Comprehensive transportation junction emergency scene simulation deduction system based on digital twinning

Abstract

The invention discloses a comprehensive transportation junction emergency scene simulation deduction system based on digital twinning, which relates to the technical field of digital simulation and comprises a data processing unit, a simulation deduction unit and a visual display unit, the data processing unit is used for acquiring emergency scene basic data of the target digital twin comprehensive transportation hub, performing multi-source integration on the basic data and constructing a model data environment; the simulation deduction unit calls a simulation deduction algorithm to construct a simulation deduction algorithm model according to the emergency scene model data, and carries out emergency situation deduction and scheduling processing based on the simulation deduction algorithm model; and the visual display unit is used for carrying out distribution management on user permissions, carrying out deduction data plotting based on GIS map basic information, and carrying out query and visual display on the deduction data according to a query instruction of a user. According to the method, a digital twinborn platform is built based on a simulation deduction algorithm model and dynamic data, so that the deduction process is more accurate, and visual display is realized in combination with GIS map data.

Description

Technical Field

[0001] The present invention relates to the technical field of digital simulation, and particularly relates to a comprehensive transportation hub emergency scenario simulation and deduction system based on digital twin. Background Art

[0002] Public transportation hubs are all characterized by large scale, numerous facilities, and compact layout. Inside the hub, the flow of people is intensive, the passenger flow organization is complex, and there are many transportation modes. Once an emergency occurs, if the evacuation is not timely, serious accidents may be caused. Existing research on public transportation scheduling for public transportation hubs mostly focuses on the decision-making requirements of daily operations, but the research on emergency collaborative scheduling in abnormal scenarios such as emergencies, technical failures, service interruptions, natural disasters, and accident disasters is still insufficient.

[0003] The emergency scenario simulation of a comprehensive transportation hub is a simulation system for specific emergency scenarios and their handling processes inside the hub. Although it has the advantages of strong flexibility and high intervenability, the current traffic emergency scenario simulation systems generally have problems such as non-standard element representation and insufficient simulation environment fidelity, resulting in difficulties in accurately deducing the evolution of the situation and being unable to effectively reflect the evolution mechanism of emergencies and the impact of handling decisions on the evolution process of the emergency situation. Summary of the Invention

[0004] In view of this, the present invention provides a comprehensive transportation hub emergency scenario simulation and deduction system based on digital twin. The system constructs an information model of all elements of the transportation hub entity, creates a digital twin simulation and deduction platform, and realizes the dynamic matching call and correlation analysis of the deduction model, thereby completing the emergency situation deduction and scheduling and handling. The system breaks through two major bottlenecks of the existing traffic emergency simulation technology: firstly, the lack of standardized element representation and high-fidelity simulation environment; secondly, it is difficult to accurately deduce the evolution process of the situation and effectively quantify the evolution mechanism of emergencies and the real-time impact of handling decisions.

[0005] To achieve the above object, the present invention provides the following technical solutions: A comprehensive transportation hub emergency scenario simulation and deduction system based on digital twin, whose core is to improve the emergency response efficiency through high-precision simulation in the virtual space. The system consists of three core modules: a data processing unit, a simulation and deduction unit, and a visualization display unit. Each module collaborates to achieve data-driven intelligent decision support.

[0006] The data processing unit is responsible for building the data foundation of the digital twin, which is used to obtain the basic data of the emergency scenarios of the target digital twin integrated transportation hub, and perform multi-source integration on the basic data to build a model data environment. During this process, the policy training module set in the data processing unit uses historical sample data and simulation feedback to train and generate a policy model based on the reinforcement learning algorithm, providing intelligent scheduling support for the subsequent simulation deduction process. The simulation deduction unit is used to call the simulation deduction algorithm according to the emergency scenario model data to build a simulation deduction algorithm model, and conduct emergency situation deduction and scheduling disposal based on the model. At the same time, the system combines the policy model output by the policy training module to dynamically optimize the response policies during the deduction process, improving the system response efficiency and decision-making quality. Specifically, the policy model is integrated into the deduction process as an auxiliary decision-making module. The system inputs the current scenario state into the policy model within each deduction process, and the model outputs recommended response policies, such as evacuation route plans and resource scheduling sequences, which, together with the simulation deduction results, are used as decision-making bases and input into the scheduling module to enhance the rationality of policy selection and the system response results. The policy model can output response policies at multiple granularities, including resource scheduling sequences at the tactical level, evacuation route guidance at the operation level, area lockdown plans, and information broadcast priority rankings. The system automatically screens and executes the most suitable combination of policy actions according to the response objectives. The visualization display unit is used to allocate and manage user permissions, plot deduction data based on the basic GIS map information, and also used to query and visually display the deduction data according to the user's query instructions and conditions. The visualization display unit also supports visualizing the results of the response plans output by the policy model, displaying recommended routes, scheduling priorities, and comparative analysis charts with actual scheduling plans, assisting users in understanding the basis of model recommendations and improving the efficiency of human-machine collaborative decision-making.

[0007] Furthermore, the data processing unit includes a basic data module, a data integration module, a feature modeling module, and a policy training module; The basic data module is used to collect multi-source data from the infrastructure layer of the transportation hub according to the established data model, and build a basic database based on the data resources. The multi-source data includes map basic data (GIS vector data, satellite images), Internet of Things perception data (equipment status, environmental parameters), and interaction data (passenger flow statistics). And build a basic database covering all elements such as buildings, roads, and equipment based on this data.

[0008] The data integration module is connected to the basic data module. The data integration module is used to integrate multi-source data and implement an eight-dimensional data processing process, including: cleaning, classification, coding, mapping, marking, fusion, pattern mining, and spatio-temporal analysis, which are used to remove noise data, divide by traffic elements, unify semantic identifiers, convert spatial coordinates, annotate metadata, align multi-source data, passenger flow spatio-temporal patterns, etc., and store the integrated processed data in the core database; The element modeling module is used to represent all elements of the transportation hub as an information model, aiming to achieve business functions, and construct a digital twin information model library for the hub.

[0009] Based on the multi-source data environment output by the data integration module and the element modeling module in the data processing unit, the policy training module uses reinforcement learning algorithms to perform training tasks in the constructed simulation environment. Specifically, in each round of training, the system first sets the current scenario state, including state parameters such as passenger flow density, channel occupancy rate, and warning level; the policy model selects scheduling actions (such as evacuation route adjustment, traffic resource allocation plan, etc.) according to the current state; the simulation environment executes the action and generates feedback results, such as handling time consumption, congestion index change, etc.; the system uses the feedback information as a reward signal to update the policy model parameters, and iteratively executes multiple rounds of training processes to continuously improve the response ability and policy effect of the policy model in complex emergency scenarios. The input parameters of the current scenario further include quantifiable structured input features, such as spatial density distribution, equipment operation status, channel accessibility, and regional risk level. The system continuously updates the state vector within the deduction cycle to drive the policy model to generate corresponding response policies. The policy model can be constructed based on value function approximation methods (such as deep Q-network) or policy gradient algorithms (such as PPO). Through the cumulative learning of state transition samples, the policy behavior function is iteratively optimized to achieve dynamic response capabilities in complex simulation environments.

[0010] Furthermore, the digital twin information model library for the hub includes a model database, a rule relationship database, and an algorithm database; the model database is used to store the model number, model type, model name, scenario event or disposal event number to be matched, algorithm name, and storage location of the information model, the rule relationship database is used to store the relationship rule data for connecting models, and the algorithm database is used to store the scenario event evolution model, the scheduling and disposal event model, and the policy model obtained by the policy training module.

[0011] Furthermore, the simulation and deduction unit includes an emergency situation awareness module, a model matching module, and a deduction and simulation module; The emergency situation awareness module is used to parse the integrated processed data and extract scenario events and event object parameters (such as fire location, passenger flow density) to obtain emergency scenario model data; The model matching module is connected to the emergency situation awareness module. The model matching module is used to match and call the simulation deduction algorithm model according to the emergency scenario model data. The simulation deduction algorithm model performs response processing according to the data processing requirement signal. Among them, in addition to using the improved KNN algorithm for dynamic matching of the algorithm model, a policy matching mechanism based on the reinforcement learning model is introduced. By constructing a state-policy mapping relationship, the policy category to which the current scenario belongs is judged based on real-time scenario parameters (such as time type, influence range, resource status, etc.), and the optimal matching solution is output by the policy model, and the corresponding simulation deduction algorithm model combination is selected; after the deduction is executed, the system records feedback indicators such as deduction deviation and resource scheduling efficiency, and updates the policy model based on the feedback to continuously optimize the policy matching behavior, so as to improve the accuracy of model selection and the response adaptation of combined deduction.

[0012] The deduction simulation module is connected to the model matching module. The deduction simulation module is used to input the event data under different emergency scenarios as the simulation deduction node conditions into the corresponding simulation deduction algorithm model, obtain the event evolution model file and the event disposal model file, and establish an evolution sequence according to the time sequence. In each deduction cycle, all the simulation deduction algorithm models in the evolution sequence are operated, the file information is analyzed and processed, and the deduction result of the event data under different scenarios relative to the simulation deduction algorithm model is determined according to the analysis and processing result. Based on the deduction result and the preset deduction result data, the simulation deduction algorithm model is optimized. At the same time, the policy training module in the data processing unit can continuously optimize the policy model based on the feedback data in the deduction simulation process, improve the accuracy and stability of its policy output, and build an evolutionary deduction optimization system with adaptive capabilities. To ensure the stability of the system, when the solution output by the policy model does not meet the preset safety constraint conditions, or there is an obvious conflict with the expert policy configured manually, the system will automatically switch to the default scheduling solution or the manual review mode to ensure the controllability and fault tolerance of key emergency behaviors.

[0013] Furthermore, the simulation deduction unit also includes a deduction control module and a message management module; the deduction control module is used to control the time and step size of the deduction, and schedule the model database according to the feedback message (load / unload the model); the message management module is implemented by using the message queue mechanism, and is used to record the data results of the emergency scenario simulation deduction, and perform information interaction with the visualization display unit and the traffic department to ensure the accurate transmission and sharing of information; and further perform policy evaluation and learning on the key decision points in the deduction process based on the reinforcement learning algorithm, specifically including: Construct a policy training model during the data processing stage, and use historical simulation data and multiple rounds of simulation interactions to perform reinforcement learning training in the simulation environment to generate a policy model with adaptive scheduling capabilities; this model is iteratively optimized based on the trial-and-error feedback in the simulation environment and is trained using reinforcement learning algorithms such as deep Q-network or proximal policy optimization, aiming to improve the policy selection ability for complex emergency scenarios; During the deduction process, the system calls the policy model to evaluate policy selection according to the current environmental state (such as channel occupancy, equipment availability, passenger flow density, etc.), and selects an optimal solution from alternative response plans such as evacuation route optimization, resource scheduling order, and traffic control measures; After the deduction is executed, the system records the feedback results, including indicators such as response efficiency and risk suppression degree, and uses this as an updated sample to continuously update the policy model parameters; By constructing a self-learning closed-loop of "policy training - policy application - feedback optimization", the adaptability of the system to dynamic scenarios and the intelligent level of emergency decision-making are improved. The policy model runs through each stage of data training, simulation deduction, and optimization feedback in the system and is dynamically called by each module of the system as the core intelligent agent, which not only improves the real-time performance and accuracy of policy selection but also enhances the overall closed-loop intelligent control ability of the system.

[0014] Furthermore, perform a situation assessment based on the deduction model optimized from the model. The situation assessment process includes: Input the event data in the emergency scenario as the node conditions of the simulation deduction algorithm model. At the same time, for some scenarios, use the simulation deduction model generated based on the reinforcement learning strategy to achieve more flexible and intelligent response scheduling, improve the ability to respond to complex emergency situations, and establish an evolution sequence according to the time sequence. In each deduction cycle, perform operations on all simulation deduction algorithm models in the evolution sequence; After the resources arrive during the event disposal, feedback the emergency scenario information to the simulation deduction algorithm model for processing, and judge whether there is an evolution. If so, generate corresponding new scenario events according to the deduction results and the relationship rules connected between the models and add them to the evolution sequence for the current emergency situation assessment. Otherwise, directly perform the current emergency situation assessment and update the situation of the organization, resources, and environment.

[0015] Furthermore, the visualization display unit includes a map basic information management module, a query and statistics module, and a data plotting and display module; The basic map information management module is used to manage basic map data and pre-process basic map data according to the actual needs of emergency scenario simulation. The pre-processing includes map clipping, adding and editing layer attributes, performing topological operations based on the roads and spatial locations of transportation hubs and building a topological network based on the operation results, publishing map services, classifying layers according to the set categories and layer names to form a tree diagram, storing the tree diagram in the core database, and adding deduction elements to the map layer according to the element attributes; the query statistics module supports querying deduction data according to time range, geographic location, data type and other conditions, and performs statistical analysis on the query results to generate charts and reports. The data plotting and display module plots the deduction data on the map in real time, supports multi-layer overlay display, and sorts and displays data according to information priority (such as the urgency of the event).

[0016] Furthermore, the visualization display unit also includes a user management module, which is used to match corresponding role permissions according to user basic information.

[0017] The basic map information management module implements topological operations to construct a three-dimensional road network and publishes WMTS map services, supporting dynamic layer rendering (heat map / trajectory flow). The data plotting and display module uses a priority algorithm to display key information (red warnings are automatically pinned to the top), supports three-dimensional model overlays, and the query statistics module provides a natural language query interface. The user management module can configure role permissions based on the RBAC model, supporting: commanders (situation overview), operators (equipment control), etc.

[0018] It can be seen from the above technical solution that the advantages of the present invention are: 1. The present invention builds a digital twin platform based on simulation deduction algorithm models and dynamic data, integrates data processing and element modeling, makes element representation more standardized, and creates a more realistic simulation environment. It also realizes a more accurate emergency simulation situation deduction process based on model connection relationships and derivative relationships, and also realizes data visualization display in combination with GIS map data, which intuitively reflects the evolution mechanism of emergencies and the impact of disposal decisions on the evolution process of emergency situations. At the same time, by introducing a reinforcement learning model, the system can continuously train through historical data and simulation feedback, optimize emergency response strategies in each deduction cycle, and further improve the decision-making accuracy and flexibility in the emergency simulation process.

[0019] 2. The automatic combination and evolution of models are realized through a rule engine, breaking through the static model limitations of traditional systems, and establishing a closed loop of "perception - deduction - feedback - optimization". According to real-time data, the model parameters are dynamically corrected to improve the prediction accuracy. The reinforcement learning model plays a key role in this closed loop. Through continuous feedback learning, it intelligently adjusts the emergency response strategy, enabling the system to better handle different emergency scenarios and automatically optimize the simulation and deduction process. By integrating BIM + GIS, two-way mapping between the physical space and the virtual model and multi-physical field coupling simulations of the pedestrian flow field, vehicle flow field, and structural stress field are achieved, providing the comprehensive transportation hub with the ability of emergency management throughout the life cycle, significantly improving the response efficiency and disposal accuracy of emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention.

[0021] Figure 1 It is a schematic structural diagram of the present invention.

[0022] Figure 2 It is a schematic diagram of the overall framework structure of this embodiment.

[0023] Figure 3 It is a schematic structural diagram of the data processing unit of the present invention.

[0024] Figure 4 It is a schematic structural diagram of the simulation and deduction unit of the present invention.

[0025] Figure 5 It is a schematic structural diagram of the visualization display unit of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To make the purpose, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. Here, the schematic embodiments of the present invention and their descriptions are used to explain the present invention, but do not serve as a limitation of the present invention.

[0027] This system adopts a hierarchical architecture, as Figure 2As shown in the figure, the bottom layer is the data perception layer (data processing unit), which integrates Internet of Things data of infrastructure, data of operation management systems, and environmental perception data. The middle layer is the simulation application layer (simulation deduction unit), which includes an emergency situation perception engine, a dynamic model matching library, and a cross-time-and-space deduction kernel. The top layer is the interactive service layer (visualization display unit), which provides a GIS spatio-temporal visualization interface, a multi-role permission management system, and a situation assessment dashboard. Each unit communicates through standardized interfaces to ensure the flexibility of module replacement and horizontal expansion. The overall system follows the digital twin concept and improves the efficiency and accuracy of emergency response through simulation in the virtual space. Refer to Figures 1 to 5 , this embodiment provides a comprehensive transportation hub emergency scenario simulation deduction system based on digital twins. Among them, the application of digital twin technology in the emergency scenario simulation deduction of comprehensive transportation hubs is mainly embodied as a highly integrated and intelligent simulation method, which improves the efficiency and accuracy of emergency response through simulation in the virtual space. As Figure 1 and Figure 2 shown, the system specifically includes: a data processing unit, a simulation deduction unit, and a visualization display unit. Among them, the data processing unit is used to obtain the basic data of the emergency scenario of the target digital twin comprehensive transportation hub, perform multi-source integration on the basic data, and build a model data environment.

[0028] Specifically, as Figure 3 shown, the data processing unit includes a basic data module, a data integration module, and a feature modeling module; the basic data module is used to establish a digital twin model based on the hub physical entities (such as buildings, roads, equipment, etc.). Then data collection is carried out, and the collected data includes map basic data: GIS geospatial data, terrain elevation data, etc.; interactive data: such as pedestrian and vehicle flow dynamic data; Internet of Things perception data: such as real-time monitoring data of sensors, cameras, and fire-fighting equipment. Finally, a basic database is established to store the original data, providing a basis for subsequent processing.

[0029] The data integration module is connected to the basic data module. The data integration module is used for multi-source data integration, integrating multi-source heterogeneous data such as BIM models, GIS data, video images, and Internet of Things perception data, and performing data cleaning to remove noise and incorrect data; classification and coding, classifying according to data types (such as structured data and unstructured data) and unifying the coding format; mapping and tagging, mapping the data to a unified coordinate system and adding metadata tags; fusion, fusing data from different sources (such as BIM and GIS) to form a complete data environment; rule mining and spatio-temporal analysis, mining data rules through machine learning algorithms and analyzing spatio-temporal correlations. Based on the complete data environment constructed by the data integration module, the system further extracts key data dimensions, such as map basic data, Internet of Things perception data, and interaction data, and constructs the data input set required by the strategy training module. Based on this input set, the strategy training module sets initial state parameters, such as passenger flow density, equipment operation status, and regional risk level, to generate a preliminary strategy model for the deduction and simulation module to generate and verify emergency response strategies.

[0030] The element modeling module is used to abstract the physical entities (such as buildings, roads, and equipment) of the transportation hub into information models, aiming to achieve business functions, and construct a hub digital twin information model library. The hub digital twin information model library includes: a model database: storing model numbers, types, model names, and associated algorithms; a rule relationship database: storing the rule data for connecting models (such as model combinations and evolution rules); an algorithm database: storing the algorithms of scenario event evolution models and scheduling and handling models. The reinforcement learning module automatically optimizes the rules and relationships in the model library according to real-time scenario feedback. The system continuously adjusts the model parameters related to events through reinforcement learning, enabling the system to respond to emergencies more accurately, dynamically adjusting models related to traffic flow, equipment scheduling, etc., thereby improving the accuracy and efficiency of emergency management. Among them, the data resources at the infrastructure layer include map basic data, interaction data, and Internet of Things perception data. The hub digital twin information model library includes a model database, a rule relationship database, and an algorithm database; the model database is used to store the model number, model type, model name, scenario event or handling event number to be matched, algorithm name, and storage location of the information model.

[0031] Since it is necessary to obtain multiple types of data of the target integrated transportation hub when simulating the emergency scenario of the target integrated transportation hub, it is necessary to perform data processing tasks and build a data environment first. Specifically, it is necessary to load the building information data model (Building Information Modeling, BIM) used for the simulation of emergency scenarios of integrated transportation hubs, multi-regional geographic information system GIS data and basic data files. Among them, the basic data files include video image data, building element models, road traffic element models, terrain site models, vegetation element models, space facility element models and logos, production information and IoT perception data, as well as data model connection relationships.

[0032] The simulation deduction unit is connected to the data processing unit. The simulation deduction unit is used to call the simulation deduction algorithm according to the emergency scenario model data to build a simulation deduction algorithm model, and perform emergency situation deduction and dispatch disposal based on the simulation deduction algorithm model. Among them, the strategy training module, as one of the core components of the simulation deduction unit, uses the emergency scenario model data generated by the data processing unit to build a preliminary strategy model, and continuously optimizes the strategy parameters through feedback during the deduction process to improve the dynamic response capability of the model. The emergency scenarios include abnormal scenarios such as technical failures, service interruptions, natural disasters, accidents and disasters, and emergencies. Among them, emergencies refer to public health, social security and other events that occur suddenly and cause or may cause serious social harm, and emergency measures need to be taken to deal with them. According to the hub management needs, analysis algorithms are provided in scenarios such as daily passenger capacity guarantee, extreme weather, fire accidents, large passenger flow evacuation, and abnormal data analysis. Provide a "simulation mode" function, which can input all relevant data through a combination of automatic and manual methods. Through the simulation algorithm, the system gives a simulation screen and corresponding data.

[0033] Specifically, Figure 4 As shown, the simulation and deduction unit includes an emergency situation awareness module, a model matching module and a deduction and simulation module.

[0034] The emergency situation awareness module is mainly used for data analysis, analyzing the integrated processed data, extracting scene events and event object parameters, and converting the analyzed data into emergency scene model data that can be used for simulation deduction; the model matching module is connected to the emergency situation awareness module. The model matching module mainly involves algorithm model matching and response processing. Algorithm model matching is to match and call the corresponding simulation deduction algorithm model from the algorithm database according to the emergency scene model data. Response processing is that the simulation deduction algorithm model responds to the data processing demand signal and prepares for deduction calculation.

[0035] The deduction simulation module is connected to the model matching module. The deduction simulation module involves steps of event data input, deduction calculation, and model optimization. Event data input mainly takes event data under different emergency scenarios as simulation deduction node conditions and inputs them into the algorithm model. Deduction calculation includes an event evolution model and an event handling model. The event evolution model: simulates the development process of an event over time (such as fire spread, passenger flow aggregation). The event handling model: simulates the intervention effect of emergency measures on the event (such as evacuation plans, traffic control). Finally, based on the deduction results and preset data, the algorithm model is optimized and adjusted. The specific process of deduction simulation is to take event data under different emergency scenarios as simulation deduction node conditions and input them into the corresponding simulation deduction algorithm model, obtain the event evolution model file and the event handling model file, and establish an evolution sequence according to the time sequence. In each deduction cycle, all simulation deduction algorithm models in the evolution sequence are operated, the file information is analyzed and processed, and based on the analysis and processing results, the deduction results of the event data under different scenarios relative to the simulation deduction algorithm model are determined. Based on the deduction results and the preset deduction result data, the simulation deduction algorithm model is optimized.

[0036] During the optimization process of the deduction simulation module, the system adopts an algorithm framework that combines Policy Gradient and Proximal Policy Optimization (PPO) to optimize and train the policy model. The method is as follows: Policy optimization algorithm: In each deduction cycle, the system first inputs the current scenario state (S) into the policy model, and the policy model outputs the current scheduling policy (A). The system calculates the reward value (R) based on the simulation feedback, and updates the parameters θ in the policy model based on the policy-provided formula ∇θJ(θ)=E[∇θlogπθ(A|S)*R].

[0037] PPO optimization: To further improve the optimization stability and prevent policy failure caused by too fast policy updates, the system introduces the PPO algorithm. The PPO algorithm effectively controls the policy update amplitude by introducing a clipped loss function L_CLIP(θ)=min(r(θ)*A,clip(r(θ),1 - ε,1 + ε)*A), where r(θ)=πθ(A|S) / πθ_old(A|S) is the policy ratio and ε is the control threshold.

[0038] Policy optimization process: After each deduction cycle ends, the system uses the feedback results (such as evacuation efficiency, resource allocation effect) as the reward signal to update the parameters of the policy model through PPO optimization. The optimized policy model will be applied in the next deduction cycle to achieve adaptive optimization and rapid response to emergency scenarios.

[0039] Algorithm Database: During the policy optimization process, the system stores the optimized policy model in the algorithm database for quick invocation in subsequent deduction scenarios. The policy model is dynamically adjusted according to real-time scenario data to achieve closed-loop optimization of the reinforcement learning policy model and the simulation deduction module.

[0040] In this embodiment, various types of simulation tools are integrated through corresponding application programming interfaces, and the corresponding simulation deduction algorithms are invoked. Among them, the simulation deduction algorithms are various algorithms used when constructing the simulation deduction algorithm model, including mathematical algorithms such as trend analysis, statistical analysis, and data fitting, as well as business algorithms such as environment simulation, security simulation, traffic simulation, and equipment simulation. Multiple types of simulation deduction algorithms are classified and encapsulated in the algorithm database for the convenience of the digital twin integrated transportation hub emergency scenario simulation deduction system to call.

[0041] More specifically, the simulation deduction unit further includes a deduction control module and a message management module. Among them, the deduction control module mainly sets the time length and step size of the simulation deduction to simulate emergency scenarios at different time scales. And according to the feedback messages (such as real-time data, user input), it dynamically loads / unloads models and updates parameters. The message management module records all data results (such as metrics, parameters, events) during the emergency scenario simulation deduction process, and conducts information interaction with the visualization display unit, sending the deduction results for display and interacting with the transportation department to send key information for decision-making (through a message queue or event bus).

[0042] The deduction control module can set the time length of the simulation deduction and the time interval of each step according to actual needs, which helps to simulate emergency scenarios at different time scales, thereby better evaluating the effectiveness of response strategies. During the deduction process, the deduction control module schedules the model database according to the feedback messages, such as real-time data, user input, etc. This includes operations such as loading or unloading models and updating model parameters to ensure the accuracy and real-time nature of the simulation deduction. The message management module is responsible for recording all data results generated during the simulation deduction process, including various metrics, parameters, events, etc. The message management module also needs to conduct information interaction with other systems or departments such as the visualization display unit and the transportation department. It can send the results of the simulation deduction to the visualization display unit for display, or send key information to relevant departments such as the transportation department so that they can make decisions in a timely manner. Specifically, a message queue or event bus mechanism is used to transfer messages between different systems or departments.

[0043] In this embodiment, situation assessment is carried out based on the deduction model of the optimized model. The situation assessment process includes: Step A: Input the event data in the emergency scenario as the conditions of the simulation deduction node into the corresponding simulation deduction algorithm model, and establish an evolution sequence according to the time sequence. In each deduction cycle, perform operations on all the simulation deduction algorithm models in the evolution sequence; Step B: After the resources arrive during the event handling, feedback the emergency scenario information to the simulation deduction algorithm model for processing, and judge whether there is evolution. If so, generate corresponding new scenario events according to the deduction results and the connection relationship rules between the models and add them to the evolution sequence for the current emergency situation assessment. Otherwise, directly conduct the current emergency situation assessment and update the situation of the organization, resources, and environment.

[0044] In the traditional information evolution system, the relationships between models, between models and data are fixed. However, for different types and natures of entity models in the comprehensive transportation hub, they need to be dynamically organized for calculation and scheduling. In this embodiment, the hub digital twin information model library organizes numerous models in a certain structural form, and the hub digital twin information model library is subdivided into a model database, a rule relationship database, and an algorithm database to achieve the retrieval and matching of models and the evolution calculation of scenario events. Among them, the evolution calculation of scenario events involves the combination and evolution of models. The combination of models means that the scenario event model is combined with the corresponding scheduling and handling event model to generate a new scenario event model algorithm. For example, when there is a road congestion, after traffic control, the congestion index is output, and the connection rule is that the initial congestion index minus the traffic control impact amount is the current congestion index. The evolution of models means that when specific certain scenario events occur to the same entity, new scenario events are generated. For example, when the passenger flow congestion level reaches the second-level warning and there are personnel conflict events or fires at the location of this scenario, casualties will occur, and this scenario event will start the corresponding model and evolve.

[0045] The comprehensive transportation hub digital twin technology aims at the dynamic interaction between physical objects and digital objects, centered around the digital twin three-dimensional scene and dynamic scene simulation, to achieve the assessment of the current state and the diagnosis of past problems, thus forming an intelligent decision-making support system of "perception - prediction - action". This technology utilizes the internal modeling and rendering of the transportation hub, train distribution, station passenger flow, and vehicle flow simulation technologies to comprehensively and real-time display warning and prediction information. Build a dynamic scene simulation module, and through the integrated fusion of BIM + GIS, the real-time fusion of multi-source intelligent monitoring and sensing information, and the digital twin visualization technology of three-dimensional interactive linkage, realize the linkage management of the digital world and the real physical world, achieve the all-round integrated closed-loop system of the whole life cycle of the hub, and reach the one-stop operation management of future hub safety intelligent control.

[0046] In this embodiment, an emergency situation assessment model is constructed based on the MECE (Mutually Exclusive Collectively Exhaustive, MECE) principle, collecting real-time perception data such as weather, induction, cameras, videos, vehicle passing through checkpoints, etc., constructing a secondary monitoring index system for dimensions such as extreme weather, fire accidents, large passenger flow events, temperature and humidity smoke sensor alarms, video device alarms, etc., and establishing a primary monitoring index system for emergency events and device alarm dimensions based on the secondary monitoring dimension indicators. The weight of each indicator is calculated using the hierarchical entropy analysis method, and an emergency situation comprehensive scoring model is constructed with the probability and severity of risk events occurring as the purpose. The specific form is as follows: -ustive, MECE) principle to construct an emergency situation assessment model, collect real-time perception data such as weather, induction, cameras, videos, vehicle passing through checkpoints, etc., construct a secondary monitoring index system for dimensions such as extreme weather, fire accidents, large passenger flow events, temperature and humidity smoke sensor alarms, video device alarms, etc., establish a primary monitoring index system for emergency events and device alarm dimensions based on the secondary monitoring dimension indicators, use the hierarchical entropy analysis method to calculate the weight of each indicator, and construct an emergency situation comprehensive scoring model with the probability and severity of risk events occurring as the purpose. The specific form is as follows: , , , Among them, is the information entropy of the indicator, is the proportion of the j-th indicator in the i-th plan for this indicator, n is the number of indicators, is the weight of the j-th indicator, is the i-th value of the j-th indicator, is the comprehensive score of the i-th plan. Based on the comprehensive score of the emergency pressure state discrimination, four risk state levels of extra-high, high, medium, and low for event emergencies are designed to achieve real-time monitoring and early warning of the emergency event dimension within the integrated transportation hub station.

[0047] The visualization display unit is mainly used to allocate and manage user permissions, plot and deduce data based on the GIS map, and support query and visualization display. Users can query the deduced data according to the query instructions and conditions, and the query conditions may include time range, geographical location, data type, etc. The query results will be visually displayed in the form of graphs, charts, etc., which can help users more intuitively understand the deduced data and discover the patterns, trends, and anomalies therein.

[0048] Specifically, such as Figure 5As shown in the figure, the visualization display unit includes a map basic information management module, a query and statistics module, a data plotting and display module, and a user management module. The map basic information management module is involved in map data management, map service publishing, and the process of overlaying deduction elements. Map data management mainly preprocesses GIS map basic data (map clipping, adding and editing layer attributes, performing topological operations based on the roads and spatial positions of transportation hubs, and constructing a topological network according to the operation results). Map service publishing is to publish the processed map data as a service for other modules to call. The overlay of deduction elements is to overlay deduction data (such as event locations and influence ranges) onto the map layer, that is, to publish the map service, classify the layers according to the set categories and layer names to form a tree diagram, store the tree diagram in the core database, and add the deduction elements to the map layer according to the element attributes, so as to realize the query, editing, and configuration of emergency scenario situation elements.

[0049] The query and statistics module supports querying deduction data according to conditions such as time range, geographical location, and data type, and statistically analyzing the query results to generate charts and reports. The data plotting and display module plots the deduction data onto the map in real time, supports multi-layer overlay display, and sorts and displays the data according to the information priority (such as the urgency of the event). The user management module is used to match the corresponding role permissions according to the user's basic information (such as management and command personnel, fire operation departments, and health departments), and to perform user authentication to ensure the legality of the user's identity and protect the security of system data. The users of this system include managers responsible for basic information maintenance and plan configuration, as well as departments participating in emergency simulations, including fire, health, and public security departments, etc. The emergency scenario simulation service is for high-level emergency command and management personnel to study. The management personnel can use functions such as situation information query, past situation query, map browsing, and be responsible for situation element configuration, etc.

[0050] Digital twin is a technical means to create a virtual entity of a physical entity in a digital way, and simulate, verify, predict, and control the whole life cycle process of the physical entity with the help of historical data, real-time data, and algorithm models, etc. For comprehensive transportation hubs, through digital twin technology, a cross-screen collaboration mechanism for management units, business collaboration, mobile collaboration, and server-side services can be constructed to achieve the purposes of real-time equipment monitoring, active accident prevention, rapid fault diagnosis, and maintenance strategy optimization.

[0051] This system combines Building Information Modeling (BIM) and Geographic Information System (GIS) to construct a high-precision three-dimensional digital twin model. It integrates Internet of Things perception data, video data, etc. to achieve real-time synchronization between virtual entities and physical entities. Through three-dimensional interactive linkage, it enables users to perform real-time operations and monitoring on virtual scenarios. Based on the results of simulation and deduction, it evaluates the current emergency situation (such as risk level classification). Finally, based on time series analysis, it predicts the development trend of events (such as passenger flow growth prediction). It conducts statistical analysis on historical data to discover event patterns (such as analysis of accident-prone areas). And through methods such as regression and interpolation, it fits the event evolution curve. It also conducts simulations of the environment, security, traffic, and equipment, simulating the impact of environmental disasters such as fires on the hub, simulating the impact of security measures (such as evacuation route blockades) on crowd flow, simulating the impact of traffic control and road closures on vehicle flow, and simulating emergency responses in scenarios such as equipment failures and power outages. Through the feedback during the simulation and deduction process, it dynamically adjusts the model parameters to optimize the deduction results. This system integrates multi-source data, various algorithms and models, achieving one-stop emergency management. Through digital twin technology, it realizes real-time interaction and dynamic simulation between virtual and physical scenarios. It provides an intuitive visualization interface, supporting emergency commanders to make quick decisions and improving the efficiency and accuracy of emergency responses.

[0052] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An integrated transportation hub emergency scenario simulation and deduction system based on digital twin, characterized in that, It includes: A data processing unit, a simulation deduction unit, and a visualization display unit; The data processing unit is used to obtain the basic data of the emergency scenarios of the target digital twin integrated transportation hub, perform multi-source integration on the basic data, and construct a model data environment; The simulation deduction unit is connected to the data processing unit. The simulation deduction unit calls a simulation deduction algorithm to construct a simulation deduction algorithm model based on the emergency scenario model data, and conducts emergency situation deduction and dispatching and handling based on the simulation deduction algorithm model; The visualization display unit is responsible for the allocation and management of user permissions, plots deduction data based on the basic information of the GIS map, and queries and visually displays the deduction data according to the user's query instructions and conditions.

2. The comprehensive transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 1, characterized in that The data processing unit includes a basic data module, a data integration module, and a feature modeling module; The basic data module is used to obtain the data resources of the infrastructure layer according to the established data model, and construct a basic database based on the data resources; The data integration module is connected to the basic data module. The data integration module is responsible for integrating data from multiple sources, cleaning, classifying, encoding, mapping, marking, fusing the data, and conducting rule mining and spatio-temporal analysis, and storing the data after integration processing in the core database; The feature modeling module is responsible for transforming the full-feature entities of the transportation hub into information models, and constructing a digital twin information model library of the hub oriented to realizing business functions.

3. The integrated transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 2, wherein The hub digital twin information model library includes a model database, a rule relationship database, and an algorithm database; the model database is responsible for storing the various attributes of the information model, including the model number, model type, model name, the numbers of the scenario events or handling events to be matched, as well as the relevant algorithm names and storage locations, the rule relationship database is used to store the relationship rule data for connecting models to each other, and the algorithm database is used to store the evolution models of scenario events and the event models of dispatching and handling.

4. The comprehensive transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 2, characterized in that, The simulation and deduction unit includes an emergency situation awareness module, a model matching module, and a deduction simulation module; the emergency situation awareness module is used to analyze the integrated processed data, extract scenario event and event object parameters, and obtain emergency scenario model data; the model matching module is connected to the emergency situation awareness module, and the model matching module is used to match and call a simulation and deduction algorithm model according to the emergency scenario model data, and the simulation and deduction algorithm model performs response processing according to the data processing requirement signal; the deduction simulation module is connected to the model matching module, and the deduction simulation module is used to input the event data under different emergency scenarios as simulation and deduction node conditions into the corresponding simulation and deduction algorithm model, obtain an event evolution model file and an event disposal model file, establish an evolution sequence according to the time sequence, and in each deduction cycle, perform operations on all the simulation and deduction algorithm models in the evolution sequence, analyze and process the file information, determine the deduction results of the event data under different scenarios relative to the simulation and deduction algorithm model according to the analysis and processing results, and optimize the simulation and deduction algorithm model based on the deduction results and the preset deduction result data.

5. The integrated transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 4, characterized in that, The simulation and deduction unit further includes a deduction control module and a message management module; the deduction control module is used to control the time and step size settings of the deduction, and schedule and manage the model database according to the feedback message; the message management module is used to record the data results of the emergency scenario simulation and deduction, and perform information interaction with the visualization display unit and the transportation department.

6. The integrated transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 5, characterized in that, Based on the deduction model of the optimized model, a situation assessment is carried out. The situation assessment process includes: Taking the event data under the emergency scenario as the node conditions of the simulation and deduction, inputting them into the corresponding simulation and deduction algorithm model, and establishing an evolution sequence according to the time sequence. In each deduction cycle, perform operations on all the simulation and deduction algorithm models in the evolution sequence; After the resources arrive during the event disposal, feedback the emergency scenario information to the simulation and deduction algorithm model for processing, judge whether there is evolution. If so, generate corresponding new scenario events according to the deduction results and the relationship rules connected between the models and add them to the evolution sequence for the current emergency situation assessment. Otherwise, directly perform the current emergency situation assessment, and update the situation of the organization, resources, and environment. Among them, the situation assessment and model optimization will combine with the reinforcement learning model, and through continuous learning and reinforcement of the deduction feedback results, realize the adaptive adjustment of the model and the optimization of intelligent strategies.

7. The integrated transportation hub emergency scenario simulation and deduction system based on digital twin according to claim 5, characterized in that The visualization display unit includes a map basic information management module, a query and statistics module, and a data plotting and display module; The map basic information management module is used to manage map basic data and preprocess the map basic data according to the actual requirements of emergency scenario simulation. The preprocessing includes map clipping, adding and editing layer attributes, performing topological operations according to the roads and spatial positions of transportation hubs and constructing a topological network based on the operation results, as well as publishing map services, classifying layers according to the set categories and layer names to form a tree diagram, storing the tree diagram in the core database, and adding deduction elements to the map layer according to element attributes. The query and statistics module is used for users to query and browse the corresponding deduction and situation evolution information; the data plotting and display module is used to plot relevant evolution data on the map and display the data according to the information priority, and display messages of the same level in sequence according to their reception order.

8. The digital twin-based integrated transportation hub emergency scenario simulation and deduction system according to claim 7, wherein The visualization display unit further includes a user management module, and the user management module is used to match corresponding role permissions according to user basic information.

Images