A digital twin sandbox simulation method and system for emergency command
Through the emergency command digital twin sand table deduction method, phased disassembly, cluster analysis and reinforcement learning algorithms are used to solve the multi-factor complexity problems faced by command and dispatch personnel in emergency events, and achieve rapid response and efficient decision-making, which improves emergency response Management level.
Patent Information
- Application Number
- CN202410013399.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-04
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-01-04
AI Technical Summary
In emergency incidents, command and dispatch personnel face too many factors and complex time and measure dimensions, resulting in low emergency response efficiency and difficulty in making quick and accurate decisions.
Using the emergency command digital twin sand table deduction method, through phased disassembly, hierarchical clustering analysis, correlation rule mining and reinforcement learning algorithm, the elements of emergency incident attention are filled in the digital twin sand table, and the action is correlated with the three-dimensional digital base model to achieve Logical association and logical linkage improve visualization and interactivity.
The abstract emergency incident data is presented in an intuitive and vivid way, shortening emergency response time, improving emergency response efficiency, and enhancing the emergency rescue management level and emergency response capabilities of emergency management departments.
Smart Images

Figure CN117952307B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sandbox simulation, and in particular to a method and system for sandbox simulation of emergency command digital twins. Background Art
[0002] With the continuous acceleration of urbanization, various public emergencies are becoming more frequent. Four types of emergencies, namely natural disasters, accidents, social security incidents and public health incidents, can cause huge losses. The continuous occurrence of such public emergencies has put forward higher requirements on the country's emergency management level and the ability of command and decision-making departments to deal with emergencies. Therefore, it is necessary to establish an information-based, structured and digital emergency command system. An efficient emergency command system can effectively deal with public emergencies, take timely precautions and respond quickly.
[0003] The occurrence of emergency events can be divided into multiple stages from the timeline, and the measures for emergency events can be divided into multiple dimensions according to the different implementation departments or objects of action. This leads to too many factors for commanders to face in the process of responding to emergencies, and the requirements for command and dispatch personnel are extremely high. Summary of the invention
[0004] In order to solve the above technical problems, the present invention provides a digital twin sandbox simulation method and system for emergency command, which can assist commanders to understand the progress of events more comprehensively and conveniently through digital management, and assist commanders to implement and simulate in terms of time and measures at the same time, thereby increasing the practicability of emergency command and improving the emergency rescue management level and emergency response capabilities of emergency management departments.
[0005] The present invention provides an emergency command digital twin sandbox simulation method, the method comprising:
[0006] Step S1, decompose the entire emergency process into stages from the time dimension to obtain the requirements of each stage;
[0007] Step S2, based on the hierarchical clustering method, the emergency events are analyzed in terms of dimensions, and the dimensions of equipment management, material management, passenger evacuation, external force coordination, and job responsibility are obtained;
[0008] Step S3, based on the association rule mining method, granularly decompose the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension to obtain the emergency event focus factors corresponding to each dimension;
[0009] Step S4, filling the emergency event focus elements into the emergency command digital twin sandbox according to the needs of each stage, and performing action association with the three-dimensional digital base model in the emergency command digital twin sandbox;
[0010] Step S5, logically associate and logically link the emergency event focus elements.
[0011] Preferably, the emergency event focus elements corresponding to the equipment management dimension include:
[0012] During the fire confirmation phase, confirm the alarm location on the FAS host and ISCS; after confirmation, press the "Fire Confirmation" button on the FAS and execute the evacuation mode on the ISCS; after the fire is confirmed, ensure that the gate is released, the access control is released, the emergency evacuation broadcast is played, and the PIS emergency information is released during the disaster relief phase, and confirm that each device executes the fire mode; cut off the power supply of related equipment during the disaster relief phase; start the fan fire smoke exhaust mode during the disaster relief phase; during the fire disaster relief phase, confirm the status of the elevator equipment, that is, whether the vertical ladder is trapped, whether the access control is fully open, whether the elevator has returned, play the emergency evacuation broadcast, and release the PIS emergency information; the station CCTV observes the on-site status of each station equipment and passengers;
[0013] The emergency event focus elements corresponding to the material management dimension include: emergency bag location, quantity, and status information; firefighting uniform location, quantity, and status information; fire extinguisher location, quantity, and status information; positive pressure breathing apparatus location, quantity, and status information; fire hydrant location, quantity, and status information;
[0014] The emergency event focus factors corresponding to the passenger evacuation dimension include: flow risk assessment; evacuation path analysis; safety island analysis; dynamic escape simulation; calling station staff to conduct emergency evacuation of the station by integrating station service staff, security, cleaning, and security inspection; PA evacuation broadcast notification; after the passengers are evacuated, organize station personnel to evacuate to the emergency entrance and exit;
[0015] The emergency event focus elements corresponding to the external force coordination dimension include: road network command center, 119 fire alarm, 120 emergency, public security and surrounding properties;
[0016] The emergency event focus factors corresponding to the job responsibilities dimension include: factors of concern to duty officers, factors of concern to duty stationmasters, factors of concern to platform duty officers, factors of concern to hall duty officers, factors of concern to security guards and factors of concern to cleaning staff.
[0017] Preferably, the step S2: performing a dimensional analysis of emergency events based on a hierarchical clustering method to obtain equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension, includes:
[0018] Step S2.1: Preprocess the emergency event data and extract event features;
[0019] Step S2.2: Using a hierarchical clustering method to perform hierarchical division based on the similarity between event features to form different event dimensions;
[0020] Step S2.3: Analyze different event dimensions to obtain equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension.
[0021] Preferably, the step S3 comprises:
[0022] Treat all dimensions as an item set, and each element in the item set is a feature;
[0023] Generate candidate item sets using the Apriori algorithm, where the candidate item sets are all possible item sets;
[0024] Calculate the frequency of each candidate item set appearing in all data, where the frequency of each candidate item set appearing in the data is the support;
[0025] According to the set minimum support threshold, frequent itemsets are screened out from the candidate itemsets;
[0026] Using the Apriori algorithm, for each frequent item set, all non-empty subsets are generated, the confidence and lift of the non-empty subsets are calculated, and the association rules that meet the requirements are obtained;
[0027] Based on each formed association rule, the emergency event focus factors corresponding to each dimension are obtained.
[0028] Preferably, step S4 includes: filling the emergency event focus factors into the digital twin sandbox according to the needs of each stage, and using the Q-Learning algorithm in reinforcement learning to perform action association on the three-dimensional digital base model in the emergency command digital twin sandbox. The Q-Learning algorithm formula is:
[0029] Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s',a')-Q(s,a))
[0030] Where s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s',a') represents the expected value of future rewards that can be obtained by selecting the optimal action a' in the current state, Q(s',a') represents the expected value of future rewards that can be obtained by selecting action a' in the current state, and Q(s,a) is the iterative optimal solution of Q(s',a').
[0031] Compared with the prior art, the digital twin sandbox simulation method for emergency command provided by the present invention has the following beneficial effects: by filling the emergency event attention elements into the emergency command digital twin sandbox and associating the action with the three-dimensional digital base model, the abstract emergency event data can be presented in a more intuitive and vivid way, improving the visualization effect and interactivity. By logically associating and logically linking the emergency event attention elements, the emergency event can be quickly and accurately identified, judged and decided, thereby shortening the emergency response time and improving the emergency response efficiency. By disassembling the emergency event in stages, analyzing the emergency event attention dimensions based on the hierarchical clustering method, and granularly disassembling the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension based on the association rule mining method, the emergency event attention elements corresponding to each dimension are obtained. Through the above-mentioned digital technology, the commander can be assisted to understand the progress of the situation more comprehensively and conveniently, and the commander can be assisted to implement and deduce in the dimensions of time and measures at the same time, thereby increasing the practicality of emergency command and improving the emergency rescue management level and emergency response capability of the emergency management department.
[0032] The present invention also provides an emergency command digital twin sandbox simulation system, which includes:
[0033] The phased decomposition module is used to decompose the entire emergency process into phases from the time dimension to obtain the requirements of each phase;
[0034] The attention dimensional analysis module is used to conduct attention dimensional analysis of emergency events based on the hierarchical clustering method to obtain the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension;
[0035] A granular decomposition module is used to granularly decompose the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension based on an association rule mining method to obtain the emergency event focus factors corresponding to each dimension;
[0036] The element filling and action association module is used to fill the emergency event focus elements into the emergency command digital twin sandbox according to the needs of each stage, and associate the actions with the three-dimensional digital base model in the emergency command digital twin sandbox;
[0037] The element logic association module is used to make logical associations and logical linkages between the elements of emergency events.
[0038] Preferably, the emergency event focus elements corresponding to the equipment management dimension include:
[0039] During the fire confirmation phase, confirm the alarm location on the FAS host and ISCS; after confirmation, press the "Fire Confirmation" button on the FAS and execute the evacuation mode on the ISCS; after the fire is confirmed, ensure that the gate is released, the access control is released, the emergency evacuation broadcast is played, and the PIS emergency information is released during the disaster relief phase, and confirm that each device executes the fire mode; cut off the power supply of related equipment during the disaster relief phase; start the fan fire smoke exhaust mode during the disaster relief phase; during the fire disaster relief phase, confirm the status of the elevator equipment, that is, whether the vertical ladder is trapped, whether the access control is fully open, whether the elevator has returned, play the emergency evacuation broadcast, and release the PIS emergency information; the station CCTV observes the on-site status of each station equipment and passengers;
[0040] The emergency event focus elements corresponding to the material management dimension include: emergency bag location, quantity, and status information; firefighting uniform location, quantity, and status information; fire extinguisher location, quantity, and status information; positive pressure breathing apparatus location, quantity, and status information; fire hydrant location, quantity, and status information;
[0041] The emergency event focus factors corresponding to the passenger evacuation dimension include: flow risk assessment; evacuation path analysis; safety island analysis; dynamic escape simulation; calling station staff to conduct emergency evacuation of the station by integrating station service staff, security, cleaning, and security inspection; PA evacuation broadcast notification; after the passengers are evacuated, organize station personnel to evacuate to the emergency entrance and exit;
[0042] The emergency event focus elements corresponding to the external force coordination dimension include: road network command center, 119 fire alarm, 120 emergency, public security and surrounding properties;
[0043] The emergency event focus factors corresponding to the job responsibilities dimension include: factors of concern to duty officers, factors of concern to duty stationmasters, factors of concern to platform duty officers, factors of concern to hall duty officers, factors of concern to security guards and factors of concern to cleaning staff.
[0044] Preferably, the emergency event focus factors are filled into the digital twin sandbox according to the needs of each stage, and the Q-Learning algorithm in reinforcement learning is used to associate the actions of the three-dimensional digital base model in the emergency command digital twin sandbox. The Q-Learning algorithm formula is:
[0045] Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s',a')-Q(s,a))
[0046] Where s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s',a') represents the expected value of future rewards that can be obtained by selecting the optimal action a' in the current state, Q(s',a') represents the expected value of future rewards that can be obtained by selecting action a' in the current state, and Q(s,a) is the iterative optimal solution of Q(s',a').
[0047] Compared with the prior art, the beneficial effects of an emergency command digital twin sandbox simulation system provided by the present invention are the same as the beneficial effects of an emergency command digital twin sandbox simulation method described in the above technical scheme, which will not be repeated here.
[0048] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the steps in any one of the above-mentioned digital twin sandbox simulation methods for emergency command are implemented.
[0049] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the emergency command digital twin sandbox simulation method described in the above technical scheme, and will not be elaborated here.
[0050] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in any of the above-mentioned emergency command digital twin sandbox simulation methods are implemented.
[0051] Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the emergency command digital twin sandbox simulation method described in the above technical solution, and will not be elaborated here.
[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0054] Figure 1A flow chart of a digital twin sandbox simulation method for emergency command provided by an embodiment of the present invention is shown;
[0055] Figure 2 A schematic diagram of an emergency command digital twin sandbox provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0056] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0057] The "multiple" mentioned in this embodiment refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The words "exemplary" or "for example" are used to indicate examples, illustrations or explanations, and are intended to present related concepts in a specific way, and should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions.
[0058] Figure 1 A flowchart of a digital twin sandbox simulation method for emergency command provided by an embodiment of the present invention is shown. Figure 1 As shown, the method includes:
[0059] Step S1, decompose the entire emergency event process into stages from the time dimension to obtain the requirements of each stage.
[0060] It should be noted that the emergency event process model is established by disassembling the emergency event process in stages from the time dimension using machine learning or deep learning algorithms. Supervised learning algorithms such as support vector machine (SVM), random forest or neural network can be used to train historical emergency event data to identify the type, development trend and impact range of emergency events. When establishing the emergency event process model, the emergency event process can be divided into multiple stages, such as the early warning stage, the preparation stage, the response stage, the recovery stage and the learning stage. The trained emergency event process model is used to automatically divide new emergency events. According to the type, development trend and impact range of the event, the event is disassembled in stages from the time dimension. Classification algorithms or clustering algorithms can be used to achieve automatic division of emergency events, such as support vector machine (SVM), K-means clustering, etc. When automatically dividing the emergency event stage, the following factors can be considered: the type of event, the time of occurrence, the location, the impact range, the duration, etc. Multivariate analysis methods can be used to comprehensively consider these factors to obtain more accurate division results. For each emergency event stage obtained by automatic division, a demand analysis is conducted. Natural language processing technology can be used to analyze historical emergency event reports to extract key tasks and requirements for each stage. For example, the early warning stage requires the establishment of an early warning mechanism and the identification of dangerous factors; the preparation stage requires the clarification of responsibilities and resource allocation; the response stage requires on-site disposal, information collection and analysis; the recovery stage requires the assessment of losses and the repair of facilities; the learning stage requires summarizing lessons learned, improving early warning and response mechanisms, etc. Text mining technology can be used to extract key tasks and requirements, such as keyword extraction and topic models. In addition, classification algorithms or clustering algorithms can be used to classify or cluster key tasks and requirements to obtain clearer demand analysis results. Then, corresponding solutions are formulated based on the requirements and key tasks of each stage.
[0061] Take a fire incident in a rail transit station as an actual application case of an emergency sandbox. The entire rail transit station fire incident process is disassembled into stages from the time dimension to obtain the needs of each stage. Because the needs for emergency assistance are different in each stage, for example, during the fire process, there is a need for fire extinguishing and evacuation, and after the fire is over, there is a need for post-disaster recovery. Because different needs will arise on the timeline of each event, the event is first divided into stages on the timeline, and then the needs are analyzed according to each stage. Specifically, from the fire in the station to the resumption of operation, the entire event process can be divided into four stages, namely "fire confirmation", "small fire rescue", "large fire rescue", and "subsequent processing". "Fire confirmation" means to understand whether a real fire has occurred manually on site or through equipment monitoring, "small fire rescue" means a fire that the station can handle by itself, "large fire rescue" means a fire that requires the introduction of external 119 rescue, and "subsequent processing" is the disposal stage for the station to resume operation after the fire is extinguished. Specifically, the needs of each stage can be Figure 2 Each element in the small box in the disc is a triggerable button.
[0062] Step S2, based on the hierarchical clustering method, the emergency events are analyzed in terms of dimensions, and the dimensions of equipment management, material management, passenger evacuation, external force coordination, and job responsibility are obtained.
[0063] It should be noted that the hierarchical clustering method is used to analyze the dimensions of emergency events, and the dimensions of equipment management, material management, passenger evacuation, external force coordination and job responsibility are obtained, including:
[0064] Step S2.1: Preprocess the emergency event data and extract event features;
[0065] Step S2.2: Using a hierarchical clustering method to perform hierarchical division based on the similarity between event features to form different event dimensions;
[0066] Step S2.3: Analyze different event dimensions according to the focus and responsible parties to obtain equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension.
[0067] Step S3, based on the association rule mining method, the equipment management dimension, the material management dimension, the passenger evacuation dimension, the external force coordination dimension and the job responsibility dimension are granularly decomposed to obtain the emergency event focus factors corresponding to each dimension.
[0068] It should be noted that step S3 includes:
[0069] Initialization: All dimensions are considered as an item set, and each element in the item set is a feature;
[0070] Generate candidate item sets: Use the Apriori algorithm to generate candidate item sets, which are all possible item sets. By continuously discovering frequent k-item sets (k=1,2,3...), the frequent k-item sets are used to generate candidate k+1 item sets, and then determine whether these candidate sets meet the minimum support requirements. If they meet the requirements, they are frequent k+1 item sets, otherwise they are pruned. This cycle continues until no new candidate sets are generated;
[0071] Calculate support: Calculate the frequency of each candidate item set in all data, that is, support;
[0072] Generate frequent item sets: filter out frequent item sets from candidate item sets according to the set minimum support threshold;
[0073] Generate association rules: Generate association rules from frequent item sets using the association rule generation process of the Apriori algorithm. For each frequent item set, generate all non-empty subsets, then calculate indicators such as confidence and lift of these non-empty subsets to find association rules that meet the requirements;
[0074] Analyze association rules: For each generated association rule, by analyzing its confidence, lift and other indicators, the emergency event focus factors corresponding to each dimension are obtained to provide a reference for emergency decision-making.
[0075] Specifically, in the device management dimension, we need to pay attention to the following elements:
[0076] (1) Fire confirmation stage: Confirm the alarm location on the FAS host and ISCS. After confirmation, press the "Fire Confirmation" button on the FAS and execute the evacuation mode on the ISCS;
[0077] (2) After the fire is confirmed, during the disaster relief phase, ensure that the gates are released, access control is released, emergency evacuation broadcasts are played, PIS emergency information is released, and confirm that each device executes the fire mode;
[0078] (3) Cut off the power supply of relevant equipment during the disaster relief phase;
[0079] (4) Start the fan fire smoke exhaust mode during the disaster relief phase;
[0080] (5) During the fire rescue phase, confirm the status of the elevator equipment, i.e., whether there are people trapped in the vertical elevator, whether the door control is fully open, whether the elevator has returned to its original position, play emergency evacuation broadcasts, and release PIS emergency information;
[0081] (6) Station CCTV observes the status of various station equipment and passengers.
[0082] In the dimension of material management, we need to pay attention to the following elements:
[0083] (1) Emergency kit location, quantity, status, etc.;
[0084] (2) Information on the location, quantity, status, etc. of firefighting uniforms;
[0085] (3) Fire extinguisher location, quantity, status, etc.;
[0086] (4) Information on the location, quantity, and status of positive pressure respirators;
[0087] (5) Information on the location, quantity, and status of fire hydrants;
[0088] In terms of passenger evacuation, the following factors need to be considered:
[0089] (1) Flow risk assessment: Analyze emergency evacuation risk points based on the real-time passenger flow of the station, and analyze and warn of possible bottlenecks in the station based on the magnitude of the passenger flow;
[0090] (2) Evacuation route analysis: horizontal evacuation route analysis and evacuation obstacle warning at each location within the station; vertical evacuation route analysis and evacuation obstacle warning at each location within the station;
[0091] (3) Safety island analysis: analysis and identification of safety islands and safe houses within the station;
[0092] (4) Dynamic simulation of escape: Perform dynamic simulation of evacuation based on real-time passenger flow or set passenger flow, simulate the passenger evacuation process, and analyze the evacuation completion time, congestion time of evacuation bottleneck points, and checkpoint facility capacity;
[0093] (5) Call station staff including station attendants, security guards, cleaners, and security inspectors to conduct emergency evacuation of the station;
[0094] (6) PA evacuation broadcast notice;
[0095] (7) After the passengers have been evacuated, station personnel will be organized to evacuate to the emergency entrances and exits.
[0096] In the dimension of external force coordination, we need to pay attention to the following factors:
[0097] (1) Road network command center (2) 119 fire alarm (3) 120 emergency (4) Public security (5) Surrounding property management The following factors should be paid attention to in job responsibilities:
[0098] (1) Duty Officer: Check the fire alarm information on site and report it to the duty station manager; check the equipment status and cut off the power supply.
[0099] (2) Duty Stationmaster: Acts as the on-site commander to arrange the work of various staff members. In the case of a small fire, he organizes the station staff to immediately evacuate the surrounding passengers. While ensuring personal safety, he organizes the station staff to extinguish the fire (if it is an electrical fire or it is about to affect live equipment, he will try to cut off the power supply of the corresponding equipment or notify the station equipment maintenance personnel). He also requires the duty personnel to start the fire smoke exhaust mode and report to the network command center. In the case of a fire disaster, immediately press the nearest hand alarm or notify the operator of the train control room to manually start the fire mode in the corresponding area, and issue an emergency evacuation order for the station (if a train happens to arrive at the station, the OCC dispatcher will manually broadcast the train to inform passengers that there is a fire in the station hall and not to get off at the station; if there is no train stopping at the platform, the train approaching the station will stop at the station as usual, and after opening the car doors and platform doors, the same control strategy as the train stopping at the platform in the station hall fire will be adopted), and station staff, comprehensive station service staff, security, cleaning, security inspection, etc. will be organized to carry out emergency evacuation of the station. The evacuation route will depend on the on-site situation, and evacuate from the entrances and exits of the station hall that are not affected by the fire. Confirm whether the smoke exhaust mode is started, the effect of the smoke exhaust mode, whether there are people trapped in the vertical ladder, whether the access control is fully open, whether the elevator has returned to the home position, play the emergency evacuation broadcast, and release the PIS emergency information; organize security guards to wear firefighting uniforms and positive pressure respirators to assist in extinguishing the fire. When using fire hydrants to extinguish the fire, be sure to cut off the power to the relevant equipment first.
[0100] (3) Platform attendant: guide passengers to evacuate the platform in an orderly manner or guide passengers to board the train; check the operating status of escalators and passenger elevators to check whether there are people trapped; provide good guidance and explanation to passengers; report the situation to the duty stationmaster.
[0101] (4) Station hall attendant: Upon receiving the notice to execute the station evacuation order, turn off the power of the customer service center, collect the money and tickets, and assist the stationmaster on duty in evacuating the passengers in the station hall. Follow the stationmaster on duty’s instructions and assemble at the emergency exit.
[0102] (5) Security guards: After discovering or receiving notification from the train control room, wear firefighting uniforms and positive pressure respirators to conduct search and rescue and firefighting work. When using fire hydrants to extinguish fires, be sure to cut off the power to related equipment first. After receiving notification from the duty stationmaster, go to the entrance and exit to meet with company support personnel, public security, fire and other rescue personnel. After the personnel are evacuated, close the entrance and exit and post notices, and then gather at the emergency entrance and exit. Cooperate with the rail transit and fire personnel to carry out on-site disposal work. After the fire is handled, assist the duty stationmaster in resuming operations.
[0103] (6) Cleaning: Follow the instructions of the stationmaster on duty and guide passengers out of the station. After evacuation, gather at the emergency exit. After the fire is dealt with, assist the stationmaster on duty in resuming operations.
[0104] Step S4, fill the emergency event focus factors into the emergency command digital twin sandbox according to the needs of each stage, and associate them with the three-dimensional digital base model in the emergency command digital twin sandbox.
[0105] It should be noted that the Q-Learning algorithm in reinforcement learning can be used to associate actions with the three-dimensional digital base model in the emergency command digital twin sandbox, so that the emergency event focus factors can be filled into the digital twin sandbox according to the needs of each stage, and interactive simulation can be performed with the digital base model. The Q-Learning algorithm formula is:
[0106] Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s',a')-Q(s,a))
[0107] Among them, s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s',a') represents the expected value of future rewards that can be obtained by selecting the optimal action a' in the current state, Q(s',a') represents the expected value of future rewards that can be obtained by selecting action a' in the current state, and Q(s,a) is the iterative optimal solution of Q(s',a'). Through continuous iterative learning, Q(s,a) will gradually approach the optimal solution, thereby optimally associating actions with the three-dimensional digital base model in the emergency command digital twin sandbox.
[0108] The emergency event focus elements analyzed and disassembled in step S3 are filled into the emergency command sandbox according to the needs of different stages of the event. This digital twin emergency sandbox can associate the focus elements with the three-dimensional digital base. Specifically, the equipment in the equipment management dimension is associated with the digital base model, and it supports clicking to view the equipment operation status and click to view the real-time CCTV video monitoring screen of the equipment.
[0109] The present invention also adopts three-dimensional visualization display technology and develops functions based on three-dimensional maps, so as to uniformly manage and display information such as fire force distribution, key fire units, fire water sources, police situations, police dispatch records, key unit distribution, road distribution, micro fire stations, social fire linkage forces, fire reserve materials, and detachment resource statistics on the GIS map.
[0110] The present invention also uses spatial computing technology, based on GIS and BIM three-dimensional models, to calculate the shortest evacuation path for passengers to escape, and simulates and analyzes obstacles and bottlenecks in the path. Analyze the evacuation completion time, congestion time of evacuation bottlenecks, and the capacity of checkpoint facilities. Specifically, by accessing real-time traffic information on the GIS map and combining the spatial geographic information of GIS, the time of each evacuation path can be calculated, and the appropriate evacuation path can be found by comparing the shortest time. Evacuation within the building is achieved through the shortest path algorithm based on Djikstra using the spatial data of the BIM model.
[0111] The present invention also adopts a pedestrian collision simulation model, simulates the passenger evacuation state based on a three-dimensional model, simulates the evacuation process under different passenger flows, and calculates the evacuation time and congestion points occurring during the evacuation.
[0112] Step S5, logically associate and logically link the emergency event focus elements.
[0113] It should be noted that the digital twin emergency command sandbox of the present invention supports manual configuration of logical associations between elements. It also supports logical linkage between elements in each stage, that is, after the elements of the previous stage are triggered, the elements of the subsequent associated stages are triggered. Because there will be logical relationships between the elements of concern, for example, during the fire extinguishing process, if you choose to extinguish with water, you must first confirm that the power supply of the equipment has been disconnected, so a power status confirmation action is required before starting the fire hydrant. Because of this logical association, it is hoped that the logical relationship will be linked and associated during the emergency plan configuration stage, so that the commander can be reminded to avoid omissions during the actual emergency command process.
[0114] The present invention also provides a configuration tool for associating attention elements, such as shutting down the power of the fire extinguishing area equipment and stopping the elevator when the fire hydrant equipment is activated.
[0115] Figure 2 FIG. 1 is a schematic diagram of a digital twin sandbox for emergency command provided by an embodiment of the present invention. Figure 2 As shown, the present invention adopts a special digital twin sand table presentation format. The entire sand table is divided into several concentric circles in the axial dimension. Each concentric axis represents the progress of the emergency event, which can be the advancement of time or the evolution stage of the situation. It can be customized and edited according to the direction of the deduction. The sand table is divided into several radial areas, each area represents the business aspect that needs to be paid attention to in the event. Taking a fire event as an example, Figure 2 As shown in the figure, the emergency command center of a fire can divide the sand table into several business aspects: personnel rescue, development of the situation, system operation, external support, external interaction, and job deployment. The emergency command disk is combined with digital twins. Digital twins are used as a technical auxiliary to the application of the emergency command disk to help command personnel confirm the geographical location of the accident, the status of the equipment, and the simulation of some plans.
[0116] In addition, emergency operations are linked. After one operation is triggered, another operation indicator light will light up. For example, if the train is stopped, the driving function will be affected, and the evacuation explanation items of the adjacent stations will light up. For example, when an emergency occurs at a station, the station will affect the adjacent stations when the train is stopped. Because there are no trains, there will be passenger congestion at the adjacent stations. Therefore, after the stop action at station B, the prompt action button for evacuating passengers at stations A\C will light up.
[0117] Compared with the prior art, the emergency command digital twin sandbox simulation method provided by the embodiment of the present invention has the following beneficial effects:
[0118] 1. Digital management can assist commanders to understand the progress of events more comprehensively and conveniently, and assist commanders to implement and deduce in terms of both time and measures.
[0119] 2. Provide digital simulation information during the emergency process based on the digital model base, such as evacuation path, equipment status, equipment location, etc.
[0120] 3. It proposes that there is a correlation between emergency event elements, and provides a sandbox editing tool to assist in the construction of trigger conditions for element correlation, thereby avoiding secondary disasters caused by operations during emergency response and avoiding behavioral omissions during the emergency process.
[0121] 4. The emergency command digital twin sandbox proposed in the present invention can assist command personnel to deploy troops from different dimensions and time axes to solve emergency events, so as to deal with the occurrence of emergency events with ease.
[0122] The embodiment of the present invention further provides an emergency command digital twin sandbox simulation system, which includes:
[0123] The phased decomposition module is used to decompose the entire emergency process into phases from the time dimension to obtain the requirements of each phase;
[0124] The attention dimensional analysis module is used to conduct attention dimensional analysis of emergency events based on the hierarchical clustering method to obtain the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension;
[0125] A granular decomposition module is used to granularly decompose the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension based on an association rule mining method to obtain the emergency event focus factors corresponding to each dimension;
[0126] The element filling and action association module is used to fill the emergency event focus elements into the emergency command digital twin sandbox according to the needs of each stage, and associate the actions with the three-dimensional digital base model in the emergency command digital twin sandbox;
[0127] The element logic association module is used to make logical associations and logical linkages between the elements of emergency events.
[0128] Preferably, the emergency event focus elements corresponding to the equipment management dimension include:
[0129] During the fire confirmation phase, confirm the alarm location on the FAS host and ISCS; after confirmation, press the "Fire Confirmation" button on the FAS and execute the evacuation mode on the ISCS; after the fire is confirmed, ensure that the gate is released, the access control is released, the emergency evacuation broadcast is played, and the PIS emergency information is released during the disaster relief phase, and confirm that each device executes the fire mode; cut off the power supply of related equipment during the disaster relief phase; start the fan fire smoke exhaust mode during the disaster relief phase; during the fire disaster relief phase, confirm the status of the elevator equipment, that is, whether the vertical ladder is trapped, whether the access control is fully open, whether the elevator has returned, play the emergency evacuation broadcast, and release the PIS emergency information; the station CCTV observes the on-site status of each station equipment and passengers;
[0130] The emergency event focus elements corresponding to the material management dimension include: emergency bag location, quantity, and status information; firefighting uniform location, quantity, and status information; fire extinguisher location, quantity, and status information; positive pressure breathing apparatus location, quantity, and status information; fire hydrant location, quantity, and status information;
[0131] The emergency event focus factors corresponding to the passenger evacuation dimension include: flow risk assessment; evacuation path analysis; safety island analysis; dynamic escape simulation; calling station staff to conduct emergency evacuation of the station by integrating station service staff, security, cleaning, and security inspection; PA evacuation broadcast notification; after the passengers are evacuated, organize station personnel to evacuate to the emergency entrance and exit;
[0132] The emergency event focus elements corresponding to the external force coordination dimension include: road network command center, 119 fire alarm, 120 emergency, public security and surrounding properties;
[0133] The emergency event focus factors corresponding to the job responsibilities dimension include: factors of concern to duty officers, factors of concern to duty stationmasters, factors of concern to platform duty officers, factors of concern to hall duty officers, factors of concern to security guards and factors of concern to cleaning staff.
[0134] Preferably, the emergency event focus factors are filled into the digital twin sandbox according to the needs of each stage, and the Q-Learning algorithm in reinforcement learning is used to associate the actions of the three-dimensional digital base model in the emergency command digital twin sandbox. The Q-Learning algorithm formula is:
[0135] Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s',a')-Q(s,a))
[0136] Where s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s',a') represents the expected value of future rewards that can be obtained by selecting the optimal action a' in the current state, Q(s',a') represents the expected value of future rewards that can be obtained by selecting action a' in the current state, and Q(s,a) is the iterative optimal solution of Q(s',a').
[0137] This invention combines digital technologies such as WebGIS path deduction, digital twin engine calculation, data collection, data analysis, and emergency process decomposition, and combines them with practical applications in specific scenarios to study and design a digital sandbox emergency command digital twin sandbox deduction system for public emergencies, improves the digitization of emergency response processes and visualization of emergency rescue information, increases the practicability of the emergency command system, and improves the emergency rescue management level and emergency response capabilities of emergency management departments.
[0138] In addition, an embodiment of the present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned emergency command digital twin sandbox simulation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0139] In addition, an embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned emergency command digital twin sandbox simulation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0140] Computer readable storage media include: permanent and non-permanent, removable and non-removable media, which are tangible devices that can retain and store instructions for use by instruction execution devices. Computer readable storage media include: electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, and any suitable combination of the above. Computer readable storage media include: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassette storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanical encoding devices (such as punched cards or raised structures in grooves with instructions recorded thereon) or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined in the embodiments of the present invention, computer-readable storage media do not include temporary signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (such as light pulses passing through fiber optic cables), or electrical signals transmitted through wires.
[0141] In the several embodiments provided in the present application, it should be understood that the disclosed devices, electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.
[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one location or distributed on multiple network units. Some or all of the units may be selected according to actual needs to solve the problem to be solved by the embodiments of the present invention.
[0143] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or part of the contribution to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (including: a personal computer, a server, a data center or other network device) to perform all or part of the steps of the method described in each embodiment of the present invention. The above-mentioned storage medium includes various media that can store program codes as listed above.
[0145] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A digital twin sandbox simulation method for emergency command, characterized in that: include: Step S1, decompose the entire emergency process into stages from the time dimension to obtain the requirements of each stage; Step S2, based on the hierarchical clustering method, the emergency events are analyzed in terms of dimensions, and the dimensions of equipment management, material management, passenger evacuation, external force coordination, and job responsibility are obtained; Step S3, based on the association rule mining method, granularly decompose the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension to obtain the emergency event focus factors corresponding to each dimension; Step S4, filling the emergency event focus elements into the emergency command digital twin sandbox according to the needs of each stage, and performing action association with the three-dimensional digital base model in the emergency command digital twin sandbox; Step S5, logically associate and logically link the emergency event focus elements; The step S4 includes: filling the emergency event focus factors into the digital twin sandbox according to the needs of each stage, and using the Q-Learning algorithm in reinforcement learning to associate actions with the three-dimensional digital base model in the emergency command digital twin sandbox. The Q-Learning algorithm formula is: Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s′,a′)-Q(s,a)) Among them, s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s′,a′) represents the expected value of future rewards that can be obtained by selecting the optimal action a′ in the current state, Q(s′,a′) represents the expected value of future rewards that can be obtained by selecting action a′ in the current state, and Q(s,a) is the iterative optimal solution of Q(s′,a′).
2. According to claim 1, a digital twin sandbox simulation method for emergency command is characterized in that: The emergency event focus factors corresponding to the equipment management dimension include: During the fire confirmation phase, confirm the alarm location on the FAS host and ISCS; after confirmation, press the "Fire Confirm" button on the FAS and execute the evacuation mode on the ISCS; after the fire is confirmed, ensure that the gate is released, the access control is released, the emergency evacuation broadcast is played, the PIS emergency information is released, and confirm that each device executes the fire mode; cut off the power supply of related equipment during the disaster relief phase; start the fan fire smoke exhaust mode during the disaster relief phase; during the fire disaster relief phase, confirm the status of the elevator equipment, that is, whether the vertical ladder is trapped, whether the access control is fully open, whether the elevator has returned, play the emergency evacuation broadcast, and release the PIS emergency information; the station CCTV observes the on-site status of each station equipment and passengers; The emergency event focus elements corresponding to the material management dimension include: emergency bag location, quantity, and status information; firefighting uniform location, quantity, and status information; fire extinguisher location, quantity, and status information; positive pressure breathing apparatus location, quantity, and status information; fire hydrant location, quantity, and status information; The emergency event focus factors corresponding to the passenger evacuation dimension include: flow risk assessment; evacuation path analysis; safety island analysis; dynamic escape simulation; calling station staff to conduct emergency evacuation of the station by integrating station service staff, security, cleaning, and security inspection; PA evacuation broadcast notification; after the passengers are evacuated, organize station personnel to evacuate to the emergency entrance and exit; The emergency event focus factors corresponding to the external force coordination dimension include: road network command center, 119 fire alarm, 120 emergency, public security and surrounding properties; The emergency event focus factors corresponding to the job responsibilities dimension include: factors of concern to duty officers, factors of concern to duty stationmasters, factors of concern to platform duty officers, factors of concern to hall duty officers, factors of concern to security guards and factors of concern to cleaning staff.
3. The digital twin sandbox simulation method for emergency command according to claim 1 is characterized in that: The step S2: based on the hierarchical clustering method, the emergency event is analyzed in terms of dimensions, and the dimensions of equipment management, material management, passenger evacuation, external force coordination and job responsibility are obtained, including: Step S2.1: Preprocess the emergency event data and extract event features; Step S2.2: Using a hierarchical clustering method to perform hierarchical division based on the similarity between event features to form different event dimensions; Step S2.3: Analyze different event dimensions to obtain equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension.
4. The digital twin sandbox simulation method for emergency command according to claim 1 is characterized in that: The step S3 comprises: Treat all dimensions as an item set, and each element in the item set is a feature; Generate candidate item sets using the Apriori algorithm, where the candidate item sets are all possible item sets; Calculate the frequency of each candidate item set appearing in all data, where the frequency of each candidate item set appearing in the data is the support; According to the set minimum support threshold, frequent itemsets are screened out from the candidate itemsets; Using the Apriori algorithm, for each frequent item set, all non-empty subsets are generated, the confidence and lift of the non-empty subsets are calculated, and the association rules that meet the requirements are obtained; Based on each formed association rule, the emergency event focus factors corresponding to each dimension are obtained.
5. An emergency command digital twin sandbox simulation system, characterized in that: include: The phased decomposition module is used to decompose the entire emergency process into phases from the time dimension to obtain the requirements of each phase; The attention dimensional analysis module is used to conduct attention dimensional analysis of emergency events based on the hierarchical clustering method to obtain the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension; A granular decomposition module is used to granularly decompose the equipment management dimension, material management dimension, passenger evacuation dimension, external force coordination dimension and job responsibility dimension based on an association rule mining method to obtain the emergency event focus factors corresponding to each dimension; The element filling and action association module is used to fill the emergency event focus elements into the emergency command digital twin sandbox according to the needs of each stage, and associate the actions with the three-dimensional digital base model in the emergency command digital twin sandbox; The element logic association module is used to make logical associations and linkages between the elements of emergency events; The emergency event focus factors are filled into the digital twin sandbox according to the needs of each stage, and the Q-Learning algorithm in reinforcement learning is used to associate the actions of the three-dimensional digital base model in the emergency command digital twin sandbox. The Q-Learning algorithm formula is: Q(s,a)=Q(s,a)+α*(r+γ*maxQ(s′,a′)-Q(s,a)) Among them, s represents the current state, α represents the current action, r represents the reward value after executing action α in the current state, γ represents the discount factor of future rewards, maxQ(s′,a′) represents the expected value of future rewards that can be obtained by selecting the optimal action a′ in the current state, Q(s′,a′) represents the expected value of future rewards that can be obtained by selecting action a′ in the current state, and Q(s,a) is the iterative optimal solution of Q(s′,a′).
6. The emergency command digital twin sandbox simulation system according to claim 5 is characterized in that: The emergency event focus factors corresponding to the equipment management dimension include: During the fire confirmation phase, confirm the alarm location on the FAS host and ISCS; after confirmation, press the "Fire Confirm" button on the FAS and execute the evacuation mode on the ISCS; after the fire is confirmed, ensure that the gate is released, the access control is released, the emergency evacuation broadcast is played, the PIS emergency information is released, and confirm that each device executes the fire mode; cut off the power supply of related equipment during the disaster relief phase; start the fan fire smoke exhaust mode during the disaster relief phase; during the fire disaster relief phase, confirm the status of the elevator equipment, that is, whether the vertical ladder is trapped, whether the access control is fully open, whether the elevator has returned, play the emergency evacuation broadcast, and release the PIS emergency information; the station CCTV observes the on-site status of each station equipment and passengers; The emergency event focus elements corresponding to the material management dimension include: emergency bag location, quantity, and status information; firefighting uniform location, quantity, and status information; fire extinguisher location, quantity, and status information; positive pressure breathing apparatus location, quantity, and status information; fire hydrant location, quantity, and status information; The emergency event focus factors corresponding to the passenger evacuation dimension include: flow risk assessment; evacuation path analysis; safety island analysis; dynamic escape simulation; calling station staff to conduct emergency evacuation of the station by integrating station service staff, security, cleaning, and security inspection; PA evacuation broadcast notification; after the passengers are evacuated, organize station personnel to evacuate to the emergency entrance and exit; The emergency event focus factors corresponding to the external force coordination dimension include: road network command center, 119 fire alarm, 120 emergency, public security and surrounding properties; The emergency event focus factors corresponding to the job responsibilities dimension include: factors of concern to duty officers, factors of concern to duty stationmasters, factors of concern to platform duty officers, factors of concern to hall duty officers, factors of concern to security guards and factors of concern to cleaning staff.
7. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the emergency command digital twin sandbox simulation method as described in any one of claims 1 to 4 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps in the emergency command digital twin sandbox simulation method as described in any one of claims 1 to 4 are implemented.
