Remote monitoring and intelligent management and control system for fire-fighting equipment

Abstract

The invention discloses a remote monitoring and intelligent management and control system for fire-fighting equipment, and belongs to the technical field of fire-fighting early warning, and the system specifically comprises the steps: deploying a multi-parameter sensor array, and enabling each sensor node to form a redundant monitoring network through a honeycomb topological structure; carrying out real-time fusion analysis on the sensor network data through an edge computing gateway, and triggering an abnormal region positioning module when detecting that any monitoring parameter exceeds a preset dynamic threshold value; the abnormal region positioning module constructs a three-dimensional thermodynamic diagram model based on the parameter gradient change of adjacent sensor nodes, and dynamically calculates the diffusion direction and the potential risk level of an abnormal region; the mobile inspection robot cluster receives the coordinates and risk parameters of the abnormal area, a multi-stage response path is automatically generated based on a building digital twin model updated in real time, a primary path quickly approaches along a preset main road, and a secondary path is dynamically adjusted according to field obstacle distribution; and the tail end path adopts a contact type detection module to recheck the abnormal area.

Description

Technical Field

[0001] The present invention relates to the technical field of fire warning, and in particular to a fire protection facility remote monitoring and intelligent management and control system. Background Art

[0002] In today's society, fire safety has always been a crucial issue in the construction field. With the acceleration of urbanization, various large-scale commercial buildings, high-rise buildings, industrial plants, etc. have sprung up like mushrooms after rain. These buildings have complex structures, diverse functions, and dense populations. Once a fire or other fire safety accident occurs, it often causes huge casualties and property losses. Therefore, how to timely and accurately monitor the status of fire protection facilities, quickly locate fire hazards and take effective control measures has become an urgent problem to be solved.

[0003] Traditional fire protection facility monitoring systems mainly rely on single sensors, such as independent smoke alarms, temperature sensors, etc. These sensors can only provide limited information and lack data fusion and analysis capabilities, making it difficult to fully and accurately reflect the fire safety status in buildings. For example, smoke alarms can only sound an alarm when the smoke concentration reaches a certain level, and cannot predict the occurrence of a fire in advance; temperature sensors can only detect local temperature changes, and it is difficult to effectively identify fire hazards in complex environments. Moreover, these sensors usually work independently, lack a coordination mechanism, and cannot form an organic whole, resulting in low monitoring efficiency and prone to missed reports and false alarms.

[0004] Traditional methods often rely on manual experience and simple logical judgment, and lack scientific and accurate positioning technology. When a fire occurs, it is difficult to quickly and accurately determine the specific location and scope of the fire, as well as the direction of fire spread and potential risk level. In terms of inspection, traditional inspection methods mainly follow fixed inspection routes and cannot dynamically adjust the inspection routes according to real-time conditions. Summary of the invention

[0005] The purpose of the present invention is to provide a remote monitoring and intelligent management and control system for fire protection facilities to solve the following technical problems: Existing technologies cannot simulate the direction of fire spread and potential risk level. In addition, the inspection method mainly follows a fixed inspection route and cannot dynamically adjust the inspection route according to real-time conditions.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A remote monitoring and intelligent management and control system for fire protection facilities, including a multi-parameter sensor array, an edge computing gateway, an abnormal area positioning module and a mobile robot, wherein: A multi-parameter sensor array is fixedly deployed inside the target building. The sensor array includes temperature, smoke, gas concentration and structural stress sensors. Each sensor node forms a redundant monitoring network with a honeycomb topology. The sensor network data is fused and analyzed in real time through the edge computing gateway. When any monitoring parameter is detected to exceed the preset dynamic threshold, the abnormal area positioning module is triggered; The abnormal area positioning module constructs a three-dimensional thermal map model based on the parameter gradient changes of adjacent sensor nodes, and dynamically calculates the diffusion direction and potential risk level of the abnormal area; The mobile inspection robot cluster receives the coordinates and risk parameters of the abnormal area, and autonomously generates a multi-level response path based on the real-time updated digital twin model of the building. The primary path quickly approaches along the preset main road, the secondary path is dynamically adjusted according to the distribution of obstacles on site, and the terminal path uses a contact detection module to review the abnormal area.

[0007] As a further solution of the present invention: the setting of the dynamic threshold adopts an environment adaptive mechanism: In the routine monitoring stage, the threshold is set to 80% of the safety standard and kept floating dynamically. The monitoring period is set to T, and the floating range is self-corrected according to the parameter fluctuation characteristics in the historical data. When coordinated changes in N related parameters are detected, N ≥ 2, the threshold sensitive mode is automatically activated, the trigger sensitivity is increased to 120% of the safety standard, the monitoring period is adjusted to T / N, and the cross-validation mechanism of the three adjacent monitoring units is started.

[0008] As a further solution of the present invention: the construction process of the three-dimensional thermal map model includes: A spherical coordinate system is established with the anomaly source as the center, and 12 sampling sections are set equidistantly along the radial direction. 32 virtual detection points are arranged on each section, and the local risk coefficient is calculated by the difference between the actual measurement value of the sensor network and the theoretical diffusion model. The movement trajectory of smoke particles is simulated by the principle of fluid dynamics, and the evolution trend of high-risk areas is predicted in combination with the real-time operating parameters of the building ventilation system.

[0009] As a further solution of the present invention, the specific process of using fluid dynamics principles to simulate the movement trajectory of smoke particles and combining the real-time operating parameters of the building ventilation system to predict the evolution trend of high-risk areas is as follows: The internal space of the building is divided into several voxel units with a volume of V and assigned material property codes, where V is a set value. A thermal-fluid-solid coupling model is constructed to simultaneously calculate the interaction between the temperature field, airflow field and structural stress field. The temperature field calculation introduces the latent heat of material phase change, the airflow field simulation is combined with the real-time parameters of the ventilation system, and the structural stress field uses the finite element method to predict the deformation trend of the component; an observation-prediction feedback mechanism is established, and the voxel state is dynamically updated by fusing multi-source observation data through the Kalman filter algorithm. When the deviation between the local measured temperature and the predicted value exceeds the preset threshold, the model parameter adaptive correction is triggered; The optimal disposal path is generated based on the simulation results, taking into account the path length, risk level and energy consumption. When the fire spread speed exceeds the robot's travel speed, it switches to the drone's rapid disposal mode; the simulation results are mapped to the building BIM model in real time to generate a four-dimensional situation map.

[0010] As a further solution of the present invention: the generation of the multi-level response path includes: Each robot is equipped with a micro laser radar and an infrared thermal imager to continuously build a local environment map with centimeter-level accuracy during movement. When an insurmountable obstacle is detected on the path, it requests building structure database data from the central control system to find hidden maintenance passages or fire-fighting paths. In confined spaces, drones are used to conduct close reconnaissance through ventilation ducts, and real-time image data is transmitted back to the host computer via an electromagnetic induction wireless charging station.

[0011] As a further solution of the present invention: the working mode of the contact detection module includes: When the distance from the suspected fire source is within the set range, the explosion-proof isolation cover is activated and the high-temperature resistant robotic arm is extended to collect gas samples. The chemical composition is detected in real time through the built-in mass spectrometer to distinguish between real fire and false alarm scenarios. When the presence of smoldering is confirmed, nano-aerosol fire extinguishing agent is released to form a local inert environment.

[0012] As a further solution of the present invention: the mobile inspection robot adopts a dynamic path optimization mechanism: After receiving the coordinates of the abnormal area, the robot first generates an initial navigation path based on the building structure data in the digital twin model; during the movement, the robot detects environmental changes in real time through the multimodal sensors it carries, including temperature gradients, smoke concentration distribution, and obstacle locations; when an insurmountable obstacle or high-risk area is detected in the path, the robot automatically triggers the path replanning module, and calculates the optimal detour path based on real-time environmental data and preset safety rules; the path replanning module comprehensively considers the travel distance, time consumption, and risk level, and uses a weighted evaluation algorithm to dynamically adjust the navigation strategy to ensure safe arrival at the target area in the shortest time.

[0013] As a further solution of the present invention: a multi-level early warning response mechanism is constructed according to the potential risk level: The first-level warning only triggers routine review by surrounding robots; the second-level warning activates the building's internal linkage system and automatically lifts access restrictions in related areas; the third-level warning directly connects to the city's fire command center and simultaneously sends a building structure vulnerability analysis report and the best rescue path planning.

[0014] As a further solution of the present invention: it also includes: after the abnormality is resolved, continuous monitoring for n hours after the parameters return to normal, during which the robot performs a re-inspection scan every m minutes; n and m are set values, and a three-dimensional spatiotemporal log of the entire event process is established, marking the response timing and misjudgment nodes of each sensor; based on the machine learning algorithm, the activation conditions of the threshold sensitive mode are optimized, and the material ignition point parameters in the digital twin model are updated.

[0015] Beneficial effects of the present invention: The present invention uses a multi-parameter sensor array to form a redundant monitoring network with a honeycomb topology structure to comprehensively perceive the internal conditions of the building. The edge computing gateway integrates and analyzes data in real time and combines with the dynamic threshold setting mechanism to accurately judge anomalies. The abnormal area positioning module constructs a three-dimensional heat map model to dynamically calculate the diffusion direction and risk level of the abnormal area. The mobile inspection robot cluster generates a multi-level response path based on the digital twin model to efficiently handle anomalies. The contact detection module accurately identifies the fire situation and effectively extinguishes the fire. The dynamic path optimization mechanism ensures that the robot can flexibly reach the target area. The multi-level early warning response mechanism responds to risks in a graded manner. The continuous monitoring and optimization measures after the abnormality is resolved continuously improve the system performance, and the overall remote accurate monitoring and intelligent and efficient control of fire-fighting facilities are realized, which greatly improves the fire prevention and control and emergency response capabilities, and ensures the safety of buildings and personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a module schematic diagram of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1As shown, the present invention is a remote monitoring and intelligent management and control system for fire protection facilities, including a multi-parameter sensor array, an edge computing gateway, an abnormal area positioning module and a mobile robot, wherein: The multi-parameter sensor array plays a key role in data collection in the entire system. It is fixedly deployed at various key locations inside the target building. These locations have been carefully planned and screened to cover the areas in the building where fire safety hazards may occur to the greatest extent. The sensor array contains multiple types of sensors, including temperature sensors for real-time monitoring of ambient temperature changes, which are like a sensitive "thermometer" that can detect abnormal temperature increases in time; smoke sensors that specifically detect the presence of smoke, which can quickly issue an alarm once smoke is generated; and gas concentration sensors that can accurately measure gas concentrations, which can detect possible harmful gases or flammable and explosive gases; in addition, structural stress sensors are used to monitor the stress changes of building structures and detect structural problems that may affect the safety of buildings in advance. Each sensor node is interconnected in a honeycomb topology to form a redundant monitoring network. This unique structural design has significant advantages. On the one hand, it can ensure all-round and no-dead-angle monitoring of the entire target building. On the other hand, even if some sensor nodes fail, it will not affect the normal operation of the entire monitoring network, greatly improving the reliability and stability of the system.

[0020] As the data processing and analysis center of the system, the edge computing gateway undertakes the important task of real-time fusion analysis of sensor network data. It is like an intelligent "brain", constantly receiving data from various sensor nodes, and processing and analyzing these data quickly and accurately. When the edge computing gateway detects that any monitoring parameter exceeds the preset dynamic threshold, it will quickly trigger the abnormal area positioning module. This process is like an efficient early warning mechanism, which can detect potential fire safety hazards in the first place and buy valuable time for subsequent processing work.

[0021] The abnormal area positioning module plays a role in accurate positioning and risk assessment in the system. It builds a three-dimensional thermal map model based on the parameter gradient changes of adjacent sensor nodes through complex and precise algorithms. This three-dimensional thermal map model is like a detailed "risk map" that can intuitively show the specific location and range of the abnormal area. At the same time, the module can also dynamically calculate the diffusion direction and potential risk level of the abnormal area. By predicting the diffusion direction of the abnormal area, the system can take corresponding measures in advance to prevent the danger from further expanding; and the assessment of the potential risk level will help to formulate a more scientific and reasonable response strategy to ensure that fire safety issues can be handled in the most effective way.

[0022] The mobile inspection robot cluster is the "action force" in the system. They receive the coordinates and risk parameters of the abnormal area, and autonomously generate multi-level response paths based on the real-time updated digital twin model of the building. Among them, the primary path quickly approaches the abnormal area along the preset main road, just like a rapid response force, able to arrive at the scene in the shortest time. The secondary path is dynamically adjusted according to the distribution of obstacles on site, which enables the robot to flexibly respond to various complex environments and ensure smooth arrival at the target location. The terminal path uses a contact detection module to review the abnormal area. Through close-range detection and analysis, it further confirms the authenticity and severity of the abnormal situation, providing a more accurate basis for subsequent processing.

[0023] In a preferred embodiment of the present invention, in order to enable the system to better adapt to different environments and working conditions, the setting of the dynamic threshold adopts an environment adaptive mechanism.

[0024] During the routine monitoring phase, the threshold is set to 80% of the safety standard and remains dynamically floating. The reason for setting the threshold to 80% of the safety standard is to be able to detect potential safety hazards in advance while ensuring system safety. The monitoring period is set to T. This period is based on a large number of experiments and practical application experience. It can ensure the monitoring effect while taking into account the operating efficiency of the system. The floating range is self-corrected according to the parameter fluctuation characteristics in the historical data. Through in-depth analysis and mining of historical data, the system can understand the normal fluctuation range and rules of the parameters, and automatically adjust the floating range of the threshold according to the actual situation, so that the system can adapt to different environmental changes more accurately.

[0025] When N related parameters are detected to have coordinated changes, where N ≥ 2, this means that the system has detected abnormal changes in multiple parameters at the same time, which often indicates that the potential fire safety hazards are more serious. At this time, the system will automatically activate the threshold sensitive mode and increase the trigger sensitivity to 120% of the safety standard. This is like the system has entered a "high alert" state, which can more keenly capture small abnormal changes. At the same time, the monitoring cycle is adjusted to T / N. By shortening the monitoring cycle, the system can collect and analyze data more frequently and promptly discover the development trend of abnormal situations. In addition, the system will also start the cross-validation mechanism of three adjacent monitoring units. By mutual verification and comparison of the data of adjacent monitoring units, the accuracy and reliability of the data can be effectively improved, and false alarms caused by individual sensor failures or misjudgments can be avoided, ensuring that the system can accurately identify and deal with real fire safety hazards.

[0026] In another preferred embodiment of the present invention, the construction of a three-dimensional thermal map model plays a vital role in the entire fire protection facility remote monitoring and intelligent management and control system. It can intuitively and accurately present the status of abnormal areas and the distribution of potential risks. The construction process of the model is described in detail below.

[0027] First, a spherical coordinate system is established with the abnormal source as the center. This step is the basis for the construction of the entire model. The abnormal source is the starting point of the fire safety hazard. Establishing a spherical coordinate system with it as the center can ensure that subsequent sampling and analysis are carried out around the key area. After the spherical coordinate system is established, 12 sampling sections are set equidistantly along the radial direction. Setting 12 sampling sections is the optimal solution obtained after a large number of experiments and simulation verifications. This setting can ensure full coverage of the abnormal area while avoiding excessive calculations due to too many sampling sections, or failing to accurately reflect the situation in the abnormal area due to too few sampling sections.

[0028] Next, 32 virtual detection points are arranged on each sampling section. These virtual detection points are like scouts distributed on various "front lines" that can collect relevant data on the section. The local risk coefficient is calculated by the difference between the actual measurement value of the sensor network and the theoretical diffusion model. The sensor network obtains the actual parameters of each location in real time, while the theoretical diffusion model is a standard model based on physical principles and a large amount of historical data. By comparing the two, the difference obtained can reflect the degree of deviation of the area from the normal situation, thereby calculating the local risk coefficient, which provides an important basis for subsequent risk assessment and treatment.

[0029] Then, the movement trajectory of smoke particles is simulated using the principle of fluid dynamics. The movement of smoke particles is crucial to determining the direction and range of fire spread, and the principle of fluid dynamics can accurately describe the flow of smoke in the air. Combined with the real-time operating parameters of the building ventilation system, the operating status of the ventilation system will have a significant impact on the spread of smoke. Real-time acquisition of the parameters of the ventilation system can make the simulation results more in line with the actual situation. By combining these two aspects, the evolution trend of high-risk areas can be predicted so that response strategies can be formulated in advance.

[0030] In a preferred case of this embodiment, the movement trajectory of smoke particles is simulated by using the principle of fluid dynamics, and the specific process of predicting the evolution trend of high-risk areas is more sophisticated and complex in combination with the real-time operating parameters of the building ventilation system.

[0031] The first step is to divide the interior space of the building into several voxel units with a volume of V and assign material property codes, where V is a set value. Voxelizing the building space is like breaking down a complex problem into small, easy-to-handle sub-problems. Each voxel unit is assigned a material property code, which can accurately describe the material properties within the unit, such as the thermal conductivity and combustion characteristics of the material, providing basic data for subsequent calculations.

[0032] The second step is to build a thermal-fluid-solid coupling model to simultaneously calculate the interaction between the temperature field, airflow field and structural stress field. These three fields are interrelated and influence each other, and together determine the complex situation inside the building when a fire occurs. The latent heat of material phase change is introduced into the temperature field calculation. The material will absorb or release a large amount of heat during the phase change process. Considering the latent heat of phase change can make the temperature field calculation more accurate. The airflow field simulation is combined with the real-time parameters of the ventilation system. The operation of the ventilation system will change the airflow distribution inside the building. The introduction of real-time parameters can make the airflow field simulation more realistic. The structural stress field uses the finite element method to predict the deformation trend of the component. The finite element method is a mature and effective numerical calculation method that can accurately predict the deformation of the component under the action of fire, providing an important basis for evaluating the safety of the building structure.

[0033] The third step is to establish an observation-prediction feedback mechanism. The voxel state is dynamically updated by fusing multi-source observation data through the Kalman filter algorithm. The Kalman filter algorithm is a filtering algorithm that can effectively handle noise and uncertainty. It can fuse observation data from different sensors to obtain more accurate and reliable voxel state information. When the deviation between the local measured temperature and the predicted value exceeds the preset threshold, the model parameter adaptive correction is triggered. This mechanism enables the model to be continuously adjusted and optimized according to the actual situation, thereby improving the accuracy and reliability of the model.

[0034] The fourth step is to generate the optimal disposal path based on the deduction results. When generating the path, the path length, risk level and energy consumption are comprehensively considered. The path length directly affects the time efficiency of the disposal, the risk level determines the safety level during the disposal process, and the energy consumption is related to the endurance of the robot or drone. By comprehensively considering these factors, a disposal path that is both safe and efficient can be generated. When the spread of the fire exceeds the speed of the robot, in order to ensure that the fire can be controlled in a timely and effective manner, switch to the drone rapid disposal mode. Drones are characterized by high speed and strong maneuverability, and can reach the target area for disposal in a short time.

[0035] Finally, the simulation results are mapped to the building BIM model in real time to generate a four-dimensional situation map. The building BIM model is a three-dimensional model that contains building geometric information and non-geometric information. The simulation results are mapped to the model in real time, and the time dimension is added to generate a four-dimensional situation map. In this way, firefighters can intuitively see the dynamic process of fire development and the risk situation of each area, providing strong support for making scientific and reasonable firefighting decisions.

[0036] In another extremely practical preferred embodiment of the present invention, the generation mechanism of the multi-level response path is a key link to ensure that the system can efficiently respond to abnormal situations such as fire. In order to enable the robot to move accurately and flexibly in a complex building environment, we carefully equipped each robot with a micro laser radar and an infrared thermal imager. The micro laser radar is like the "eyes" of the robot. It can emit laser beams and accurately measure the distance and position of surrounding objects by receiving the reflected laser signals, thereby continuously building a local environment map with centimeter-level accuracy during the movement of the robot. The infrared thermal imager is like the robot's "heat sensing detector", which can detect the infrared radiation emitted by objects, and then identify abnormally high temperature areas hidden in smoke or darkness, providing more comprehensive information for the robot's navigation.

[0037] When the robot detects an insurmountable obstacle in its path during movement, it will not blindly try to pass through it, but will quickly request data from the building structure database from the central control system. This database is like a "treasure trove" of building information, which stores detailed structural information of the building, including hidden maintenance passages and fire-fighting paths. By analyzing this data, the robot can quickly find the best route to bypass the obstacle and ensure that it can reach the abnormal area as soon as possible.

[0038] In a special environment such as a confined space, the robot's actions may be greatly restricted due to the narrow space and limited vision. At this time, we use a drone to conduct close reconnaissance from the ventilation duct. The ventilation duct usually runs through the entire building and is a relatively hidden channel with good connectivity. The drone is small in size and highly maneuverable. It can easily fly in the ventilation duct and observe abnormal areas at close range. At the same time, the drone will transmit real-time image data back to the host through the electromagnetic induction wireless charging pile. This wireless charging and data transmission method is not only convenient and fast, but also avoids the cumbersomeness and limitations of traditional wired connections, ensuring stable data transmission.

[0039] In another preferred embodiment of the present invention, the working mode of the contact detection module is an important guarantee for accurately judging the fire situation and taking fire extinguishing measures in time. When the robot approaches a suspected fire source during movement and enters the set range, the explosion-proof isolation cover will be activated immediately. This explosion-proof isolation cover is like a solid "shield" that can effectively prevent the explosion or flame impact that may occur around the fire source from damaging the robot and detection equipment, providing a safe environment for subsequent detection work.

[0040] Next, the robot will extend a high-temperature resistant robotic arm to collect gas samples. The high-temperature resistant robotic arm uses special high-temperature resistant materials and designs, and can work normally in high-temperature environments. It is like a flexible "arm" that can accurately grab gas samples around the fire source to provide a basis for subsequent chemical composition analysis. The collected gas samples will be transported to the built-in mass spectrometer for real-time detection of chemical components. The mass spectrometer is a high-precision analytical device that can quickly and accurately analyze various chemical components in the gas, thereby distinguishing between real fires and false alarm scenarios. In some cases, the sensor may misjudge due to other factors. Through the detection of the mass spectrometer, these false alarms can be eliminated to ensure the accuracy and reliability of the system.

[0041] When the smoldering phenomenon is confirmed, the contact detection module will release nano-aerosol fire extinguishing agent to form a local inert environment. Nano-aerosol fire extinguishing agent has the advantages of small particle size, good diffusion and high fire extinguishing efficiency. It can quickly fill the space around the fire source, isolate oxygen, and inhibit the combustion reaction, thereby effectively extinguishing the smoldering fire and preventing the fire from further expanding.

[0042] In another preferred embodiment of the present invention, the dynamic path optimization mechanism adopted by the mobile inspection robot is the core technology to improve the efficiency and safety of the robot's actions. After receiving the coordinates of the abnormal area, the robot first generates an initial navigation path based on the building structure data in the digital twin model. The digital twin model is an accurate digital mapping of the real building, which contains the detailed structure, layout and facility information of the building. By analyzing this data, the robot can plan a theoretically optimal path, just like planning a route to a destination on a map.

[0043] During the movement, the robot will not rely solely on the initial path, but will detect environmental changes in real time through the multimodal sensors it carries. These multimodal sensors include temperature sensors, smoke sensors, lidar, etc. They are like various "sensory organs" of the robot, which can perceive changes in the surrounding environment in all directions. For example, the temperature sensor can detect changes in the temperature gradient to determine the location of the fire source and the direction of the fire spread; the smoke sensor can detect the distribution of smoke concentration to help the robot avoid areas with heavy smoke; the lidar can monitor the location of obstacles in real time to ensure that the robot does not collide with obstacles.

[0044] When an insurmountable obstacle or high-risk area is detected in the path, the robot automatically triggers the path replanning module. This module is like the "intelligent brain" of the robot. It combines real-time environmental data with preset safety rules to calculate the optimal detour path. During the calculation process, the path replanning module comprehensively considers multiple factors such as travel distance, time consumption and risk level. In order to weigh these factors, we use a weighted evaluation algorithm to assign corresponding weights according to the importance of different factors, so as to dynamically adjust the navigation strategy. In this way, the robot can safely reach the target area in the shortest time, which not only ensures the efficiency of the action but also ensures its own safety.

[0045] In another preferred embodiment of the present invention, a multi-level early warning response mechanism constructed according to the potential risk level is an important means to achieve hierarchical management and efficient response to abnormal situations such as fires. Level 1 warning is the mildest warning level. When the system detects that the potential risk is low, it only triggers the surrounding robots to conduct routine reviews. The surrounding robots will quickly rush to the abnormal area to further confirm and check the situation to ensure that no details are missed. This method can timely eliminate some possible false alarms without causing a large-scale response, thereby improving the operating efficiency of the system.

[0046] The second-level warning indicates that the potential risk has increased. At this time, the system will activate the internal linkage system of the building and automatically lift the access control restrictions of the relevant areas. The internal linkage system of the building is a comprehensive system that integrates multiple subsystems. It can be linked with the access control system, fire-fighting equipment, etc. When the second-level warning is triggered, the access control system will automatically open the doors of the relevant areas to facilitate personnel evacuation and fire rescue. At the same time, the fire-fighting equipment will also enter a standby state and be ready to be put into use at any time.

[0047] Level 3 warning is the highest level of warning, which means that the potential risk is very high and serious fires and other accidents may have occurred. At this time, the system will directly connect to the city fire command center and simultaneously send a building structure vulnerability analysis report and the best rescue path planning. The building structure vulnerability analysis report is generated based on the digital twin model and real-time monitoring data. It can help firefighters understand which parts of the building are vulnerable to damage in fires and other situations, so as to take corresponding protective measures. The best rescue path planning is calculated based on real-time environmental data and building structure information, which can provide firefighters with the fastest and safest rescue route, ensuring that they can quickly reach the accident site for rescue.

[0048] In another preferred embodiment of the present invention, when the abnormality is resolved, we will not take it lightly, but will take a series of measures to ensure safety and optimize system performance. After the parameters return to normal, the system will continue to monitor for n hours, where n is a value set according to the actual situation, generally determined according to factors such as the severity of the fire and the type of building. During the monitoring period, the robot will perform a recheck scan every m minutes, where m is also a set value. The robot will conduct a comprehensive inspection of the abnormal area and the surrounding environment to ensure that there are no residual fire sources or potential safety hazards.

[0049] At the same time, we will create a three-dimensional space-time log of the entire event process. This log is like a detailed "event record book", which will record the response timing and misjudgment nodes of each sensor from the occurrence of the abnormality to the resolution of the abnormality. By analyzing these logs, we can understand the performance of the system in dealing with abnormal situations and find out the existing problems and shortcomings.

[0050] Based on machine learning algorithms, we will optimize the activation conditions of threshold-sensitive modes. Machine learning algorithms can learn and analyze large amounts of historical data to find out the patterns and characteristics of abnormal situations. By continuously optimizing the activation conditions of threshold-sensitive modes, we can improve the sensitivity and accuracy of the system and reduce false positives and false negatives. In addition, we will also update the material ignition point parameters in the digital twin model. As time goes by and the environment changes, the material properties in the building may change. Updating the material ignition point parameters can make the digital twin model more accurately reflect the real situation and provide a more reliable basis for the system's decision-making.

[0051] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A fire protection facility remote monitoring and intelligent management and control system, characterized in that: It includes a multi-parameter sensor array, an edge computing gateway, an abnormal area positioning module and a mobile robot, among which: A multi-parameter sensor array is fixedly deployed inside the target building. The sensor array includes temperature, smoke, gas concentration and structural stress sensors. Each sensor node forms a redundant monitoring network with a honeycomb topology. The sensor network data is fused and analyzed in real time through the edge computing gateway. When any monitoring parameter is detected to exceed the preset dynamic threshold, the abnormal area positioning module is triggered; The abnormal area positioning module constructs a three-dimensional thermal map model based on the parameter gradient changes of adjacent sensor nodes, and dynamically calculates the diffusion direction and potential risk level of the abnormal area; The mobile inspection robot cluster receives the coordinates and risk parameters of the abnormal area, and autonomously generates a multi-level response path based on the real-time updated digital twin model of the building. The primary path quickly approaches along the preset main road, the secondary path is dynamically adjusted according to the distribution of obstacles on site, and the terminal path uses a contact detection module to review the abnormal area.

2. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: The dynamic threshold is set using an environment adaptive mechanism: In the routine monitoring stage, the threshold is set to 80% of the safety standard and kept floating dynamically. The monitoring period is set to T, and the floating range is self-corrected according to the parameter fluctuation characteristics in the historical data. When coordinated changes in N related parameters are detected, N ≥ 2, the threshold sensitive mode is automatically activated, the trigger sensitivity is increased to 120% of the safety standard, the monitoring period is adjusted to T / N, and the cross-validation mechanism of the three adjacent monitoring units is started.

3. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: The construction process of the three-dimensional heat map model includes: A spherical coordinate system is established with the anomaly source as the center, and 12 sampling sections are set equidistantly along the radial direction. 32 virtual detection points are arranged on each section, and the local risk coefficient is calculated by the difference between the actual measurement value of the sensor network and the theoretical diffusion model. The movement trajectory of smoke particles is simulated by the principle of fluid dynamics, and the evolution trend of high-risk areas is predicted in combination with the real-time operating parameters of the building ventilation system.

4. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 3, characterized in that: The specific process of predicting the evolution trend of high-risk areas by simulating the movement trajectory of smoke particles using the principles of fluid dynamics and combining the real-time operating parameters of the building ventilation system is as follows: The internal space of the building is divided into several voxel units with a volume of V and assigned material property codes, where V is a set value. A thermal-fluid-solid coupling model is constructed to simultaneously calculate the interaction between the temperature field, airflow field and structural stress field. The temperature field calculation introduces the latent heat of material phase change, the airflow field simulation is combined with the real-time parameters of the ventilation system, and the structural stress field uses the finite element method to predict the deformation trend of the component; an observation-prediction feedback mechanism is established, and the voxel state is dynamically updated by fusing multi-source observation data through the Kalman filter algorithm. When the deviation between the local measured temperature and the predicted value exceeds the preset threshold, the model parameter adaptive correction is triggered; The optimal disposal path is generated based on the simulation results, taking into account the path length, risk level and energy consumption. When the fire spread speed exceeds the robot's travel speed, it switches to the drone's rapid disposal mode; the simulation results are mapped to the building BIM model in real time to generate a four-dimensional situation map.

5. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: The generation of the multi-level response path includes: Each robot is equipped with a micro laser radar and an infrared thermal imager to continuously build a local environment map with centimeter-level accuracy during movement. When an insurmountable obstacle is detected on the path, it requests building structure database data from the central control system to find hidden maintenance passages or fire-fighting paths. In confined spaces, drones are used to conduct close reconnaissance through ventilation ducts, and real-time image data is transmitted back to the host computer via an electromagnetic induction wireless charging station.

6. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: The working modes of the above-mentioned contact detection module include: When the distance from the suspected fire source is within the set range, the explosion-proof isolation cover is activated and the high-temperature resistant robotic arm is extended to collect gas samples. The chemical composition is detected in real time through the built-in mass spectrometer to distinguish between real fire and false alarm scenarios. When the presence of smoldering is confirmed, nano-aerosol fire extinguishing agent is released to form a local inert environment.

7. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: The mobile inspection robot adopts a dynamic path optimization mechanism: After receiving the coordinates of the abnormal area, the robot first generates an initial navigation path based on the building structure data in the digital twin model; During the movement, the robot uses the multimodal sensors it carries to detect environmental changes in real time, including temperature gradients, smoke concentration distribution, and obstacle locations. When an insurmountable obstacle or high-risk area is detected on the path, the robot automatically triggers the path replanning module, which calculates the optimal detour path based on real-time environmental data and preset safety rules. The path replanning module comprehensively considers travel distance, time consumption, and risk level, and uses a weighted evaluation algorithm to dynamically adjust the navigation strategy to ensure safe arrival at the target area in the shortest time.

8. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: Construct a multi-level early warning response mechanism based on the potential risk level: The first-level warning only triggers routine review by surrounding robots; the second-level warning activates the building's internal linkage system and automatically lifts access restrictions in related areas; the third-level warning directly connects to the city's fire command center and simultaneously sends a building structure vulnerability analysis report and the best rescue path planning.

9. A fire-fighting facility remote monitoring and intelligent management and control system according to claim 1, characterized in that: It also includes that after the abnormality is resolved, the parameters are restored to normal and the robot performs a recheck scan every m minutes during this period. n and m are set values, and a three-dimensional spatiotemporal log of the entire event process is established, marking the response timing and misjudgment nodes of each sensor; The activation conditions of the threshold-sensitive mode are optimized based on a machine learning algorithm, and the material ignition point parameters in the digital twin model are updated.

Images