vertical coordinates of each point Indicates the first path The three-dimensional vertical coordinates of each point Indicates impedance weight, This indicates the factor affecting the thermal resistance of the cable. Indicates the thermal resistance coefficient of the cable. Indicates the reference thermal resistance. Indicates the influence factor of bending angle. Indicates the maximum curvature angle of the path segment. Indicates the factors affecting spatial congestion. This indicates the number of devices within a 5m radius around the path segment. Indicates the density of the reference equipment. Indicates the aging sensitivity coefficient. Indicates the length of service. This indicates the material baseline weight.

4. The method for multi-dimensional real-time digital twin collaborative management and control of the entire park as described in claim 1, characterized in that, S3 includes the following sub-steps: S31. Obtain spatially tagged cleaning data from the filtered IoT data; S32. Based on the clean data with spatial labels, delete the failed components of the BIM model using the spatiotemporal coding mapping table, call the inserted components of the BIM model using the spatiotemporal coding mapping table, complete the equipment update, and perform lightweight rendering to complete the dynamic update of the BIM model.

5. The method for multi-dimensional real-time digital twin collaborative management and control of the entire park as described in claim 1, characterized in that, S5 includes the following sub-steps: S51. Based on the parameters in the cable material library, calculate the transformer capacity, cable current, total temperature rise, and corrected power as physical constraints. S52. Based on physical constraints and the revised preliminary coordination instructions, obtain space compliance scheduling instructions; S53. Calculate the operation and maintenance costs of the park based on spatial accessibility; S54. Based on the space compliance scheduling instructions and the operation and maintenance costs based on space reachability, the final control instruction set is obtained.

6. The method for multi-dimensional real-time digital twin collaborative management and control of the entire park as described in claim 1, characterized in that, S6 includes the following sub-steps: S61. Use the K-Means clustering algorithm to detect outliers in the real-time IoT data collected in the park and mark abnormal devices and their timestamps. S62. Based on the list of abnormal devices, query the device event logs of the abnormal devices and the BIM spatial topology relationship in the dynamically updated BIM model, and calculate the causal probability using the spatiotemporal fusion probability function. S63. Generate a fault root cause report based on the maximum causal probability, and dynamically render the fault propagation path in the BIM model. Use the final control instruction set and the fault root cause report as the collaborative management and control results. In S62, the spatiotemporal fusion probability function The expression is: ； ； in, Indicates an event Caused the incident causal probability, Indicates an event The timestamp of the occurrence, Indicates an event The timestamp of the occurrence, Indicates the time decay coefficient. Indicates the strength of spatial correlation. Indicates the space normalization factor. This represents the first weighting coefficient. This represents the second weighting coefficient. Indicates the spatial distance between two anomalies. Indicates the reliability of the connector. Indicates the topological hop count. This represents an exponential function.

7. A multi-dimensional real-time digital twin collaborative management and control system for the entire park, characterized in that, The park-wide multidimensional real-time digital twin collaborative management and control system is used to execute the park-wide multidimensional real-time digital twin collaborative management and control method as described in any one of claims 1-6. The park-wide multidimensional real-time digital twin collaborative management and control system includes an equipment mapping unit, a data processing unit, a BIM model updating unit, an instruction correction unit, a collaborative management and control unit, and an anomaly report generation unit. The device mapping unit is used to construct a spatiotemporal encoding mapping table and a material library; The data processing unit is used to collect and filter IoT data in real time based on the cable material library; The BIM model update unit is used to dynamically update the BIM model based on the filtered IoT data; The instruction correction unit is used to generate and correct preliminary collaborative instructions based on the dynamically updated BIM model using federated learning. The collaborative management and control unit is used to obtain the final control instruction set based on the revised preliminary collaborative instructions and the park's operation and maintenance costs based on spatial accessibility. The anomaly report generation unit is used to perform anomaly detection and root cause analysis on the collected IoT data, generate a fault root cause report, and use the final control instruction set and fault root cause report as the collaborative management and control result.

Images