Fire-fighting door and window dynamic opening and closing decision-making method and system based on multi-source fire features

Abstract

The invention provides a fire-fighting door and window dynamic opening and closing decision-making method and system based on multi-source fire features, and the method comprises the steps: collecting multi-source data, such as smoke concentration, environment temperature and personnel activity states, through distributed sensing nodes, and generating a comprehensive fire situation evaluation result through space-time registration and feature fusion; determining an evacuation priority by combining a house type map and a personnel thermodynamic model; a cellular automaton model is adopted for fire spread prediction, door and window state weights, smoke attenuation coefficients and personnel density factors are introduced into path planning, and a door and window opening and closing priority sequence is dynamically calculated based on an improved A path planning algorithm; finally, intelligent control is achieved through an executing mechanism, manual emergency intervention is supported, automatic control is paused when an inner side manual opening signal is received, information is recorded and uploaded, and the priority of the associated area is recalculated; through cooperation of the multi-source sensing module, the data preprocessing module, the decision analysis module and other units, the functions of accurately responding to a fire and dynamically adapting to an opening and closing strategy are achieved.

Description

Technical Field

[0001] This invention belongs to the field of fire monitoring technology, specifically relating to a dynamic opening and closing decision-making method and system for fire doors and windows based on multi-source fire characteristics. Background Technology

[0002] Fire door and window opening and closing control devices refer to devices that open or close fire doors and windows through mechanical or electronic control during the occurrence and development of a building fire. Their core function is to balance fire prevention and personnel evacuation safety by blocking the path of fire spread and maintaining the unobstructed evacuation routes. They are an important component of building fire protection systems that combine passive fire prevention with active response. They are widely used in densely populated areas such as residential areas and commercial buildings and play a key role in reducing fire casualties and property losses.

[0003] The basic structure of existing fire door and window opening and closing control devices typically consists of three parts: a single sensor module, a simple control unit, and an actuator. The single sensor module usually integrates only one of a smoke sensor or a temperature sensor, triggering alarm and control signals through a preset threshold. The simple control unit often uses a microcontroller or relay circuit with built-in fixed opening and closing logic; for example, current technology mainly relies on the automatic fire alarm system to trigger a synchronous motor to automatically open and close center-hung windows. However, this device relies solely on a single fire alarm signal, lacking comprehensive consideration of multi-source fire characteristics such as smoke concentration and temperature, making it difficult to accurately assess the fire situation. In practical applications, false alarms or incompatibility with complex fire scenarios may lead to inappropriate timing of door and window opening and closing. The actuator is often a DC motor with gear transmission, with the manual control section retaining only a separate mechanical unlocking component. Compared to this application, this type of structure has obvious shortcomings: the single-source sensing module is susceptible to environmental interference due to the lack of multi-parameter verification (such as kitchen fumes accidentally triggering the smoke sensor), leading to false alarms or missed alarms, affecting the accuracy of control; the fixed opening and closing logic cannot adjust the strategy according to the dynamics of people's activities in the residential area (such as people concentrating in bedrooms at night and in public areas during the day), which can easily lead to problems such as "blindly closing and hindering evacuation" or "failure to close in time, resulting in the spread of fire"; there is no linkage mechanism between manual control and automatic control, and mechanical unlocking can only physically open doors and windows, and cannot feed back operation information to the control unit, which may cause the automatic control to repeatedly trigger the closing action, conflicting with the needs of personnel evacuation, and the overall structure lacks data fusion and dynamic decision-making capabilities, making it difficult to adapt to the diversified needs in complex fire scenarios. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a dynamic opening and closing decision method and system for fire doors and windows based on the characteristics of multi-source fires, for accurately responding to fires and dynamically adapting opening and closing strategies.

[0005] The technical solution adopted by this invention to solve the above-mentioned technical problems is: a dynamic opening and closing decision-making method for fire doors and windows based on multi-source fire characteristics, comprising the following steps: The beneficial effects of this invention are as follows: 1. The present invention relates to a dynamic opening and closing decision-making method and system for fire doors and windows based on multi-source fire characteristics. This method collects multi-source data such as smoke concentration, ambient temperature, and personnel activity status through distributed sensor nodes. After spatiotemporal registration and feature fusion, a comprehensive fire situation assessment result is generated. Evacuation priorities are determined by combining floor plan data and personnel thermal models. A cellular automata model is used to predict fire spread, and door and window status weights, smoke attenuation coefficients, and personnel density factors are introduced into the path planning. An improved A-path planning algorithm is used to dynamically calculate the door and window opening and closing priority sequence. Finally, intelligent control is achieved through an actuator that supports manual emergency intervention. When a manual opening signal is received from the inside, automatic control is paused, information is recorded and uploaded, and the priority of the associated area is recalculated. Through the collaboration of various units such as the multi-source sensing module, data preprocessing module, and decision analysis module, the system achieves accurate fire response and dynamic adaptation of opening and closing strategies.

[0006] 2. This invention solves the problems in existing fire door and window opening and closing control, such as single-source fire sensors being prone to false alarms and missed alarms due to interference, fixed opening and closing strategies being difficult to adapt to complex personnel activity scenarios in residential areas, and poor coordination between automatic control and manual opening by internal personnel. It realizes flexible coordination between automatic and manual control, improves response accuracy and scenario adaptability, and takes into account both fire isolation and personnel evacuation needs.

[0007] 3. This invention employs distributed sensing nodes (smoke, temperature, flame, and personnel monitoring units) and a Kalman filter spatiotemporal registration algorithm, combined with sliding window filtering, gradient calculation, and video / infrared cross-validation. It solves the problems of false alarms and missed alarms caused by environmental interference (such as false alarms from cooking fumes) in single-source sensing (e.g., smoke or temperature only), as well as the shortcomings of isolated data and lack of verification. It achieves high-precision synchronous fusion of multi-dimensional fire characteristics (smoke concentration, temperature change rate, flame intensity, and personnel status), generating a comprehensive fire situation assessment result with credibility weighting, significantly improving the accuracy of fire detection and the comprehensiveness of situational awareness. 4. This invention employs a cellular automata fire spread prediction model (parameters include temperature threshold, combustible material level, air circulation, and door / window status) and an improved A* path planning algorithm (the cost function includes weights for door / window status, smoke attenuation coefficient, and personnel density factor), combined with floor plan maps and personnel thermal models. This solves the problem of "blindly closing doors and windows to hinder evacuation" or "failure to close doors and windows in time to allow fire to spread" caused by fixed opening and closing logic failing to adapt to complex personnel activities (such as differences in day and night distribution). It achieves a dynamic priority sequence (updated every 10-30 seconds) based on real-time fire prediction and optimal evacuation routes, realizing accurate dynamic matching of fire door and window opening and closing strategies with fire development and personnel distribution.

[0008] 5. This invention employs a mechanical unlocking component with a built-in microswitch and a wireless transmission unit (ATmega328P+433MHz module) to link with the decision-making center's pause mechanism; it resolves the conflict caused by the lack of coordination between automatic control and manual activation by internal personnel (such as automatic repeated shutdown hindering evacuation); it achieves the following after a manual activation signal is triggered: automatic control pauses for 1-5 minutes, operation information (time, location, personnel characteristics) is uploaded, and the priority of the associated area is recalculated; it ensures priority for emergency evacuation while incorporating manual intervention into the decision-making closed loop.

[0009] 6. This invention adopts an FPGA+ARM hardware architecture (FPGA for parallel processing of fire prediction and path planning, and ARM for instruction generation), an L298N motor driver chip, Hall sensor angle feedback, and overcurrent protection circuit; it solves the problem of response delay caused by insufficient computing power in traditional microcontroller / relay architectures, as well as the lack of status monitoring of actuators; it achieves millisecond-level computing power for complex algorithms (cellular automata, dynamic programming), combined with high-precision motor control (PWM speed regulation) and real-time status feedback (opening and closing angle monitoring), ensuring the real-time performance, accuracy, and reliability of decision-making and execution.

[0010] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of an embodiment of the present invention.

[0013] Figure 2 This is a timing diagram of the decision-making process for opening and closing fire doors and windows according to an embodiment of the present invention.

[0014] Figure 3 This is a system component configuration diagram according to an embodiment of the present invention.

[0015] Figure 4 This is a flowchart of the feature fusion data processing according to an embodiment of the present invention.

[0016] Figure 5 This is a flowchart of the door and window opening and closing decision-making process according to an embodiment of the present invention.

[0017] Figure 6 This is a timing diagram of the manual intervention response in an embodiment of the present invention. Detailed Implementation

[0018] 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. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0019] It should be noted that the terms "vertical," "horizontal," "up," "down," "left," "right," and similar expressions used in this article are for illustrative purposes only and do not represent the only possible implementation.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1 See Figure 1 The specific steps of the dynamic opening and closing decision-making method for fire doors and windows based on the characteristics of multi-source fires are as follows: S1: Real-time collection of multi-source fire characteristic data in the monitoring area through distributed sensor nodes; Multi-source fire characteristic data include smoke concentration, ambient temperature, flame intensity, and personnel activity status; S2: Perform spatiotemporal registration and feature fusion on the collected multi-source data, and generate a comprehensive fire situation assessment result through outlier removal and confidence weighted calculation; Feature fusion includes: applying sliding window mean filtering to smoke concentration data, calculating gradient rate of change for temperature data, and cross-validating personnel activity status using video image recognition and infrared sensor data. During the fusion process, time synchronization of multi-source data is achieved through the Kalman filter algorithm.

[0022] S3: Call the preset residential area floor plan and population activity heat model, and combine it with real-time population distribution data to determine the evacuation priority of each area; S4: Based on the comprehensive fire situation assessment results and regional evacuation priorities, the opening and closing weight values ​​of each fire door and window are calculated through fire spread prediction algorithm and path planning algorithm to generate a dynamic priority sequence. The fire spread prediction algorithm uses a cellular automata model and calculates the following parameters: cell temperature threshold, combustible material combustion level, air circulation coefficient, and fire door and window closure status parameters. The prediction period is set to 10-30 seconds, and the door and window opening and closing priority is updated after each prediction.

[0023] The path planning adds the following to the traditional cost function: the opening status weight of fire doors and windows on the path, the smoke concentration attenuation coefficient, and the personnel density correction factor. The optimal evacuation path set is calculated through dynamic programming, and the closing priority of relevant doors and windows is adjusted accordingly.

[0024] S5: Sends opening and closing control commands to the actuator according to the priority sequence, receives door and window status feedback information in real time, and responds to the manual operation signal from the inside to temporarily release automatic control.

[0025] It also includes: when a manual opening signal is received, recording the operation time, location, and operator characteristics, pausing the automatic control of the door / window for 1-5 minutes, and uploading the operation information to the decision center to recalculate the opening and closing priority of doors and windows in the associated area.

[0026] This embodiment of the invention collects multi-source data such as smoke concentration, ambient temperature, and personnel activity status through distributed sensing nodes. After spatiotemporal registration and feature fusion (combining sliding window filtering, cross-validation, and Kalman filtering to achieve accurate data synchronization), a comprehensive fire situation is generated. Then, user-type maps and personnel thermal models are adjusted, and the priority of door and window opening and closing is dynamically calculated by combining cellular automata fire prediction algorithms and improved A* path planning algorithms. At the same time, a manual interaction module is set up to pause automatic control and record information when a manual opening signal is received from the inside, and recalculate the priority of the associated area. Through the collaboration of various units such as multi-source sensing modules, data preprocessing modules, and decision analysis modules (such as FPGA+ARM architecture to achieve efficient algorithm operation and Hall sensor feedback status), the accuracy of fire response, dynamic adaptability of opening and closing strategies, and flexible coordination of automatic and manual control are achieved, taking into account both fire containment and personnel evacuation needs.

[0027] Example 2 The steps in this embodiment are the same as in Embodiment 1, the difference being that each step is applied to a specific instance. For example... Figure 2 , 3 As shown in Figure 4, the specific steps include: First, multi-source fire characteristic data of the monitoring area are collected in real time through distributed sensor nodes, including smoke concentration, ambient temperature, flame intensity and personnel activity status; Subsequently, the collected data were spatiotemporally registered and feature fused. A comprehensive fire situation assessment result was generated by outlier removal and confidence weighting calculation. The feature fusion process involved using sliding window mean filtering to process smoke concentration data, calculating gradient change rate of temperature data, cross-validating personnel activity status using video image recognition and infrared sensor data, and using Kalman filtering algorithm to achieve time synchronization of multi-source data. Next, the preset residential area floor plan and population activity heat map are called, and the evacuation priority of each area is determined by combining real-time population distribution data; Then, based on the comprehensive fire situation assessment results and regional evacuation priorities, the opening and closing weight values ​​of each fire door and window are calculated through fire spread prediction algorithm and path planning algorithm to generate a dynamic priority sequence. The fire spread prediction adopts a cellular automaton model, with parameters including cell temperature threshold, combustible combustion level, air circulation coefficient and fire door and window closing status parameters. The prediction period is set to 10-30 seconds and the door and window opening and closing priorities are updated after each prediction. The path planning adds the opening status weight of fire doors and windows on the path, smoke concentration attenuation coefficient and personnel density correction factor to the traditional cost function. The optimal evacuation path set is calculated through dynamic programming and the closing priority of relevant doors and windows is adjusted accordingly. Finally, opening and closing control commands are sent to the actuator according to the priority sequence, and door and window status feedback information is received in real time. At the same time, the automatic control is temporarily released in response to the manual operation signal from the inside. When a manual opening signal is received, the operation time, location and operator characteristics are recorded, the automatic control of the door and window is suspended for 1-5 minutes, and the operation information is uploaded to the decision center to recalculate the opening and closing priority of the doors and windows in the associated area.

[0028] This embodiment involves the Kalman filter algorithm, cellular automaton model, improved A algorithm, and fuzzy PID control algorithm. The Kalman filter algorithm achieves multi-source data time synchronization through the Kalman filter toolbox in MATLAB. The cellular automaton model is based on the PyCA library in Python to build a fire spread prediction model. The improved A algorithm uses C++ to write a path planning program in the Visual Studio development environment. The fuzzy PID controller achieves dynamic adjustment of weight coefficients through PLC programming or embedded systems.

[0029] This embodiment employs a cellular automata fire spread prediction model (parameters include temperature threshold, combustible material level, air circulation, and door / window status) and an improved A* path planning algorithm (the cost function includes weights for door / window status, smoke attenuation coefficient, and personnel density factor), combined with floor plan maps and personnel thermal models. It solves the problem of "blindly closing doors and windows to hinder evacuation" or "failure to close doors and windows in time to cause fire spread" caused by fixed opening and closing logic being unable to adapt to complex personnel activities (such as differences in day and night distribution). It achieves a dynamic priority sequence (updated every 10-30 seconds) based on real-time fire prediction and optimal evacuation routes, realizing accurate dynamic matching between fire door and window opening and closing strategies and fire development and personnel distribution.

[0030] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0031] Example 3 This embodiment is used to implement the principle of the above method embodiment to construct a dynamic opening and closing decision system for fire doors and windows based on multi-source fire characteristics, such as... Figure 4 , 5 As shown in Figure 6, the system includes a multi-source sensing module, a data preprocessing module, a decision analysis module, an execution drive module, a manual interaction module, and a power management module. According to the signal flow direction, the multi-source sensing module is connected to the data preprocessing module via wired or wireless means, and the data preprocessing module is connected to the decision analysis module via Ethernet. The decision analysis module is connected to the execution drive module via a CAN bus and communicates with the manual interaction module via a wireless receiving unit. The multi-source sensing module is used to collect raw characteristic data, including smoke sensing units, temperature sensing units, flame detection units, and personnel monitoring units distributed at various monitoring points. The smoke sensing unit uses an MQ-2 sensor and an ADC conversion circuit to output a 0-5V analog signal; the temperature sensing unit uses a DS18B20 digital sensor connected via a single bus; the personnel monitoring unit includes an infrared pyroelectric sensor and a CMOS camera, and data acquisition is triggered by an AND gate circuit. The output signals of both are triggered by the AND gate circuit. The distributed layout of the smoke, temperature, flame, and personnel monitoring units in the multi-source sensing module ensures the comprehensiveness and real-time nature of fire characteristic data collection, providing a reliable data foundation for subsequent decision-making.

[0032] The data preprocessing module generates standardized fire situation data and includes a signal conditioning circuit and a data fusion algorithm module. Through signal conditioning and fusion algorithms, the data preprocessing module achieves spatiotemporal synchronization and reliability weighting of multi-source heterogeneous data, effectively improving the accuracy of fire situation assessment results. Physically integrated within the regional data collection box, the data preprocessing module's SPI interface connects to the ADC conversion circuit of the smoke sensor unit, its single-bus interface connects to the temperature sensor unit, and its GPIO interface receives the linkage trigger signal from the personnel monitoring unit. The data preprocessing module connects to the sensor units through a dedicated interface, not only completing the unified conversion of signal formats but also ensuring the instantaneous synchronization of multi-source data acquisition through a hardware-level linkage trigger mechanism, laying a foundation for timing consistency in subsequent fusion calculations.

[0033] The decision analysis module, as the core processing unit, is centrally deployed in the fire control center. Its Ethernet interface connects to the switches of the data preprocessing modules in each area, while the CAN bus interface connects the nodes of each execution drive module in a daisy-chain manner. This allows the module to receive output data from the preprocessing modules and generate door and window control commands, including a unit type database, a personnel activity model, and a priority calculation engine. The decision analysis module employs a collaborative architecture of FPGA and ARM. The FPGA is used for parallel computation of fire spread simulation and path planning algorithms, while the ARM coordinates data interaction and control command generation, significantly improving system response speed and meeting the real-time requirements of fire emergency decision-making. The decision analysis module aggregates all preprocessed data via high-speed Ethernet and utilizes the parallel architecture of the FPGA chip to hardware accelerate the cellular automata fire model and dynamic path planning, reducing the processing time of traditional software algorithms from minutes to seconds. This enables the system to achieve prediction updates within a 10-30 second cycle, greatly improving the real-time performance of decision response.

[0034] The execution drive module receives control commands from the decision analysis module and executes the opening and closing actions of doors and windows. The execution drive module includes a motor drive circuit, a position feedback circuit, an overcurrent protection circuit, and a mechanical transmission mechanism. The motor drive circuit uses the L298N chip to receive PWM control signals to adjust the DC motor speed. The position feedback circuit consists of a Hall sensor and a counter to monitor the opening and closing angle of doors and windows in real time and feed it back to the decision analysis module. The overcurrent protection circuit uses a self-resetting fuse and a current detection chip to automatically cut off the motor power supply when an abnormal current is detected. The mechanical transmission mechanism is directly coupled to the door and window shaft via a coupling and installed inside the door and window frame. The execution drive module reliably communicates via a CAN bus and directly couples the motor to the door and window shaft. Combined with high-precision Hall sensor feedback, it achieves millimeter-level control of the door and window opening and closing angle, ensuring precise execution of physical isolation. Through precise motor control and position feedback circuitry, the execution drive module ensures the precise execution of the opening and closing actions of fire doors and windows and real-time status monitoring.

[0035] The manual interaction module is embedded in a prominent, easily accessible location on the inside of doors and windows, enabling manual intervention and providing feedback on operational information. The module includes a mechanical unlocking component and an electronic signal transmission unit. The mechanical unlocking mechanism is linked to a microswitch, triggering the switch action when the mechanical lock cylinder rotates. The electronic signal transmission unit uses an ATmega328P microcontroller to convert the switch signal into a digital signal, which is then transmitted to the decision analysis module via a 433MHz wireless module. Built-in LED indicators display the operational status. The wireless module of the manual interaction module and the 433MHz receiver of the decision analysis module form a star network. The prominent embedding and wireless transmission design of the manual interaction module ensures convenient emergency operation while avoiding complex wiring, allowing its operational signals to seamlessly integrate into the decision-making closed loop. While ensuring the main functions of automatic control, the manual interaction module provides a channel for manual intervention in emergencies and feeds operational information back to the decision center via wireless communication, demonstrating the system's human-centered design and flexibility.

[0036] The power management module is located within each module chassis and provides a stable power supply to each module to ensure continuous system operation. The power management module includes a main power supply and backup power supply switching circuit. The distributed backup power supply design of the power management module ensures that the failure of any node does not affect the overall system operation.

[0037] Ultimately, through the aforementioned connections, the modules work together to achieve dynamic, accurate, and intelligent decision-making on the priority of opening and closing fire doors and windows. This forms an intelligent fire protection system with synchronized data acquisition, real-time decision calculation, precise execution control, and reliable human-computer interaction. It effectively solves the problems of slow response, single strategy, isolated operation, and lack of coordination in traditional fire protection systems, and significantly improves the efficiency and safety of personnel evacuation in building fires.

[0038] In use, this embodiment also relies on the existing automatic fire alarm system (FAS) in the building as the upper-level linkage node, interconnecting with the system's decision analysis module via a standard RS485 or Ethernet interface to receive its comprehensive fire situation assessment results and upload them to the cloud monitoring platform; it needs to utilize the existing fire protection power distribution lines in the building structure to provide the main power input for the power management module, and rely on fire-resistant cables such as WDZN-YJY type low smoke halogen-free flame-retardant cables to complete the power transmission and signal communication between modules; it needs to use the building's steel fireproof doors and windows as the installation base for the actuator, and the door leaf material must be cold-rolled steel plate conforming to GB12955-2008 standard, with the inner... The system is filled with fire-resistant aluminum silicate cotton; the existing lightning protection grounding device in the computer room must be used to provide grounding protection for the system, and all module chassis must be connected to the equipotential terminal box through BV-4mm² wires; the existing security system's pipeline resources must be used to lay sensor cables, and the shielded twisted pair cable of the temperature sensing unit DS18B20 must be concealed in the ceiling through JDG20 metal conduit; the system must rely on public mobile communication networks or dedicated fire wireless networks as backup communication channels when the 433MHz transmission of the manual interaction module is blocked; finally, it must be connected to the city's fire remote monitoring center, and the door and window opening and closing priority sequence and status information generated by this system must be uploaded to the command and dispatch platform through a protocol conversion gateway.

[0039] Specifically, the implementation of this solution requires adherence to existing building automation system installation specifications. The smoke sensor unit of the multi-source sensor module will be fixedly installed using pre-embedded 86-type junction boxes in the ceiling. The temperature sensor unit will be attached to the metal frame surface of fire doors and windows using high-temperature resistant magnetic bases. The personnel monitoring unit will be installed using the existing camera poles of the security system via clamps. System wiring must comply with GB50166 "Construction and Acceptance Standard for Automatic Fire Alarm Systems," using flame-retardant RVVP shielded cables for signal transmission, and RVV flame-retardant cables for power supply, concealed along the wall in metal conduits. System integration requires data exchange with the existing building automation system via the OPCUA protocol, utilizing BAC... The .NET protocol is linked with the HVAC system to regulate smoke exhaust and air supply volumes. During the commissioning phase, standard smoke and temperature calibration devices are required to calibrate sensors on-site, and laser rangefinders are used to calibrate the door and window opening and closing travel limits. During system operation, the existing fire control room's graphic display device is used to present fire situation assessment results in real time, and historical data storage and analysis are performed through an IoT platform deployed in the cloud. Routine maintenance requires the use of portable infrared thermal imagers to periodically check the temperature rise of circuit connection points and the use of megohmmeters to measure line insulation resistance. Final acceptance requires functional testing according to the GB16806 "Fire Linkage Control System" standard, and the use of simulated fire generators to produce standard smoke and temperature fields to verify the system's response thresholds.

[0040] Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make various modifications and alterations without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be determined by the claims.

[0041] It should be noted that, depending on the implementation needs, the various steps / components described in this application can be broken down into more steps / components, or two or more steps / components or parts of the operation of steps / components can be combined into new steps / components to achieve the purpose of this invention.

[0042] This embodiment also includes a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the program is executed by the processor, the processor performs the steps of the dynamic opening and closing decision method for fire doors and windows based on multi-source fire characteristics.

[0043] This embodiment also provides a computer-readable storage medium storing executable instructions that, when executed by a processor, enable the processor to implement a dynamic opening and closing decision method for fire doors and windows based on multi-source fire characteristics.

[0044] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0045] Furthermore, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] This application is described with reference to the flowchart of the method and computer program product according to Embodiment 1 and the block diagram of the device (system) according to Embodiment 3. It should be understood that each step or block in the flowchart or block diagram, as well as combinations of steps or blocks in the flowchart or block diagram, can be implemented by computer program instructions.

[0047] These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which are executable by the processor of the computer or other programmable data processing device, produce instructions for implementing the process. Figure 1 One or more processes or boxes Figure 1 A dynamic decision-making system for opening and closing fire doors and windows based on multi-source fire characteristics, specifying functions within one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes or boxes Figure 1 The steps of the dynamic opening and closing decision-making method for fire doors and windows based on multi-source fire characteristics are specified in one or more boxes.

[0050] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for dynamic opening and closing decision of fire door and window based on multi-source fire characteristics, characterized in that: It comprises the following steps: S1: Real-time acquisition of multi-source fire characteristic data of the monitoring area by distributed sensing nodes; S2: Temporal and spatial registration and feature fusion of the collected multi-source fire characteristic data, generation of comprehensive fire situation assessment results through outlier elimination and weighted confidence calculation; S3: Calling the preset residential area house type atlas and personnel activity heat model, determining the evacuation priority of each area combined with real-time personnel distribution data; S4: Based on the comprehensive fire situation assessment results and regional evacuation priority, calculating the opening and closing weight value of each fire door and window through fire spread prediction algorithm and path planning algorithm, and generating dynamic priority sequence; S5: According to the priority sequence, send opening and closing control instructions to the actuator, and receive door and window state feedback information in real time, while responding to manual operation signals to temporarily release automatic control.

2. The method for dynamic opening and closing decision of fire door and window based on multi-source fire characteristics according to claim 1, characterized in that: In step S1, the multi-source fire characteristic data includes smoke concentration, environmental temperature, flame intensity and personnel activity state.

3. The method of claim 2, wherein the method further comprises: In step S2, the feature fusion includes mean filtering processing of smoke concentration using sliding window, gradient change rate calculation of environmental temperature, and cross verification of video image recognition and infrared sensing data for personnel activity state; In the fusion process, the time synchronization of multi-source data is realized by Kalman filtering algorithm.

4. The method of claim 1, wherein the method further comprises: In step S4, the fire spread prediction algorithm uses a cellular automaton model; model parameters include cell temperature threshold, combustible material burning grade, air flow coefficient, fire door and window closing state, and prediction period; the opening and closing priority of the door and window is updated after each prediction.

5. The method for dynamic opening and closing decision of fire door and window based on multi-source fire characteristics according to claim 1, characterized in that: In step S4, the path planning algorithm increases the opening state weight of the fire door and window on the path, the smoke concentration attenuation coefficient and the personnel density correction factor in the cost function, calculates the optimal evacuation path set through dynamic programming, and adjusts the closing priority of the related door and window.

6. The method for dynamic opening and closing decision of fire door and window based on multi-source fire characteristics according to claim 1, characterized in that: In step S5, when receiving the manual opening signal, record the operation time, position and operator feature information, pause the automatic control of the door and window for a period of time, upload the operation information to the decision center, and recalculate the opening and closing priority of the door and window in the related area.

7. A dynamic opening and closing decision system for fire doors and windows based on multi-source fire characteristics, characterized by: A multi-source sensing sub-module for real-time acquisition of multi-source fire characteristic data of the monitoring area by distributed sensing nodes; A data preprocessing sub-module for temporal and spatial registration and feature fusion of the collected multi-source fire characteristic data, generation of comprehensive fire situation assessment results through outlier elimination and weighted confidence calculation; A decision analysis sub-module for calling the preset residential area house type atlas and personnel activity heat model, determining the evacuation priority of each area combined with real-time personnel distribution data; And for generating dynamic priority sequence by calculating the opening and closing weight value of each fire door and window through fire spread prediction algorithm and path planning algorithm based on the comprehensive fire situation assessment results and regional evacuation priority; An execution driving sub-module for sending opening and closing control instructions to the actuator according to the priority sequence, and receiving door and window state feedback information in real time, while responding to manual operation signals to temporarily release automatic control.

8. The multi-source fire feature based dynamic opening and closing decision system for fire doors and windows according to claim 7, characterized in that: The decision analysis module is connected with the data preprocessing modules of the areas through Ethernet, and the nodes of the execution driving modules are connected in a hand-in-hand mode through CAN bus, for receiving the output data of the preprocessing modules and generating door and window control instructions to be sent to the execution driving modules.

9. The dynamic opening and closing decision system for fire doors and windows based on multi-source fire characteristics according to claim 7, characterized in that: The manual interaction module is further included for realizing manual intervention and feeding back operation information. The power management module is further included for providing stable power supply for the modules.

10. A computer memory, characterized by: The computer program stored in the memory can be executed by the computer processor, and the computer program executes the dynamic opening and closing decision method for fire doors and windows based on multi-source fire characteristics as claimed in any one of claims 1 to 6.

Images