144 results about "Fire behavior" patented technology

The invention provides a tunnel fire behavior inversion method based on multi-modal fusion and physical constraint, and aims to solve the problem that the position and power of a fire source are difficult to invert accurately in real time in traditional fire behavior monitoring. According to the method, data, temperature distribution images and physical parameters of distributed temperature sensors in a tunnel are collected, and a spatial-temporal feature fusion network is constructed; designing an information leakage prevention training mechanism, and adopting a modal random discarding and sensor shielding technology to avoid overfitting of the model to a specific input mode; a physical constraint loss function is introduced, and the temperature gradient, the maximum temperature rise and the longitudinal attenuation law are combined to ensure the physical rationality of an inversion result; a coarse-fine two-stage position prediction framework is adopted, and meter-scale precision positioning of the position of a fire source is achieved. According to the invention, the power and position of the fire source can be inversed accurately in real time, and reliable technical support is provided for intelligent monitoring and emergency rescue of tunnel fire.

The invention discloses a fire alarm linkage system for fire engineering based on the Internet of Things. The operation process of the system specifically comprises the following steps: generating a dynamic risk probability distribution diagram based on a building three-dimensional point cloud model and multi-source data, and deploying a differential sensor array; environment multi-physical field parameters are collected in real time through a differential sensor array, and a multi-mode fire behavior sensing signal set is generated; building a fire situation credibility map: calling a multi-criterion decision module to calculate a linkage equipment weight distribution matrix based on the fire situation credibility map, and generating a multi-stage linkage control instruction set in combination with the building topological structure model and the personnel distribution thermodynamic diagram; and performing multi-cross-system cooperative execution and closed-loop optimization. The method has the following advantages and effects that the inherent limitation of a traditional system can be broken through by constructing an intelligent prevention and control framework combining risk quantification, situation deduction and decision closed loop, the personnel evacuation efficiency is effectively improved, and damage caused by major accidents such as detonation is reduced.

The invention relates to the technical field of urban fire safety rescue, in particular to a low-altitude fire fighting system and method based on urban CIM and Beidou positioning. According to the system and the method, full space-time accurate positioning is realized through the Beidou differential base station and the UWB indoor positioning equipment; integrating the urban information model system and unmanned aerial vehicle cluster data, and constructing a multi-source heterogeneous data set; a coordinate system is unified based on a space-time reference calibration module, and fire behavior prediction, path planning and resource scheduling are realized through AI computing nodes; the unmanned aerial vehicle task distribution module is used for realizing multi-vehicle cooperative rescue; and iteratively optimizing system parameters through a closed-loop adaptive optimization module. The method is suitable for fire emergency rescue in an urban complex building environment, and the rescue response speed, the decision-making precision and the cooperative combat capability are remarkably improved.

The invention relates to the technical field of image recognition, in particular to a fire behavior recognition method and system based on video monitoring. The technical problem that the early warning reliability of a video monitoring system on fire smoke is insufficient is solved. The method comprises the following steps: acquiring a monitoring video stream of a monitoring area and time sequence data acquired by a sensor in the monitoring area; determining an evaluation value of the to-be-detected area based on the image feature and the morphological change of the to-be-detected area; determining a confidence factor based on the form change trend of the to-be-detected region and the change trend of the time series data; determining a smoke authenticity value based on the evaluation value and the confidence factor; and adjusting an alarm threshold value of the smoke alarm based on the smoke authenticity value. The method is used for fire smoke early warning and monitoring scenes.

When the intelligent fire-fighting unmanned aerial vehicle cluster system works, the method comprises the following steps that 1, an intelligent fire-fighting unmanned aerial vehicle cluster detects a fire scene and searches a water source near the fire scene, and an optimal route is searched between the water source and the fire scene to lay a pressurizing water pump and a fire hose; 2, the intelligent fire-fighting unmanned aerial vehicle cluster controls a fire-fighting nozzle to conduct fire extinguishing operation, and the positions of a pressurizing water pump and a fire hose are adjusted according to fire behavior changes of a fire scene; and 3, the intelligent fire-fighting unmanned aerial vehicle cluster performs handover control on a fire-fighting nozzle, a pressurizing water pump and a fire-fighting hose in turn, and fuel oil is supplemented to the pressurizing water pump until fire extinguishing operation is finished. A fire-fighting water supply channel can be laid between a water source and a fire scene at an ultra-fast speed, the fire extinguishing operation speed is high, manual intervention is not needed, and nearly infinite fire-fighting water can be continuously provided.

The invention discloses a subway tunnel fire behavior spreading prediction method, which comprises the steps of 1, fire source type digital modeling, 2, fire scene initialization, 3, dynamic fire source loading and ignition triggering, 4, fire behavior spreading multi-physics field coupling calculation, 5, ventilation system dynamic response, 6, visual risk thermodynamic diagram generation, and 7, fire behavior spreading prediction. Step 7, carrying out real-time early warning on the safety margin; the method has the beneficial effects that a total factor modeling capability is realized, multi-dimensional parameter input from fire source characteristics to a tunnel environment is supported, a scene range covering a typical subway fire disaster is expanded, solving is realized through a multi-physics field simultaneous equation, a fire spreading error is reduced, smoke diffusion simulation precision is improved, and a dynamic ventilation adjustment and safety early warning mechanism is realized. And more buffer time is provided for emergency response.

The invention relates to the technical field of computer vision, and discloses a flame recognition and fire extinguishing system for indoor fire fighting, comprising: a binocular infrared imaging module for acquiring a thermal imaging image; the monocular visible light imaging module is used for acquiring a visible light image; the infrared stereoscopic vision module is used for carrying out processing and feature extraction on the thermal imaging images, carrying out feature aggregation to obtain an aggregated feature map, carrying out parallax optimization on the aggregated feature map, and carrying out calculation according to a parallax optimization result to obtain depth information of the thermal imaging images at different visual angles; the multi-mode stereoscopic vision fusion module is used for fusing the thermal imaging image with the depth information and the visible light image; the flame identification and fire behavior prediction module is used for performing flame detection according to the fused image, predicting a bounding box, confidence and a category label of the flame in the fused image, and predicting a future diffusion position of the flame, a diffusion scale of the flame and a diffusion trend of the flame; and the self-adaptive water gun spraying control module controls the water gun to execute spraying operation.

The invention relates to the technical field of fire prevention and control, and discloses an unmanned aerial vehicle cooperative control fire extinguishing operation method and system, and the method comprises the steps: determining the target geographic position parameter of a fire source region according to the observation parameters corresponding to a tower monitoring device and / or an investigation unmanned aerial vehicle when a fire behavior is monitored in a target region; fire extinguishing operation parameters for the fire source area are determined according to the target geographic position parameters and the fire scene image data of the fire source area; the fire extinguishing unmanned aerial vehicle is controlled to fly to the fire source area so as to perform networking operation with the investigation unmanned aerial vehicle, and after networking is completed, the fire extinguishing unmanned aerial vehicle is controlled to perform fire extinguishing operation on the fire source area through the investigation unmanned aerial vehicle and according to the fire extinguishing flight control parameters and bomb dropping parameters of the fire extinguishing unmanned aerial vehicle, so that manual control in the fire extinguishing operation process is reduced, and the fire extinguishing efficiency is improved. And an effective cooperative combat system between the unmanned aerial vehicles is formed, and the overall fire extinguishing operation efficiency is improved.

The invention relates to the technical field of fire-fighting management, and discloses an intelligent fire-fighting management method and system based on a multi-modal large model, and the method comprises the steps: 1, collecting multi-modal perception data in a field environment, and transmitting the multi-modal perception data as input data to a multi-modal semantic recognition module; and 2, performing modal analysis and semantic fusion on the input data by using the multi-modal semantic recognition module, and generating a unified semantic description containing fire state elements. According to the invention, a multi-modal perception data semantic fusion mechanism and a multi-modal large model-driven fire behavior recognition framework are adopted, and data of different modals from a camera, a temperature and humidity sensor, a smoke detector and combustible gas monitoring equipment are input into a unified semantic recognition module, so that unified fire behavior state semantic description is constructed; and the technical effects of multi-source data complementation and semantic-level collaborative recognition of the fire state are achieved.

The invention discloses a building fire safety management and control method based on a digital twinborn technology, and the method comprises the steps: constructing sensor-middle platform-model bidirectional mapping, and reconstructing a dynamic scene through employing a neural radiation field technology; fusing the cross-domain desensitization data based on federal transfer learning, and constructing a building total-factor dynamic digital mirror image; through a spectrum analysis algorithm, a fire source is positioned in real time, and a flame spreading track is predicted; performing fire simulation in linkage with a total-factor dynamic digital mirror image, and optimizing a fire-fighting resource scheduling path through a multi-target particle swarm optimization algorithm; a multi-target rescue scheme is generated, an asynchronous block chain is used for evidence storage of a fire-fighting decision instruction, a rescue key area is plotted, and an optimal evacuation route is planned; and converging federal node data to quantify the data contribution degree, reproducing a historical fire behavior and deducing a new scene to carry out iterative optimization. According to the method, the problems of data sensing fragmentation, difficulty in cross-domain fusion, fire prediction lag, underscientific resource scheduling, slow drill scheme iteration and the like in traditional management and control are solved.

The invention particularly relates to a control method applying an unmanned aerial vehicle and based on multi-modal characteristics of a fire source, and relates to the technical field of fire safety. Acquiring multi-modal data of a fire source in real time; comprehensively estimating the heat power of the fire source; correcting combustion intensity; and quantitative calculation of fire extinguishing agent demand. An infrared imaging sensor, a visible light camera and a gas sensor array are integrated, a multi-mode fire source sensing system is constructed, the sensing limitation that a traditional fire extinguishing system only depends on single temperature or image is broken through, fire source temperature distribution, flame forms and combustion gas concentration changes can be comprehensively captured, and complete data support is provided for fire behavior judgment; the thermal power of a fire source is estimated in a fusion manner, a fuel type is combined to calibrate a correction coefficient, a differential quantitative calculation model is established according to liquid and solid fire extinguishing agents, fire disasters of different fuels such as wood, gasoline and plastic are adapted, and economy and fire extinguishing reliability are both considered.

The invention discloses an ancient building group fire early warning method and system based on an internet platform, and relates to the technical field of fire early warning, and the specific implementation scheme is as follows: obtaining a visible light image, and determining a scene type based on smoke detection confidence; the method comprises the following steps: after triggering to execute registration operation on an original infrared image, extracting an infrared feature map and a visible light feature map, generating an attention weight map according to the infrared feature map and the visible light feature map, and generating a preliminary fusion feature by combining the infrared feature map and the visible light feature map; performing dimension reduction compression processing on the preliminary fusion feature to obtain a low-dimensional feature vector, and inputting the low-dimensional feature vector into a classifier to obtain a fire occurrence probability of the current monitoring grid so as to select an early warning scheme; and marking the current monitoring grid as a risk source grid, calculating a directional propagation coefficient, updating a fire occurrence probability of an adjacent target grid, and adjusting an early warning scheme. According to the technical scheme of the invention, the problem of poor effectiveness of fire early warning of the ancient building group caused by abnormal fire behavior recognition is solved.

The invention provides a fire detection and disposal system and method based on multi-robot cooperation, and the system comprises a quadruped robot platform, a cloud platform, and a wheel-foot robot platform. Wherein the quadruped robot platform is used for detecting a fire behavior and sending information to the cloud platform in real time; the cloud platform receives information of the quadruped robot platform and dispatches and controls the quadruped robot platform and the wheel-foot robot platform; the wheel-foot robot platform is used for receiving an instruction of the cloud platform to execute fire extinguishing treatment; according to the method, the system is used for fire detection and disposal.

The invention provides a multi-sensor-based detection cabin fire-fighting monitoring and fire-fighting processing method and system, and relates to the technical field of monitoring processing, and the method comprises the steps: obtaining multi-sensor real-time monitoring data, employing a deep learning model to evaluate a fire behavior state, employing a distributed edge calculation mode to carry out a fire behavior response decision based on a fire behavior evaluation result, and the movable fire extinguishing device is controlled to autonomously move to the optimal fire extinguishing position, spraying parameters are adaptively adjusted, the execution effect is monitored in real time, and the deep learning model is fed back and optimized. The fire behavior evaluation accuracy and the fire-fighting processing efficiency are improved, and the reliability and the adaptability of the system are enhanced.

The utility model relates to semi-surrounding type foldable and movable automobile fire extinguishing equipment. The semi-surrounding type foldable and movable automobile fire extinguishing equipment comprises a movable integrated box body, a chassis water spraying frame, two lateral water spraying pipes, a first fire insulation fence and two second fire insulation fences, the chassis water spraying frame is connected to the lower end of the surface of the movable integrated box body and can be turned over, the two lateral water spraying pipes are connected to the lower end of the surface of the movable integrated box body and located on the two sides of the chassis water spraying frame, and the lateral water spraying pipes can be turned over; the first fire insulation fence is connected to the mobile integrated box body and faces the chassis water spraying frame, a water spraying opening is formed in the first fire insulation fence, the two second fire insulation fences are rotationally connected to the surfaces of the two lateral water spraying pipes correspondingly and can be turned over, and four-side water spraying is conducted on a vehicle on fire through the chassis water spraying frame, the two lateral water spraying pipes and the water spraying opening in the first fire insulation fence; and the first fire barrier and the two second fire barriers are arranged, it can be guaranteed that flames cannot be splashed to the outer sides of the first fire barrier and the two second fire barriers when the fire behavior is large, and the whole fire extinguishing process is safer.

The invention provides a smoke and fire detection alarm method and a camera, and relates to the technical field of fire safety intelligent monitoring and emergency response, and the method comprises the steps: collecting an image of a monitoring area through the camera; analyzing the image of the monitoring area, extracting the form, texture, color and dynamic change multi-dimensional features of smoke and flame in the image, comparing the features with a preset smoke and flame feature database, analyzing the possibility of existence of smoke or flame features, and obtaining a possibility value; according to the possibility value, if smog or flame characteristics are analyzed and confirmed, an alarm triggering instruction is automatically obtained and sent out; based on an alarm triggering instruction, a remote alarm notification is automatically sent to a specified contact person through a wireless communication network in various modes of making a call, sending a short message or pushing a message by means of a built-in communication function. According to the invention, intelligent and efficient management and control of the whole process from early-stage accurate recognition of the fire behavior to emergency disposal can be realized.

The invention provides a fire detection method and system and a computer readable storage medium, and the method comprises the steps: carrying out the multiple scanning of a surrounding environment from coarse to fine, achieving the three-dimensional coverage scanning, and avoiding the missing detection caused by a single scanning parameter; in each scanning process, the acquisition unit is controlled to scan the surrounding environment based on the current vertical range, fire behavior identification is carried out on each frame of infrared image acquired in the current scanning process in real time to obtain a current identification result list, and the current vertical range is determined based on the last identification result list; in this way, the vertical scanning range is gradually focused to the fire point area, comprehensive scanning is achieved, and resource waste is avoided. According to the method, the confidence coefficient of the remaining candidate fire point areas is calculated after the interference heat source of the surrounding environment is eliminated from the candidate fire point list, and fire point alarm is performed when the confidence coefficient exceeds the preset confidence threshold value, so that the accuracy of fire detection is ensured, and false detection is avoided.

The fire extinguishing robot comprises a machine body, a moving device, a fire extinguishing device and an operation device, the machine body comprises a storage box, the storage box is used for containing a fire extinguishing medium, the moving device is connected with the bottom of the machine body and used for walking, the fire extinguishing device is arranged on the side face of the machine body, and a nozzle of the fire extinguishing device communicates with the storage box; the nozzle can rotate around the first axis and the second axis, the operation device is arranged at the top of the machine body and comprises a grabbing and clamping assembly and a mechanical arm, the grabbing and clamping assembly is arranged at the end of the mechanical arm, the mechanical arm can rotate around the third axis, and the mechanical arm is used for controlling the height of the grabbing and clamping assembly. Wherein the first axis and the third axis extend in the vertical direction, and the second axis extends in the horizontal direction. The moving device, the operating device and the fire extinguishing device are matched with one another, so that the fire extinguishing robot can walk, remove environmental obstacles and assist operation actions, fire behavior processing actions are enriched, and the fire extinguishing efficiency is improved.

The invention discloses a mining vehicle early fire early warning method and system based on multi-source information fusion, and belongs to the technical field of fire alarm, and the method comprises the steps: carrying out the multi-source monitoring of a mining vehicle, and obtaining the environment, working condition and visual monitoring data of the vehicle; fire sign sensitive feature detection is carried out on the vehicle environment monitoring data; fire sign sensitive feature detection is carried out on the vehicle operation condition data; fire sign sensitive feature detection is carried out on the vehicle visual monitoring data; performing single-factor fire deduction on the environment, working condition and visual fire sensitive feature vectors according to the vehicle fire historical event set; and performing multi-factor coupling fire behavior deduction according to the fire behavior deduction first map, and executing early fire behavior early warning according to the fire behavior deduction second map. The technical problems that in the prior art, mining vehicle fire early warning depends on single-dimensional monitoring data, information is one-sided, and early multi-factor collaborative risks are difficult to capture, so that fire missed judgment, misjudgment and untimely early warning are caused are solved.

The invention discloses a simulated fire extinguishing examination method for a fire drill box, and the method comprises the steps: presetting examination scene parameters through a control unit, including an initial fire behavior form defined by a visual simulation unit and a dynamic simulation unit, and a qualified standard of an intelligent examination module; the scene simulation module is started according to preset assessment scene parameters, the visual simulation unit presents a flame visual form, and the dynamic simulation unit drives the flexible curtain to generate a dynamic effect to form a simulated fire behavior; a practicer operates the fire extinguishing simulation device, a simulation injection track is emitted to the target sensing unit through the simulation injection assembly, and the operation sensing module synchronously collects operation posture data, operation distance data and operation duration data; and the intelligent assessment module receives process data of the operation sensing module and sensing data of the target sensing unit, compares the process data and the sensing data with a preset qualification standard, generates an assessment result and outputs the assessment result through the display unit, and meanwhile, the control unit adjusts the simulated fire behavior state of the scene simulation module according to the sensing data until the simulated fire behavior is extinguished.

The invention provides an electric power fire-fighting emergency decision-making method and system based on a knowledge graph, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing an electric power fire-fighting knowledge graph, integrating transformer station equipment ledger data, real-time monitoring data, external environment data and historical case data, and building an association relationship among multi-source data, thereby obtaining an electric power fire-fighting emergency decision-making result; a structured knowledge base supporting emergency decision making is obtained; performing dynamic risk reasoning based on a structured knowledge base and fire alarm data transmitted in real time, identifying a fire behavior influence range and a key risk point, and obtaining a preliminary differentiated emergency disposal scheme based on a reasoning result; and extracting spatial features of the key risk points and the monitoring positions, dynamically determining and updating boundary parameters of the fire behavior influence area through a spatial feature fitting algorithm, and defining the dynamically updated fire behavior influence area. According to the method, the whole-process intelligence from data integration to instruction execution is realized.

The invention relates to the field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle-based fire extinguishing device which comprises an aerial vehicle body, a plurality of paddle arms are uniformly and fixedly connected to the outer wall of the aerial vehicle body, a driving paddle is mounted at the end of each paddle arm, and a placement frame is fixedly connected to the bottom of the aerial vehicle body; a liquid storage box and a powder storage box are placed on the two sides of the upper end of the placement frame respectively, a grabbing and clamping support is arranged in the placement frame, the grabbing and clamping support grabs the liquid storage box and the powder storage box at the same time and clamps and fixes the liquid storage box and the powder storage box, a supporting frame is fixedly arranged at the bottom of the placement frame, and a control pipe is fixedly arranged at the top in the supporting frame. For different fire behaviors in different areas, the aircraft can be flexibly switched between a liquid spraying mode and a powder spraying mode, a fire extinguishing medium does not need to be replaced after shutdown, the aircraft can quickly reach a fire scene to extinguish fire, efficient transfer of the aircraft among different fire scenes is effectively guaranteed, and the fire extinguishing effect can be effectively improved.

The invention relates to a fabric warehousing device and a working method thereof, and relates to the technical field of warehousing, the fabric warehousing device comprises a storage frame system, a conveying vehicle system, a plurality of limiting systems and a plurality of fireproof curtain devices, the storage frame system is provided with a plurality of containing cavities, the bottom of each containing cavity is provided with a plurality of containing conveying wheels, and the conveying vehicle system is slidably installed on the side edge of the storage frame system; the limiting systems are installed at the two ends of the containing cavity, the fireproof curtain devices are installed on the storage frame system in a horizontal sliding mode, each fireproof curtain device comprises a sliding block, fireproof cloth and an unfolding roller, one end of the fireproof cloth is installed on the sliding block, the fireproof cloth is wound around the unfolding roller, and the unfolding roller is detachably installed at the bottom of the sliding block. The sliding block horizontally slides along the top of the storage frame system through the sliding block and the sliding rail, the sliding rail is horizontally installed on the top of the storage frame system, the sliding block is installed on the sliding block, the sliding block horizontally slides through the motor and the synchronous belt, an electromagnet used for attracting the unfolding roller is arranged on the sliding block, fire behavior control is facilitated, and fire disasters are prevented.

The utility model discloses an overhead rail type fire-fighting robot which comprises a main body unit, a main body unit, a main body unit and a main body unit, the main body unit comprises a sliding rail, a sliding block is connected to the sliding rail in a sliding mode, and two bidirectional monitoring heads are arranged on the sliding block; and the positioning unit comprises a screw rod, the two ends of the screw rod are rotationally connected to the inner walls of the two sides of the sliding rail correspondingly, the screw rod penetrates through the sliding block in a threaded mode, and the surface of one side of the sliding rail fixedly communicates with a reciprocating motor. The reciprocating motor drives the screw rod to rotate, so that the sliding block translates left and right, rapid positioning of fire extinguishing is facilitated, the response time of fire extinguishing is shortened, the servo motor drives the fire-fighting water box to rotate, a plurality of water spraying heads extinguish fire in surrounding areas, dense fire extinguishing water curtains are formed, fire behaviors in different directions are effectively extinguished, and fire extinguishing efficiency is improved. And when a fire source is located below the equipment, rotation is stopped, water enters the porous drainage pipe and is vertically sprayed downwards, accurate fire extinguishing is achieved, the fire extinguishing flexibility of the equipment is improved, and the fire fighting range is widened.

The invention provides a fireproof flame-retardant bag, and relates to the technical field of fire extinguishing. The bag comprises a bag body and a bag body top opening, a bag cover is connected to the bag body top opening, a first nylon fastener tape is arranged between the bag body and the bag cover, at least one lock catch assembly is arranged between the bag cover and the bag body, the layered structure of the bag body and the bag cover sequentially comprises an inner layer, a middle layer and an outer layer from inside to outside, the inner layer is made of high-silica fiber cloth, and the outer layer is made of high-silica fiber cloth. The middle layer is a high-silica needled felt, and the outer layer is aramid fiber cloth. The thermal runaway lithium battery or the ignition object can be isolated from the outside, and the purpose of extinguishing and controlling the fire behavior is achieved.

The invention provides a cable trench liquid nitrogen fire extinguishing scheme generation method, system and device and a medium, and belongs to the field of intelligent fire prevention and control, and the method comprises the steps: obtaining structure data of a cable trench and real-time monitoring data of a sensor, and obtaining prediction results of corresponding fire behavior expansion trend data, liquid nitrogen cooling temperature field change data and oxygen concentration replacement data. Performing parameter combination search by using a target optimization algorithm based on the prediction result to obtain an optimal parameter combination; and acquiring actual measurement data of the environment of the fire scene, dynamically comparing the actual measurement data with the prediction result, and performing correction feedback. And recalculating by using a target optimization algorithm based on the corrected prediction result to obtain a real-time adjusted fire extinguishing scheme. Accurate fire recognition, self-adaptive fire extinguishing control and resource optimization configuration are achieved, the fire extinguishing efficiency is remarkably improved, and the equipment damage risk is reduced.

The utility model discloses high-temperature-resistant fireproof glass which comprises a fireproof glass assembly, the fireproof glass assembly comprises a glass assembly body and a protective frame, the glass assembly body comprises first fireproof glass and second fireproof glass, and a clamping cavity is formed between the first fireproof glass and the second fireproof glass. A first stabilizing net and a second stabilizing net are symmetrically arranged on the two sides of the interior of the clamping cavity respectively, and filling glue is arranged in the middle of the interior of the clamping cavity and is transparent thermosetting resin glue. According to the fireproof glass, the fireproof effect when the fireproof glass is broken is achieved, the practicability is improved, and therefore the problems that when the fireproof glass is broken due to the high temperature effect or the impact of external objects in the fire disaster process, the fireproof performance can be greatly reduced, even the fire behavior can be rapidly spread, and the use safety and practicability are reduced are solved.

The invention discloses a control method and device of a fire rescue auxiliary system and a storage medium, and relates to the technical field of data processing. According to the method, the fire scene image, the thermal imaging, the gas sensing and the audio multi-mode detection data are collected, and the pre-trained multi-mode learning model is used for extracting the features and identifying the comburent to replace experience judgment to reduce deviation; meanwhile, a fire behavior range evolution graph is generated through a time sequence model in combination with motion features and meteorological data obtained through an optical flow method to achieve accurate pre-judgment, finally, a target rescue plan is determined based on a comburent recognition result and the fire behavior evolution graph, a complete data-driven decision link is formed, a scientific basis is provided for rescue, and the rescue efficiency is improved. Therefore, the problems of strong subjectivity, inaccurate pre-judgment and the like of empirical decision are solved, and the rescue efficiency is improved.

The invention provides a pressure control type dry powder fire extinguishing experiment device which comprises a fire extinguishing unit, a control unit, a fire source simulation unit and a data collection unit. According to the device, aiming at different combustion types, the doses of various fire extinguishing agents in the fire extinguishing unit are adjusted, and even the types of the fire extinguishing agents are changed, and the first control part can control the dose output of the first fire extinguishing part; the second control part can control whether the fire extinguishing agent in the first fire extinguishing part is output into the second fire extinguishing part or not and can also control whether the mixed fire extinguishing agent in the second fire extinguishing part is output or not, and then fire extinguishing simulation for adjusting fire behaviors of different scales in different places is achieved by adjusting the position of an output port of the second fire extinguishing part. And the fire extinguishing effect is analyzed according to the received data so as to conveniently count the optimal fire extinguishing mode, so that the fire extinguishing device is more reasonable in design, extinguishes fire more effectively and improves the fire extinguishing effect compared with the existing fire extinguishing device which adopts the same processing mode to extinguish fire of different degrees in various places.

The invention relates to the technical field of image recognition, and particularly discloses a car washer construction real-time fire smog detection and recognition system based on computer vision, and the system comprises the steps: carrying out the image enhancement processing of a video stream collected in real time, and obtaining a preprocessing image sequence; foreground segmentation is carried out by adopting dynamic background modeling in combination with a predefined inherent moving part mask of the car washer, and a real moving foreground area is extracted; based on color space analysis and a dark channel theory, parallelly extracting a suspected flame region and a suspected smoke region from the motion foreground region; respectively extracting static texture features and dynamic shape change features of the flame region to form a flame feature vector, and extracting color statistical features and gradient direction features of the smoke region to form a smoke feature vector; inputting the feature vectors into a pre-trained classification model to obtain a fire behavior and smoke probability value, and outputting a structured recognition result containing category and position information when the probability value exceeds a set threshold value; the real fire behavior and the environment interference can be effectively distinguished.