A digital twin-driven intelligent fire-fighting collaborative method and system for dynamic topology networks

Abstract

This invention relates to the fields of fire fighting and automatic control, providing a digital twin-driven intelligent fire-fighting coordination method and system based on dynamic topology networks. The method constructs a digital twin model of a fire monitoring scenario, monitors data in real time through multiple devices, and the model can be dynamically updated. It then establishes a dynamic topology network, deploys communication nodes, and optimizes the topology. Subsequently, it analyzes the monitoring scenario, defines task priorities based on resource and environmental information, allocates tasks, schedules communication nodes, and finally visualizes the results. This system integrates task allocation, resource scheduling, and communication optimization into a unified mathematical framework, overcoming the fragmented nature of traditional fire-fighting decision-making and improving rescue efficiency.

Description

Technical Field

[0001] This invention belongs to the field of fire fighting and automatic control, and particularly relates to a digital twin-driven dynamic topology network intelligent fire fighting collaborative method and system. Background Technology

[0002] With the rapid development of urban construction, the number of complex buildings such as high-rise buildings and underground spaces has surged, significantly increasing the risk and severity of fires. Digital twin technology, as an emerging technology, enables real-time monitoring, simulation analysis, and optimized control of physical systems by constructing virtual models of these systems. Dynamic topology network technology can automatically adjust the network structure based on the dynamic changes of nodes, ensuring the stability and reliability of communication. Both technologies provide new technical support for collaborative firefighting operations.

[0003] Currently, fire and rescue operations primarily rely on traditional decision-making methods, encompassing task allocation, resource scheduling, and communication support. Task allocation often depends heavily on human experience, resource scheduling frequently overlooks the capacity of communication links, and communication deployment is not coordinated with tasks and resources. Each stage operates relatively independently, leading to fragmented decision-making, delayed rescue orders, resource misallocation, waste of human and material resources, increased safety risks for rescue personnel, and severely impacting the efficiency of firefighting and rescue operations. Summary of the Invention

[0004] The purpose of this invention is to provide a digital twin-driven intelligent fire-fighting collaborative method for dynamic topology networks, which aims to solve the technical problems existing in the prior art as identified in the background section.

[0005] This invention is implemented as follows:

[0006] A digital twin-driven intelligent fire-fighting collaborative method for dynamic topology networks, the main steps of which are as follows:

[0007] Step 1: Construct a digital twin model of the fire monitoring scenario. When no fire occurs, various data within the scenario are monitored in real time using devices such as temperature sensors, anemometers, gas leak imagers, and laser methane telemetry devices. In the event of a fire, the model can also reflect the real-time development of the fire, and it can be continuously updated and corrected based on data collected from the scene.

[0008] Obtain the geometric structure of the fire-prone building or scene to be monitored using oblique photography by drones or 3D laser scanning, and add environmental data such as door and window locations, wall materials, evacuation routes, water source locations, and building spacing. For flammable and explosive scenarios such as oil and gas stations where gas leaks are possible, information on the material of combustible gas pipelines and valve locations should also be added, along with marking historical leak points and high-risk areas (such as valve interfaces and flange connections). Construct a 3D spatial architecture.

[0009] A comprehensive monitoring and early warning network is deployed, with temperature sensors, smoke sensors, combustible / toxic gas composition sensors, and wind speed and direction indicators installed in the monitored area. In special cases, laser methane telemetry devices are deployed in flammable and explosive areas. Gas leak imagers are deployed in open spaces or at high altitudes to visualize gas leak areas. Acoustic imagers for gas leaks are deployed in enclosed or semi-enclosed areas. All monitoring and early warning devices and sensors transmit data back to the space architecture through a low-power network.

[0010] Based on a three-dimensional spatial architecture, the scene space is decomposed into grid cells, and each grid cell is associated with material properties and ventilation parameters to form a computable spatial topology. A "hazard-fire" correlation prediction model is constructed. If a fire has already occurred, an intelligent fire spread prediction model is established by combining aerodynamics and machine learning algorithms.

[0011] The specific logic behind the "hazard-fire" correlation prediction is as follows:

[0012] When the concentration of combustible gas reaches 10%-25% of the lower explosive limit, it is considered a Level 1 warning, triggering a local area alert and dispatching drones to conduct close-range verification.

[0013] When the concentration of combustible gas reaches 25%-50% of the lower explosive limit, it is considered a level two warning, and the area valves are shut down and the ventilation system is activated. At the same time, a broadcast is made to notify people to evacuate.

[0014] When the temperature rises abnormally (e.g., exceeding 80°C and continuing to rise) or the imaging device detects sparks, combined with gas concentration data, it is determined to be a "precursor to fire." This is considered a Level 3 warning, and fire-fighting preparations are immediately initiated.

[0015] The specific logic of the intelligent fire spread prediction model is as follows:

[0016] The initial temperature field, velocity field, and smoke concentration field are solved using the continuity equation and Newton's second law of momentum from fluid dynamics to generate a physical feature matrix. Historical fire data is collected to extract spatiotemporal features such as temperature gradient and spread rate. The physical feature matrix and historical data are used as input to train a machine learning fusion model.

[0017] Real-time monitoring data is input into the model, the grid state is updated through physical equations, and the prediction results are corrected by machine learning models to output the fire spread path and danger zone for a period of time in the future.

[0018] Step 2: Establish a dynamic topology network and deploy fire communication nodes. Utilize an adaptive routing algorithm to optimize the topology network in real time.

[0019] Establish a dynamic topology network and optimize the topology network through adaptive routing algorithms;

[0020] High-power base stations, backup power supplies, and anti-interference cables are deployed in structurally stable and durable areas such as building entrances, fire shafts, etc., serving as signal relays and network hubs.

[0021] When the equipment detects a leak or abnormal temperature, the dynamic topology network automatically marks the location as a "potential fire source" and dispatches the nearest firefighting robot carrying a portable detector to confirm the fire. If a fire is confirmed, drones are deployed to dynamically hover over high-risk areas based on an intelligent fire spread prediction model, providing communication relay and blind spot hazard warnings. Firefighting robots equipped with multi-band communication modules are deployed to access the spatial architecture model to obtain a 3D map of the fire scene and proceed to severely affected areas to perform firefighting operations such as dropping fire extinguishing bombs.

[0022] Step 3: The data twin model performs real-time analysis of the monitoring scenario, combining the deployment of fire protection resources and current environmental information. It defines task priorities, assigns early warning processing or firefighting tasks, and dynamically solves the scheduling of fire communication nodes.

[0023] The task priorities differ slightly depending on the monitoring scenario. Level 1 tasks primarily include: fire suppression, life-saving rescue, and protection of critical facilities. Level 2 tasks primarily include: obstacle clearing, environmental monitoring, relay deployment, containing flammable gas leaks, and cooling / explosion prevention. Level 3 tasks primarily include: isolating and restricting access to high-risk areas, and replenishing fire extinguishing agents.

[0024] The beneficial effects of this invention are:

[0025] This invention addresses the fragmented nature of traditional firefighting decision-making by constructing a real-time updated digital twin model of the fire scene, optimizing communication through dynamic topology networks and adaptive routing algorithms, and integrating task allocation, resource scheduling, and communication optimization into a unified mathematical framework. It also incorporates "hazard-fire" correlation prediction from equipment such as gas leak imagers, achieving an upgrade from passive fire suppression to proactive prevention. Its intelligent fire spread prediction model, combining fluid dynamics and machine learning algorithms, accurately outputs fire spread paths and hazardous areas. The dynamic priority algorithm adjusts task weights according to fire stages, and the task allocation model and communication node scheduling model achieve efficient resource matching and reliable communication through constraints. Furthermore, the system dynamically adjusts strategies based on fire development and visualizes the results, effectively improving the scientific rigor, timeliness, and resource utilization efficiency of firefighting and rescue efforts, while reducing the risk of casualties and property damage. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0027] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0029] like Figure 1 As shown, this invention provides a digital twin-driven intelligent fire-fighting collaborative method for dynamic topology networks, with the following specific steps:

[0030] Step 1: Construct a digital twin model of the fire monitoring scenario:

[0031] In the absence of a fire, this model uses equipment such as temperature sensors, anemometers, gas leak imagers, and laser methane telemetry devices to monitor various data within the scene in real time. During a fire, it can reflect the fire's development in real time and continuously update and correct itself based on collected on-site data. Its specific construction process is as follows:

[0032] 1. Construct a high-precision 3D spatial architecture: Obtain the geometric structure of the fire-prone building or scene to be monitored through UAV oblique photography or 3D laser scanning, and add environmental data such as door and window positions, wall materials, evacuation routes, water source locations, and building spacing; for flammable and explosive scenes such as oil and gas stations where gas leaks may occur, it is also necessary to add information on the material of combustible gas pipelines, valve locations, and mark historical leak points and high-risk areas (such as valve interfaces and flange connections).

[0033] 2. Deploy a comprehensive monitoring and early warning network: Deploy temperature sensors, smoke sensors, combustible / toxic gas composition sensors, and wind speed and direction indicators in the monitoring area; deploy laser methane telemetry devices in flammable and explosive areas; deploy gas leak imagers in open spaces or at high altitudes to visualize gas leak areas; and deploy acoustic gas leak imagers in enclosed or semi-enclosed areas; all monitoring and early warning devices and sensors transmit data back to the space architecture through a low-power network.

[0034] 3. Constructing a predictive model: Based on the above three-dimensional spatial architecture, the scene space is decomposed into grid units, and each grid unit is associated with material properties and ventilation parameters to form a computable spatial topology; a "hazard-fire" correlation prediction model is constructed; if a fire has already occurred, an intelligent fire spread prediction model is established by combining aerodynamics and machine learning algorithms.

[0035] The logic behind the "hazard-fire" correlation prediction is as follows:

[0036] When the concentration of combustible gas reaches 10%-25% of the lower explosive limit, a Level I warning is triggered, a local area alert is initiated, and drones are dispatched to conduct close-range verification.

[0037] When the concentration of combustible gas reaches 25%-50% of the lower explosive limit, a level-two warning is triggered, which involves shutting down area valves, starting the ventilation system, and broadcasting a notice to evacuate personnel.

[0038] When the temperature rises abnormally (e.g., exceeding 80°C and continuing to rise) or the imager detects a spark, combined with gas concentration data, it is determined to be a "precursor to fire," triggering a level-three warning and directly initiating fire extinguishing preparations.

[0039] The logic of the intelligent fire spread prediction model is as follows:

[0040] Based on the continuity equation and the momentum equation of Newton's second law in fluid dynamics, the temperature field, velocity field and smoke concentration field at the initial moment are solved to generate a physical feature matrix; historical fire data are collected to extract spatiotemporal features such as temperature gradient and spread rate; the physical feature matrix and historical data are used as input to train a machine learning fusion model.

[0041] The transition equations for the machine learning fusion model are:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] In the above system of equations, for The input characteristics at any given time are specifically the real-time data from the sensor, such as temperature, smoke concentration, and wind speed. for The status is hidden at all times, specifically the fire trend analysis results at the current moment; for The real-time cell state, specifically the stored fire development information, such as temperature change patterns and spread patterns; , The activation values ​​for the forget gate, input gate, and output gate are given, where the forget gate is specifically the "trust level" of the historical fire status. This is the weight matrix; , , , For bias terms; for Activation function.

[0049] Real-time monitoring data is input into the model, the grid state is updated through physical equations, and the prediction results are corrected by machine learning models to output the fire spread path and danger zone for a period of time in the future.

[0050] Step 2: Establish a dynamic topology network and deploy fire communication nodes:

[0051] An adaptive routing algorithm is used to optimize the network topology in real time. The specific process is as follows:

[0052] 1. Optimize the topology network: Establish a dynamic topology network and optimize it using an adaptive routing algorithm. The path selection cost function is:

[0053] ;

[0054] In the above formula, Number of jumps; Available bandwidth, in units of (bits per second); For transmission delay, unit (millisecond); , , These are the weighting coefficients.

[0055] 2. Deploy network hubs: Deploy high-power base stations, backup power supplies, and anti-interference cables in structurally stable and durable areas such as building entrances and fire shafts to act as signal relays.

[0056] 3. Dispatching firefighting equipment: When equipment detects a leak or abnormal temperature, the dynamic topology network automatically marks the location as a "potential fire source" and dispatches the nearest firefighting robot carrying a portable detector to confirm the fire. If a fire is confirmed, drones are deployed to hover and guard high-risk areas based on an intelligent fire spread prediction model, providing functions such as communication relay and blind spot hazard alarms. At the same time, firefighting robots equipped with multi-band communication modules are deployed to access the spatial architecture model to obtain a 3D map of the fire scene and go to the severely affected areas to perform firefighting operations such as throwing fire extinguishing bombs.

[0057] Step 3: Real-time analysis, task definition, and dynamic solution:

[0058] The data twin model performs real-time analysis of the monitoring scenario, combines fire resource deployment and current environmental information to define task priorities, allocate early warning processing or firefighting tasks, dynamically solve the problem by scheduling fire communication nodes, and visualize the results. The specific process is as follows:

[0059] 1. Define Task Priorities: Task priorities differ depending on the monitoring scenario. Level 1 tasks include fire suppression, life-saving rescue, and protection of critical facilities; Level 2 tasks include obstacle clearing, environmental monitoring, relay deployment, containing flammable gas leaks, and cooling / explosion prevention; Level 3 tasks include isolating high-risk areas and replenishing extinguishing agents. A dynamic priority definition algorithm is used.

[0060] ;

[0061] In the above formula, For dynamic priority, The urgency of the mission is determined by the speed of the fire's spread and the risk to trapped personnel. For time sensitivity (the time the trapped personnel can tolerate). The matching degree of fire-fighting resource allocation. Dynamic adjustments based on the digital twin model, such as prioritizing firefighting in the early stages of a fire, can increase... In the middle stages of a fire, the focus is more on life-saving efforts. The proportion will increase accordingly.

[0062] 2. Task allocation: The task allocation model is as follows:

[0063] ;

[0064] In the above formula, The cost of task execution, of which Indicates the total number of tasks; Total number of firefighting resources (including deployed drones and firefighting robots, etc.); Indicates using Firefighting resources to execute The overall cost of the task, which includes the cost of consumption. That is, the product of distance and energy consumption coefficient; risk cost. This is the product of the task risk level and the vulnerability of fire-fighting resources; time cost. That is, the product of the estimated execution time of the task and the urgency of the task. For the task The urgency of the task. For task decision variables; The overall goal is to maximize the value of the task, among which, For the task The priority is obtained by the dynamic priority definition algorithm; The task completion status is defined as 1 for completed and 0 for incomplete; This is the value amplification factor, which is adjusted by the digital twin based on the task type.

[0065] The constraints of this model include:

[0066] To avoid the misuse of firefighting resources, only one resource is used for each task, i.e.:

[0067] ;

[0068] The load on fire-fighting resources during operation should not exceed the maximum load-bearing capacity of that model of fire-fighting resource, that is:

[0069] ;

[0070] In the above formula Indicates task Firefighting resources The load, such as the number of fire extinguishing bombs that a fire-fighting robot can carry.

[0071] If it is the early warning stage, the items carried by the fire-fighting robot will be changed to handheld detection equipment.

[0072] Special missions require the use of specific firefighting resources; for example, drones cannot carry heavy demolition tools.

[0073] ;

[0074] In the above formula, if Executable; otherwise .

[0075] This model strives for a balance between cost and value, considering both task execution costs and priority value to avoid neglecting high-priority tasks in pursuit of low costs. Furthermore, load constraints and resource compatibility limitations ensure the feasibility of the task allocation scheme.

[0076] 3. Scheduling Communication Nodes: The communication node scheduling model is as follows:

[0077] ;

[0078] In the above formula, For task communication quality, among which Indicates task From resources The communication bandwidth required for execution; Represents task-resource pairs The reliability of the communication link is calculated as the product of the reliability of all nodes on the path, and the mathematical formula is: In this mathematical formula Communication nodes for digital twin prediction The probability of damage / failure during mission execution, such as the probability of node failure in a high-temperature area severely affected by a fire. And it will increase as the duration of high temperature increases; The cost of node activation, where, This represents the total number of communication nodes. For communication decision variables, 1 indicates that the communication node is activated. Conversely, 0 indicates that the communication node is not active; For nodes Activation cost; As a cost-sensitive coefficient, this variable is dynamically adjusted by the digital twin based on the remaining power of fire-fighting resources, typically when the power is low. It will increase.

[0079] The constraints of this model include:

[0080] For critical missions (such as life-saving operations), communication reliability must be greater than or equal to 95%, i.e.:

[0081] , ;

[0082] The number of connections on a single node should not exceed the maximum supported number. , ,in, Represents task-resource pairs Whether to pass through node communication; For nodes The maximum number of connections.

[0083] Task-resource pairs must ensure that there is at least one valid communication path, i.e.:

[0084] , ;

[0085] For primary missions (such as life-saving operations), a high reliability threshold is set to ensure stable transmission of instructions for critical tasks and prevent rescue failures due to communication breakdowns that could result in casualties. Simultaneously, the cost sensitivity coefficient is dynamically adjusted based on fire resource power levels, reducing the activation of high-cost nodes when power is low to balance communication needs with resource consumption.

[0086] 4. Dynamic solution:

[0087] Acquire digital twin data, including: task location Task type Task priority Task risk level Location of fire-fighting resources Remaining battery power Firefighting resource load Location of communication nodes Probability of communication node damage / failure .

[0088] A two-layer nested approach is adopted for task allocation and communication scheduling: the upper layer solves the task allocation problem using integer linear programming for a given communication information node. The lower layer optimizes the activation of communication nodes using conventional heuristic search and shortest path algorithms based on the task allocation results from the upper layer. With path .

[0089] System dynamic adjustment: During the initial stages of a fire and potential hazards, the cost coefficient is increased to minimize costs; during the severe stages of a fire, more communication nodes are allowed to ensure the reliability of firefighting operations; when the digital twin predicts the probability of a node failure... When the power supply of fire-fighting resources is insufficient, switch to the backup node; when the power supply of fire-fighting resources is insufficient. If necessary, consider having it return to base and reassigning the task.

[0090] like Figure 2 As shown, the present invention also provides a digital twin-driven intelligent fire-fighting collaborative system for dynamic topology networks. This system is applied to any of the aforementioned digital twin-driven intelligent fire-fighting collaborative methods for dynamic topology networks. The system includes:

[0091] The digital twin modeling module is used to construct a virtual mapping of real-world scenes, enabling the digital representation of physical space.

[0092] The multi-source data fusion module is used to acquire multi-dimensional data of the monitored scene and update the digital twin model in real time.

[0093] The dynamic topology optimization module is used for the communication allocation and deployment of fire protection resources. It adjusts the fire protection network topology in real time based on changes on site and optimizes resource coordination paths.

[0094] The real-time communication control module ensures the transmission of instructions and status feedback for various communication nodes and terminals in the topology network.

[0095] The intelligent decision-making reasoning module is used for hazard detection and early warning, fire spread prediction and reasoning, and visualization of task allocation results.

[0096] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A digital twin-driven intelligent fire-fighting collaborative method for dynamic topology networks, characterized in that, The method includes: A digital twin model of the fire monitoring scenario is constructed, and the scenario data is monitored in real time through temperature sensors, wind speed and direction instruments, gas leak imagers, and laser methane telemetry instruments; when a fire occurs, the fire development trend is analyzed in real time, and the digital twin model is updated and corrected based on the monitoring scenario data collected on site. Establish a dynamic topology network, deploy fire communication nodes, and use an adaptive routing algorithm to optimize the topology network in real time. The monitoring scene data is analyzed in real time through a digital twin model. Combined with the currently deployed fire protection resources and current environmental information, task priorities are defined, tasks are assigned, early warning processing tasks and fire fighting tasks are assigned, and the scheduling of fire communication nodes is dynamically solved. in: The implementation logic for task allocation is as follows: Establish a task allocation model: ； In the formula, The cost of task execution, of which Indicates the total number of tasks; Total number of fire-fighting resources; Indicates using Firefighting resources to execute The overall cost of the task, which includes the cost of consumption. That is, distance With energy consumption coefficient Accumulation; Risk Cost That is, the task risk level Vulnerability of fire-fighting resources The accumulation of time costs That is, the estimated execution time of the task. With the urgency of the task The accumulation of, For the task The urgency of the task; As a task decision variable, ; The overall goal is to maximize the value of the task, among which, For the task Priority; The task completion status is defined as 1 for completed and 0 for incomplete; This is the value amplification factor; The task allocation model has the following constraints: Each task is assigned to only one fire-fighting resource for execution; The load on fire-fighting resources during the performance of their duties shall not exceed the maximum load-bearing capacity of the corresponding model of fire-fighting resources; When a special task is identified, specific special fire-fighting resources are assigned to perform it.

2. The method according to claim 1, characterized in that, The construction of the digital twin model for the fire monitoring scenario specifically includes: Acquire the geometric structure of the fire monitoring scene, add environmental data, construct a three-dimensional spatial architecture, and deploy a monitoring and early warning network. Based on a three-dimensional spatial architecture, the fire monitoring scene space is decomposed into grid units. Each grid unit is associated with material properties and ventilation parameters to construct a hazard-fire correlation prediction model. If a fire already exists, an intelligent fire spread prediction model is established by combining aerodynamics and machine learning algorithms.

3. The method according to claim 2, characterized in that, The logic for implementing the hazard-fire correlation prediction model is as follows: A Level 1 warning is triggered when the concentration of combustible gas reaches 10%-25% of the lower explosive limit, and a drone is dispatched for verification. When the concentration of combustible gas reaches 25%-50%, a level-two warning is triggered, valves are shut off, ventilation is activated, and personnel are evacuated. A Level 3 warning is triggered when the temperature exceeds 80°C and continues to rise, or when a spark is detected, and fire extinguishing preparations are initiated.

4. The method according to claim 3, characterized in that, The implementation logic of the intelligent fire spread prediction model is as follows: The temperature field, velocity field, and smoke concentration field at the initial moment of a fire are solved based on the continuity equation and the momentum equation of Newton's second law in fluid dynamics, generating a physical characteristic matrix. The intelligent fire spread prediction model is trained by combining historical fire data and then real-time monitoring scene data is input after training. The grid state is updated and the prediction results are corrected through physical equations, and the fire spread path and danger zone for future periods are output.

5. The method according to claim 4, characterized in that, The establishment of a dynamic topology network, deployment of fire communication nodes, and real-time optimization of the topology network using an adaptive routing algorithm specifically include: Establish a dynamic topology network, with the path selection cost function as follows: ； In the formula, Number of jumps; Available bandwidth, in units of ; Transmission delay, in units of ; These are the weighting coefficients; When a leak or temperature anomaly is detected in the area, potential fire sources are marked and firefighting robots are dispatched to confirm them; after a fire is confirmed, drones are deployed to dynamically hover over the fire area, access a 3D spatial architecture to obtain a 3D map of the fire area, and firefighting robots are dispatched to perform firefighting operations.

6. The method according to claim 1, characterized in that, The implementation logic of the dispatch fire communication node is as follows: Establish a communication node scheduling model: ； In the formula, For task communication quality, among which Indicates task From resources The communication bandwidth required for execution; Represents task-resource pairs The reliability of the communication link That is, the product of the reliability of all nodes on the path. Communication nodes for digital twin prediction Probability of damage / failure during task execution; The cost of node activation, where, This represents the total number of communication nodes. For communication decision variables, 1 indicates that the communication node is activated. ,0 indicates that the communication node is not active; For nodes Activation cost; The cost-sensitive coefficient is dynamically adjusted by the digital twin based on the remaining power of fire-fighting resources; The communication node scheduling model has the following constraints: For Level 1 critical missions, communication reliability must be greater than or equal to 95%. There must be at least one valid communication path between the task and the resource.

Images