Underground space energy management system based on digital twinborn technology

Abstract

The invention provides an underground space energy management system based on a digital twin technology. The system comprises a data processing module, a disaster prevention prediction module and a disaster prevention management module. The data processing module is used for collecting operation data and layout data of an energy system of an underground space, and constructing a digital twinborn body according to the operation data, the layout data and a preset simulation model; the disaster prevention prediction module is used for performing simulation deduction on a monitored disaster scene through the digital twinborn body to generate a disaster prevention prediction report; and the disaster prevention management module is used for generating a disaster prevention scheduling strategy according to the disaster prevention prediction report.

Description

Technical Field

[0001] This application relates to the field of digital twin technology, and in particular to an underground space energy management system based on digital twin technology. Background Technology

[0002] With the rapid development of urbanization and industrialization in my country, above-ground space resources are becoming increasingly scarce, and the development and utilization of underground space has gradually become an important way to alleviate urban problems and expand development dimensions. Driven by industrialization, my country's underground space has evolved from civil defense projects and underground transportation to multi-functional complexes, and the number of functional blocks in underground space is increasing day by day.

[0003] However, the energy systems of each functional area within the underground space are planned independently. Although some functional areas have improved energy management efficiency through modern information technology, the underground space lacks a unified, visualized management system, making overall management difficult and resulting in long response times for adjustments. Especially during urban disaster prevention and mitigation, the existing energy management system for underground spaces still suffers from chaotic management and lagging energy adjustments, severely impacting the efficiency of disaster prevention and mitigation. Summary of the Invention

[0004] This application provides an underground space energy management system based on digital twin technology, which is used to improve the management level and adjustment efficiency of the energy system in underground spaces.

[0005] In a first aspect, embodiments of this application provide an underground space energy management system based on digital twin technology, the system comprising: The data processing module is used to collect operational and deployment data of the energy system in the underground space, and to construct a digital twin based on the operational data, the deployment data, and a pre-set simulation model. The disaster prevention and prediction module is used to simulate and extrapolate the monitored disaster scenarios through the digital twin and generate a disaster prevention and prediction report; The disaster prevention management module is used to generate disaster prevention scheduling strategies based on the disaster prediction report.

[0006] In some embodiments, the simulation model includes: a first BIM model and a GIS model, wherein the first BIM model is a three-dimensional simulation model of the underground space, and the data processing module, when performing the collection of operational and deployment data of the energy system in the underground space, and constructing a digital twin based on the operational data, the deployment data, and the preset simulation model, specifically performs the following: Based on the deployment data, the equipment layout and pipeline connection relationship of the energy system are configured in the BIM model to generate a second BIM model; Based on the operational data, the energy system is assigned operational logic in the second BIM model to generate a third BIM model; The third BIM model and the GIS model are coordinate registered to construct a digital twin, which uses the disaster prediction data provided by the GIS model as the simulation boundary conditions.

[0007] In some embodiments, when the disaster prevention prediction module is used to perform simulation and extrapolation of the monitored disaster scenario through the digital twin and generate a disaster prevention prediction report, it is specifically used to perform the following: Based on the GIS model, disaster scenario types and intensity parameters are obtained, and a disaster parameter set is generated according to the disaster scenario types and intensity parameters. Based on the third BIM model, the direct impact of disasters on the energy system is simulated according to the disaster parameter set, and damage assessment results are generated. Based on the third BIM model, a disaster prevention prediction report is generated according to the damage assessment results.

[0008] In some embodiments, when the disaster prediction module is used to simulate the direct impact of a disaster on the energy system based on the third BIM model and the disaster parameter set, and to generate damage assessment results, it is specifically used to perform the following: In the third BIM model, a list of affected equipment is determined based on the disaster scenario type. The list of affected equipment includes: energy equipment type and spatial range. Based on the list of affected equipment and the strength parameters, the damage coefficient and the degree of damage are calculated; Damage assessment results are generated based on the damage coefficient and the damage degree.

[0009] In some embodiments, when the disaster prevention prediction module is used to generate a disaster prevention prediction report based on the damage assessment results using the third BIM model, it is specifically used to perform the following: In the third BIM model, the fault propagation path is determined based on the damage assessment results; A disaster prevention prediction report is generated based on the described fault propagation path.

[0010] In some embodiments, when the disaster prevention management module is used to execute the disaster prevention scheduling strategy generated based on the disaster prevention prediction report, it is specifically used to execute: Based on the energy supply capacity change trend in the disaster prevention prediction report, an emergency energy supply plan and equipment switching sequence are formulated, and a dispatch instruction set is generated. The scheduling instruction set is converted into a standardized control protocol and sent to the execution equipment in the energy system through a communication interface.

[0011] In some embodiments, the energy system includes at least one of a power supply and distribution system, a heating, ventilation and air conditioning system, and a gas system, and the actuators include at least one of a circuit breaker, a valve, a fan, and a pump unit.

[0012] In some embodiments, determining the fault propagation path based on the damage assessment results in the third BIM model is specifically performed by: In the third BIM model, a directed graph model is constructed based on the equipment layout and pipeline connection relationship of the energy system. The directed graph model includes multiple equipment nodes. The failure probability of the device node is calculated based on the damage assessment results, using the following formula: ; Where Pf(j) is the probability that node j becomes a node in the fault propagation path; Ds(j) is the damage state coefficient of node j, which is dimensionless and ranges from [0,1], where 0 represents intact and 1 represents completely damaged; ηj is the vulnerability index of node j; k is the total number of faulty nodes connected to node j; Df(i) is the degree of damage of the faulty node i; Tij is the transmission coupling coefficient between node i and node j; dij is the network distance between node i and node j; and σ is the fault propagation attenuation constant. The device nodes whose failure probability is greater than a preset probability threshold are set as failure nodes, and the failure propagation path is determined based on the failure nodes.

[0013] This application provides an underground space energy management system based on digital twin technology. The system includes a data processing module, a disaster prediction module, and a disaster management module. The data processing module collects operational and deployment data of the underground space energy system and constructs a digital twin based on the operational data, deployment data, and a pre-set simulation model. The disaster prediction module simulates and extrapolates monitored disaster scenarios using the digital twin, generating a disaster prediction report. The disaster management module generates disaster prevention scheduling strategies based on the disaster prediction report. In this system, the simulation and extrapolation based on the digital twin by the disaster prediction module can quickly identify disaster scenarios and generate prediction reports, while the disaster management module can rapidly convert the prediction results into specific scheduling strategies and automatically distribute them to the execution equipment. This improves the system's adjustment efficiency and realizes a shift from a passive response to an active prediction management model. Through intelligent disaster prediction and automated scheduling execution, it provides efficient and accurate management methods for underground space energy systems, meeting the needs of modern underground space energy management for intelligence and rapid response. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A schematic block diagram of an underground space energy management system based on digital twin technology provided for embodiments of this application; Figure 2 A schematic flowchart illustrating a disaster simulation method provided in an embodiment of this application; Figure 3 This is a schematic flowchart illustrating a method for determining a fault propagation path provided in an embodiment of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described below with reference to the accompanying drawings.

[0017] The terms "first" and "second," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0018] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] It should be understood that in this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0020] Please see Figure 1 , Figure 1 This is a schematic block diagram of an underground space energy management system based on digital twin technology, provided in an embodiment of this application. Figure 1 As shown, the underground space energy management system 100 based on digital twin technology includes: a data processing module 101, a disaster prediction module 102, and a disaster management module 103.

[0021] The data processing module 101 is used to collect the operation data and deployment data of the energy system in the underground space, and to construct a digital twin based on the operation data, deployment data and pre-set simulation model.

[0022] For example, the data processing module 101 continuously collects real-time operational data such as voltage, current, power, temperature, pressure, and flow rate using a sensor network deployed in subsystems such as power supply and distribution, HVAC, and gas. Simultaneously, it retrieves static deployment data such as equipment models, installation locations, and connection topologies from engineering drawings and asset databases to form a digital description of the physical world. Based on this, a pre-built BIM model, serving as the geometric and information skeleton of the digital twin, is loaded into the processing engine. According to detailed deployment data, the engine performs three-dimensional spatial positioning and attribute configuration for various energy devices in the model, such as transformers, pumps, ventilation units, and their associated pipelines, ensuring that the equipment layout and pipeline routing in the virtual model are completely consistent with the actual underground space, thereby generating a static entity model. The virtual equipment in the BIM model operates according to the laws of the physical world; for example, circuit breakers are given on / off logic, valves are given opening adjustment logic, and refrigeration units are given energy consumption algorithms based on temperature settings. Meanwhile, the GIS model provides a macroscopic geospatial context, accurately registering its included spatial data, such as geological structures, surrounding environment, and hydrological information, with the pre-constructed BIM model using coordinate transformation algorithms. By integrating equipment attributes from BIM, spatial environment attributes from GIS, and real-time operational data from sensor networks using data fusion technology, a digital twin is constructed. This digital twin can keep pace with the actual energy system in the underground space at an update frequency of seconds or even milliseconds.

[0023] The disaster prevention prediction module 102 is used to simulate and extrapolate the monitored disaster scenarios through a digital twin and generate a disaster prevention prediction report.

[0024] For example, when the disaster prediction module 102 is activated, it uses the terrain data provided by the GIS model to simulate the flood spread path and combines it with the specific spatial coordinates of the equipment in the BIM model to determine which equipment will be submerged. Alternatively, it calculates the mechanical response of the equipment supports and connecting components based on the seismic parameters using a structural response analysis algorithm. Then, based on the equipment's vulnerability curve, it quantitatively assesses the probability and degree of damage to each critical piece of equipment, such as a high-voltage switchgear or a central air conditioning unit, generating a damage assessment result. The simulation depth does not stop at direct damage assessment but further uses the damage assessment result as a trigger event, based on the pre-defined energy network topology in the BIM model, to initiate a chain reaction failure propagation analysis process. This process constructs a directed graph model of the system, abstracting energy equipment as nodes and the dependencies of energy flow or signal flow as edges. It simulates the chain reaction process where the failure of a critical piece of equipment causes its load to transfer to adjacent equipment, potentially triggering other equipment to fail due to overload, thus depicting the propagation path and impact range of the failure in the energy network. By comprehensively assessing and visually analyzing the massive amounts of data generated throughout the simulation process, including direct equipment damage, changes in network connectivity, and areas of energy supply disruption, this module generates a disaster prediction report. This report not only identifies high-risk areas and key weak points, but also predicts the functional degradation trajectory and possible recovery time of the energy system under different disaster intensities.

[0025] The disaster prevention management module 103 is used to generate disaster prevention scheduling strategies based on disaster prediction reports.

[0026] For example, the disaster prevention management module 103 performs in-depth analysis of the disaster prediction report, identifying key trends in energy supply capacity, impending or existing supply gaps, and critical load areas requiring priority protection. Based on this information and a pre-built emergency response knowledge base, it automatically generates a disaster prevention dispatch strategy, forming a set of dispatch instructions including: starting standby generators, adjusting substation operation modes, shutting down ventilation systems in non-critical areas, and changing the gas supply path of gas pressure regulating stations. To ensure the feasibility and effectiveness of the dispatch strategy, the generated dispatch instruction set is immediately fed back to the digital twin for simulation verification and optimization iteration. These dispatch instructions are simulated in a virtual environment, observing the dynamic response of the entire energy system, evaluating whether the strategy can effectively isolate faults, restore power supply, or reduce risks, and fine-tuning the execution order and parameter settings of the instructions based on the simulation results to seek the optimal effect, thereby obtaining the disaster prevention dispatch strategy. Once the strategy is determined, it needs to be converted into a standardized control protocol that can be recognized and executed by various execution devices in the underground space. For example, the instruction to "close the water supply valve in area A" is converted into a data frame that conforms to the Modbus TCP or BACnet protocol specifications. These command data packets containing specific control parameters are reliably transmitted to the corresponding field execution devices through communication interfaces such as industrial Ethernet or wireless private networks. These devices include, but are not limited to, intelligent circuit breakers, electric regulating valves, variable frequency fans, and pump sets.

[0027] This creates a closed loop from decision-making to execution, enabling the underground space energy management system 100 based on digital twin technology to proactively and intelligently adjust the system's operating status before or during a disaster, maximizing energy supply security and mitigating potential losses.

[0028] This application provides an underground space energy management system based on digital twin technology. The system includes a data processing module, a disaster prediction module, and a disaster management module. The data processing module collects operational and deployment data of the underground space energy system and constructs a digital twin based on the operational data, deployment data, and a pre-set simulation model. The disaster prediction module simulates and extrapolates monitored disaster scenarios using the digital twin, generating a disaster prediction report. The disaster management module generates disaster prevention scheduling strategies based on the disaster prediction report. In this system, the simulation and extrapolation based on the digital twin by the disaster prediction module can quickly identify disaster scenarios and generate prediction reports, while the disaster management module can rapidly convert the prediction results into specific scheduling strategies and automatically distribute them to the execution equipment. This improves the system's adjustment efficiency and realizes a shift from a passive response to an active prediction management model. Through intelligent disaster prediction and automated scheduling execution, it provides efficient and accurate management methods for underground space energy systems, meeting the needs of modern underground space energy management for intelligence and rapid response.

[0029] To more clearly illustrate the technical solution of this application, the technical solution of this application will be described below through specific embodiments. It should be noted that the specific embodiments are used to expand the description of the technical solution of this application, and are not intended to limit this application.

[0030] In some embodiments, the simulation model includes a first BIM model and a GIS model. The first BIM model is a three-dimensional simulation model of the underground space. When the data processing module 101 collects operational and layout data of the energy system in the underground space and constructs a digital twin based on the operational data, layout data, and a pre-set simulation model, it specifically performs the following: Based on the layout data, it configures the equipment layout and pipeline connection relationships of the energy system in the BIM model to generate a second BIM model. Based on the operational data, it assigns operational logic to the energy system in the second BIM model to generate a third BIM model. It then performs coordinate registration between the third BIM model and the GIS model to construct a digital twin, with the digital twin using disaster prediction data provided by the GIS model as simulation boundary conditions.

[0031] For example, in the application of digital twins in underground commercial complexes, the data processing module 101 accurately configures the equipment layout and pipeline connections of energy systems such as power supply transformers, chillers, and ventilation equipment in a first BIM model containing a three-story underground structure based on deployment data, generating a second BIM model containing 1200 equipment nodes and a 3500-meter pipeline network. Subsequently, based on real-time collected operational data such as current, temperature, and pressure, the second BIM model assigns operational logic to each energy system, establishes control associations and energy consumption calculation models between equipment, and generates a third BIM model with dynamic simulation capabilities. Through GPS coordinate transformation and elevation correction algorithms, the third BIM model is coordinate-registered with a GIS model covering a surrounding 5 square kilometers, unifying the spatial benchmark and constructing a digital twin. The digital twin can receive disaster prediction data such as rainfall, seismic intensity, and surrounding fires provided by the GIS model as simulation boundary conditions, realizing the organic integration of spatial and energy information and improving the accuracy and intelligence level of underground space energy management.

[0032] In some embodiments, when the disaster prevention prediction module 102 is used to perform simulation and deduction of monitored disaster scenarios through digital twins and generate a disaster prevention prediction report, it specifically performs the following: Based on the GIS model, it obtains disaster scenario type and intensity parameters, and generates a disaster parameter set according to the disaster scenario type and intensity parameters. Based on the third BIM model, it simulates the direct impact of the disaster on the energy system according to the disaster parameter set and generates damage assessment results. Based on the third BIM model, it generates a disaster prevention prediction report according to the damage assessment results.

[0033] For example, a disaster impact assessment mechanism based on digital twins uses a GIS model to obtain typhoon disaster scenario types and intensity parameters, such as wind speed reaching level 12, rainfall intensity of 80 mm / h, and disaster duration of 6 hours, to generate a disaster parameter set, including: disaster level, impact range, and time series. Utilizing the 3D coordinates and attribute information of equipment in a third-party BIM model, the direct impact of the disaster on underground space energy systems such as power supply, ventilation, and water supply and drainage is simulated based on the typhoon path and intensity distribution in the disaster parameter set. Finite element analysis is used to calculate the stress on each piece of equipment and the risk of water ingress, generating damage assessment results covering equipment damage probability, functional degradation degree, and estimated repair time. Based on the damage assessment results, the energy supply interruption area and impact duration are analyzed, generating a disaster prevention prediction report including a disaster impact range map, equipment damage list, and energy supply capacity change curve. This report provides a scientific basis for emergency decision-making, enabling managers to understand the specific impact of the disaster on underground space energy supply 2-4 hours in advance, significantly improving the pertinence and effectiveness of disaster prevention plans.

[0034] In some embodiments, such as Figure 2As shown, when the disaster prediction module 102 is used to execute S21-S23 to simulate the direct impact of disasters on the energy system based on the third BIM model and the disaster parameter set, and generate damage assessment results, the specific steps are:

[0035] S21. In the third BIM model, determine the list of affected equipment based on the disaster scenario type. The list of affected equipment includes: energy equipment type and spatial scope.

[0036] For example, in a third-party BIM model, by comprehensively scanning and matching the spatial location and attributes of all energy equipment within the model, the types of energy equipment that may be directly exposed to flood disaster scenarios and their corresponding spatial ranges can be accurately identified. For instance, when simulating a flood disaster scenario, the third-party BIM model loads the three-dimensional geometric data and topology of the entire energy system, including energy equipment types such as transformers, distribution cabinets, drainage pumps, and cable joints. These energy equipment types are assigned detailed installation coordinates, altitude parameters, and waterproofing performance indicators. Then, based on the characteristics of the flood disaster scenario, such as the total rainfall of 200 mm per hour and the duration of 12 hours, the inundation impact of the flood path on each floor of the building in the third-party BIM model is calculated. By comparing these inundation data with the installation thresholds of each energy equipment type, high-risk markers are assigned. For example, distribution cabinets located in underground spaces below the flood level are marked as high-risk, while elevated ventilation equipment above 1.5 meters above ground requires an assessment of splash penetration effects, thus generating a list of affected equipment. This list of affected equipment not only identifies energy equipment types directly impacted by floods, such as emergency generators and control panels, but also precisely marks the spatial extent of each type. Furthermore, in the dynamic simulation environment of the third-party BIM model, this process of determining the affected equipment list can be integrated with real-time hydrological data interfaces. If the flood scenario involves upstream dam failure, the third-party BIM model will filter out energy equipment types, such as cooling towers and energy storage batteries, whose spatial extent is exposed to low-lying areas based on peak flow thresholds, such as 500 cubic meters per second. This list of affected equipment types is accompanied by water flow distribution maps to highlight vulnerable openings within the spatial extent, such as vents, thus providing a solid foundation for simulating diverse flood scenario types. The entire process is optimized through algorithmic iteration to ensure that the coverage of the affected equipment list reaches over 98%, avoiding the omission of any potential combinations of energy equipment types and spatial extents.

[0037] S22. Based on the list of affected equipment and strength parameters, calculate the damage coefficient and damage degree.

[0038] Through multiphysics coupling simulation, the damage coefficient and degree of damage of various energy devices within a specified spatial range are calculated to quantify the degradation of structure and function under preset disaster scenarios. Taking a flood scenario as an example, the input intensity parameters include a water level of 4.0 meters and a flow velocity of 3.0 meters per second to the fluid dynamics module. Hydrodynamic analysis is performed on equipment such as submerged transformers and drainage pumps, and the water flow impact force is solved using the finite element method. The damage coefficient is defined as the ratio of the equipment's waterproof rating to the actual exposure intensity. For example, for underground cable joints located in low-lying areas, the IP65 rating is compared with a water depth of 4.0 meters, resulting in a damage coefficient of 0.85, indicating an 85% potential probability of damage. For overhead distribution cabinets, the water flow impact pressure is estimated to be 20 kPa using Bernoulli's equation, with a damage coefficient of 0.55.

[0039] The damage severity is further divided into five gradient levels, from slight dampness to complete short circuit. Combining Monte Carlo simulations, and considering random fluctuations in intensity parameters (such as the uncertainty of water level within ±0.3 meters), a probability distribution map is generated. For example, a control panel in a confined space is rated as "moderate immersion," with an expected 50% loss of functionality. This calculation comprehensively considers equipment material properties (such as the corrosion resistance of the aluminum alloy casing) and spatial geometric factors (such as the amplification effect of gap area on water ingress), improving the robustness of the results. Furthermore, this method supports multi-intensity parameter overlay analysis; for example, when flooding is accompanied by increased pollutant concentration, the damage coefficient can be increased by 20%, and the damage severity can be adjusted to "severe corrosion" to reflect the complexity of the disaster and provide a basis for protective design.

[0040] S23. Generate damage assessment results based on the damage coefficient and damage degree.

[0041] Based on the obtained damage coefficient and damage degree, damage assessment results are generated using visualization tools and risk quantification indicators of the third BIM model. For example, for a foundation submerged drainage pump with a damage coefficient of 0.9, the damage degree is "severe short circuit," and the damage assessment results include: a 90% failure rate, a 150-day repair cycle, and a backup isolation threshold; while for a wall-mounted sensor with a damage coefficient of 0.2, the damage degree is "minor splashing," and the assessment results show a 10% probability of functional interruption without requiring major intervention.

[0042] This generation mechanism employs a threshold mapping algorithm to transform damage data into actionable indicators, such as identifying high-risk areas using heatmaps and outputting economic loss estimates (e.g., 8 million yuan) and recovery timelines. For different damage levels, the assessment results include specific response measures; for example, fully submerged transformers require immediate power disconnection, and the assessment results include a 72-hour power outage duration and a list of replacement parts. For equipment with damp surfaces, a drying protocol is recommended to prevent secondary corrosion. The entire process is concise and data-driven, supporting output in formats such as XML, facilitating system integration, and providing reliable quantitative support for flood disaster prediction.

[0043] This allows for the assessment of the specific impact of floods on various energy equipment in underground spaces, providing a scientific and quantitative basis for developing equipment protection measures and emergency repair plans, and effectively improving the targeted nature of risk management for energy equipment under flood conditions.

[0044] S11. In some embodiments, when the disaster prevention prediction module 102 is used to generate a disaster prevention prediction report based on the damage assessment results using a third BIM model, it specifically performs the following: In the third BIM model, it determines the fault propagation path based on the damage assessment results. It then generates a disaster prevention prediction report based on the fault propagation path.

[0045] For example, in the third BIM model, the transformer damage in the main power distribution room of the underground space is identified as a critical fault point based on the damage assessment results. The propagation path of the fault's impact is traced through the network connections of the power system, determining the sequence of power outages that will sequentially affect downstream equipment such as secondary distribution cabinets, lighting circuits, ventilation equipment, and fire pumps, forming a fault propagation path covering 15 key nodes. Based on the connection strength and propagation time of each node in the fault propagation path, it is predicted that the power outage will expand to 70% of the underground space within 30 minutes, and affect ventilation and fire protection functions after 60 minutes. A disaster prevention prediction report is generated, which clearly shows the chain reaction process and final impact range triggered by the disaster. This provides important reference for developing tiered response strategies and optimizing emergency resource deployment, enabling emergency management personnel to accurately grasp the evolution pattern of the fault.

[0046] In some embodiments, when the disaster prevention management module 103 is used to execute the disaster prevention dispatch strategy generated based on the disaster prediction report, it specifically performs the following: based on the energy supply capacity change trend in the disaster prediction report, it formulates an emergency energy supply plan and equipment switching sequence, and generates a dispatch instruction set. The dispatch instruction set is then converted into a standardized control protocol and sent to the execution equipment in the energy system via a communication interface.

[0047] For example, based on the predicted energy supply trend in the disaster prevention forecast report—that the underground space's power supply capacity will decrease to 40% of normal levels within two hours after a disaster—an emergency energy supply plan is formulated, including starting backup diesel generators, switching to emergency lighting mode, and shutting down non-critical equipment loads. The plan also prioritizes the switching sequence of fire-fighting equipment, ventilation equipment, and emergency lighting, generating a set of dispatch instructions for specific operations. This dispatch instruction set is converted into a standardized control protocol via the Modbus communication protocol and distributed to various execution devices distributed across the three underground levels via an Ethernet communication interface. Specifically, circuit breakers receive switching commands, valves adjust their opening and closing degrees, fans adjust their speed parameters, and pump sets modify their operating pressure setpoints. The entire command issuance and execution process is completed within three minutes, achieving fully automated closed-loop control from disaster prediction to emergency response. This significantly shortens emergency response time and improves the energy supply guarantee capability of underground spaces during disasters.

[0048] In some embodiments, the energy system includes at least one of a power supply and distribution system, a heating, ventilation and air conditioning system, and a gas system, and the actuators include at least one of a circuit breaker, a valve, a fan, and a pump unit.

[0049] In some embodiments, such as Figure 3 As shown, in the third BIM model, the fault propagation path is determined based on the damage assessment results, specifically for execution: S31-S33.

[0050] S31. In the third BIM model, a directed graph model is constructed based on the equipment layout and pipeline connection relationship of the energy system. The directed graph model includes multiple equipment nodes.

[0051] For example, in the third BIM model, equipment layout data and pipeline connection relationship data of the energy system are extracted. The equipment layout data includes the location coordinates and geometric attributes of the energy equipment, and the pipeline connection relationship data includes the connection direction and flow path between the energy equipment. Based on the equipment layout data and pipeline connection relationship data, the energy equipment is mapped as equipment nodes, and directed edges are defined according to the pipeline connection relationship data. Directed edges represent unidirectional dependencies or flow relationships between energy equipment. By integrating the equipment nodes and directed edges, a directed graph model is constructed.

[0052] In the third BIM model, the equipment layout of all energy devices is obtained by parsing the model's geometric layers and attribute database. For example, the transformer is located at coordinates (10, 15, 2) meters and its geometric attributes include a volume of 2 cubic meters. Simultaneously, pipeline connection data is extracted from the connection topology, including: a 50-meter unidirectional flow path for cable conduits from the generator set to the distribution cabinet, and a flow rate of 100 liters per minute for valve-controlled cooling conduits from the pump station to the air conditioning unit. This extraction process also incorporates semantic tags from the BIM model, such as labeling pipeline connection data as high-pressure or low-pressure types to distinguish critical dependencies between energy devices. For instance, during extraction, the total number of pipeline connections is calculated to be up to 150, ensuring coverage of the entire energy system's branch structure and avoiding omissions of implicit paths such as backup power lines to emergency lighting equipment. The entire process of extracting equipment layout and pipeline connection data is accelerated through a gridded index, achieving millisecond-level response times to support real-time flood spread simulation. Based on the extracted equipment layout data and pipeline connection data, the process of mapping energy equipment to equipment nodes involves converting each energy device into a graph theory entity, where each equipment node is assigned a unique identifier. Simultaneously, directed edges are defined according to the pipeline connection data. For example, a directed edge from a generator node to a distribution cabinet node has a transmission efficiency weight of 0.95, representing unidirectional power flow, while a directed edge from a drainage pump node to a cooling tower node is labeled with water flow directionality to reflect potential backflow risks under flood scenarios. These definitions of equipment nodes and directed edges are initialized in the third BIM model using an adjacency matrix. During the mapping process, the spatial proximity of the equipment layout data is also considered. For example, energy equipment nodes less than 3 meters apart are clustered into subgraphs to optimize the impact assessment of pipeline connection data at a flood level of 4.0 meters. Furthermore, when defining directed edges, if the pipeline connection data involves vulnerable PVC materials, a vulnerability coefficient of 0.7 is added to the directed edges, making the relationships between equipment nodes more disaster-sensitive. By integrating the aforementioned device nodes and directed edges, the process of constructing a directed graph model assembles these elements into a unified network representation. The directed graph model is centered around device nodes, with directed edges linking them to form the complete topology of the energy system. This construction process employs graph embedding technology in the third-party BIM model, projecting the three-dimensional coordinates of the device layout data onto the two-dimensional directed graph model plane, highlighting its role in the energy system. The entire operation integrating device nodes and directed edges outputs an adjacency list format for the directed graph model, ensuring rapid path traversal in disaster simulations to predict the cascading effects of flood disruptions.

[0053] S32. Calculate the failure probability of the equipment node based on the damage assessment results. The specific calculation formula is as follows: ; Where Pf(j) is the probability that node j becomes a node in the fault propagation path. Ds(j) is the damage state coefficient of node j, ranging from [0,1], where 0 represents intact and 1 represents completely damaged. ηj is the vulnerability index of node j, ranging from [0.5,3.0], determined according to the node type and importance. k is the total number of faulty nodes connected to node j. Df(i) is the degree of damage of the faulty node i. Tij is the transmission coupling coefficient between node i and node j, ranging from [0,1], determined according to the energy transmission capacity between nodes. dij is the network distance between node i and node j. σ is the fault propagation attenuation constant.

[0054] This formula not only considers the direct impact of node j's own damage state coefficient Ds(j) and vulnerability index ηj on the failure probability, but also comprehensively evaluates the indirect impact of failed nodes connected to it on itself through a product term. Here, the transmission coupling coefficient Tij quantifies the energy dependence strength between nodes, while the exponential decay term... It also takes into account the natural attenuation of fault impact with network distance, thus comprehensively improving the accuracy of fault node identification.

[0055] S33. Set the device nodes with a failure probability greater than the preset probability threshold as failure nodes, and determine the failure propagation path based on the failure nodes.

[0056] For example, when the calculated failure probability exceeds a preset probability threshold, such as 0.6 of the preset probability threshold, the corresponding device node is identified as a failure node and included in the failure propagation path.

[0057] This probabilistic model-based fault identification method significantly improves the accuracy and reliability of fault prediction, enabling managers to grasp the propagation direction and impact range of faults in the energy network in advance, and improving the intelligence level and disaster prevention capabilities of underground space energy management.

[0058] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An underground space energy management system based on digital twin technology, characterized in that, include: The data processing module is used to collect operational and deployment data of the energy system in the underground space, and to construct a digital twin based on the operational data, the deployment data, and a pre-set simulation model. The disaster prevention and prediction module is used to simulate and extrapolate the monitored disaster scenarios through the digital twin and generate a disaster prevention and prediction report; The disaster prevention management module is used to generate disaster prevention scheduling strategies based on the disaster prediction report.

2. The underground space energy management system based on digital twin technology as described in claim 1, characterized in that, The simulation model includes a first BIM model and a GIS model. The first BIM model is a three-dimensional simulation model of the underground space. When the data processing module collects operational and deployment data of the energy system in the underground space and constructs a digital twin based on the operational data, the deployment data, and the pre-set simulation model, it specifically performs the following: Based on the deployment data, the equipment layout and pipeline connection relationship of the energy system are configured in the BIM model to generate a second BIM model; Based on the operational data, the energy system is assigned operational logic in the second BIM model to generate a third BIM model; The third BIM model and the GIS model are coordinate registered to construct a digital twin, which uses the disaster prediction data provided by the GIS model as the simulation boundary conditions.

3. The underground space energy management system based on digital twin technology as described in claim 2, characterized in that, When the disaster prevention prediction module is used to simulate and extrapolate the monitored disaster scenarios through the digital twin and generate a disaster prevention prediction report, it is specifically used to perform the following: Based on the GIS model, disaster scenario types and intensity parameters are obtained, and a disaster parameter set is generated according to the disaster scenario types and intensity parameters. Based on the third BIM model, the direct impact of disasters on the energy system is simulated according to the disaster parameter set, and damage assessment results are generated. Based on the third BIM model, a disaster prevention prediction report is generated according to the damage assessment results.

4. The underground space energy management system based on digital twin technology as described in claim 3, characterized in that, When the disaster prevention and prediction module is used to simulate the direct impact of disasters on the energy system based on the third BIM model and the disaster parameter set, and to generate damage assessment results, it is specifically used to perform the following: In the third BIM model, a list of affected equipment is determined based on the disaster scenario type. The list of affected equipment includes: energy equipment type and spatial range. Based on the list of affected equipment and the strength parameters, the damage coefficient and the degree of damage are calculated; Damage assessment results are generated based on the damage coefficient and the damage degree.

5. The underground space energy management system based on digital twin technology as described in claim 3, characterized in that, When the disaster prevention prediction module is used to generate a disaster prevention prediction report based on the damage assessment results using the third BIM model, it specifically performs the following: In the third BIM model, the fault propagation path is determined based on the damage assessment results; A disaster prevention prediction report is generated based on the described fault propagation path.

6. The underground space energy management system based on digital twin technology as described in claim 1, characterized in that, The disaster prevention management module is used to execute the disaster prevention scheduling strategy generated based on the disaster prediction report, specifically for the following purposes: Based on the energy supply capacity change trend in the disaster prevention prediction report, an emergency energy supply plan and equipment switching sequence are formulated, and a dispatch instruction set is generated. The scheduling instruction set is converted into a standardized control protocol and sent to the execution equipment in the energy system through a communication interface.

7. The underground space energy management system based on digital twin technology as described in claim 1, characterized in that, The energy system includes at least one of a power supply and distribution system, a heating, ventilation and air conditioning system, and a gas system, and the actuators include at least one of a circuit breaker, a valve, a fan, and a pump set.

8. The underground space energy management system based on digital twin technology as described in claim 5, characterized in that, In the third BIM model, the fault propagation path is determined based on the damage assessment results, specifically for the following purposes: In the third BIM model, a directed graph model is constructed based on the equipment layout and pipeline connection relationship of the energy system. The directed graph model includes multiple equipment nodes. The failure probability of the device node is calculated based on the damage assessment results, using the following formula: ； Where Pf(j) is the probability that node j becomes a node in the fault propagation path; Ds(j) is the damage state coefficient of node j; ηj is the vulnerability index of node j; k is the total number of faulty nodes connected to node j; Df(i) is the damage degree of the faulty node i; Tij is the transmission coupling coefficient between node i and node j; dij is the network distance between node i and node j; σ is the fault propagation attenuation constant. The device nodes whose failure probability is greater than a preset probability threshold are set as failure nodes, and the failure propagation path is determined based on the failure nodes.

Images