466 results about "Fire smoke" patented technology

The invention discloses a fire smoke and fire source accurate positioning method based on image recognition, and the method comprises the following steps: S1, collecting multi-modal data, and carrying out the graying, denoising, histogram equalization and shielding correction preprocessing; s2, inputting the preprocessed data into a vortex sensing network to generate a preliminary detection result of flame and smoke; s3, dividing the scene into dynamic space blocks by using a dynamic space division algorithm and allocating priorities; s4, eliminating non-fire feature interference through an environment feature filter, and generating an optimization candidate region; s5, inputting the candidate area into an event-driven time sequence analysis module, and extracting a key frame to analyze flame and smoke diffusion and time trend; s6, verifying position consistency by adopting a flame and smoke joint detection method, and generating a three-dimensional space positioning result; and S7, generating a fire three-dimensional thermodynamic diagram according to three-dimensional positioning and triggering an alarm mechanism. According to the invention, accurate detection and positioning of fire smoke and a fire source are realized by using a vortex sensing network, an event-driven mechanism and the like.

The invention discloses a fire smoke image early recognition method based on multi-modal fusion. The method comprises the following steps: S1, collecting multi-modal data and carrying out time alignment; s2, constructing a visible light branch, an infrared branch and a photoacoustic branch, generating multi-modal features, and storing the multi-modal features in a shared feature pool; s3, embedding a space-time tracking module in the shared feature pool, and generating global feature representation; s4, generating a dynamic background template by adopting a low-rank matrix decomposition algorithm, and separating and removing background noise; s5, multi-modal features are fused in the shared feature pool through a lightweight self-attention mechanism, and missing features are compensated; s6, enhancing an early smoke signal through a sparse feature enhancement algorithm, and performing fire state classification and smoke diffusion path prediction by applying a multi-task classification network; and S7, updating the shared feature pool and the space-time tracking module through a dynamic feedback mechanism. According to the invention, early-stage accurate identification of fire smoke is realized by using multi-modal fusion, space-time tracking and dynamic feedback methods.

The invention discloses a tunnel fire non-equilibrium control-smoke exhaust automatic adjustment control system and method, and belongs to the field of frequency conversion fan technology and tunnel fire control-smoke exhaust ventilation. The system comprises a data acquisition module, a data transmission module, a data processing and control algorithm module, a fan driving module and an emergency disposal module. The system dynamically and automatically controls the operation state of the smoke exhaust fan according to real-time fire smoke in the tunnel, and the exhaust air rate is reasonably adjusted. The abnormal environment parameters of the tunnel ceiling are collected through the sensing equipment, so that the approximate position of a fire in the tunnel and the real-time dynamic state of fire smoke spreading are obtained. And parameters such as the smoke front spreading speed and the smoke exhaust efficiency of the fan at the smoke exhaust port are obtained by applying an algorithm program to automatically control the start, stop and operation frequency of the fan. The interlocking arrangement of the emergency disposal module ensures that the other combinations are started under the condition that the exhaust air rate of one set of smoke exhaust port-smoke exhaust fan combination of the system is insufficient, fire smoke spreading is effectively controlled, and it is generally ensured that smoke is efficiently exhausted while the fire smoke is controlled within a safe range by the system.

The invention discloses a high-reliability fire detection method and system, and relates to the technical field of fire alarm, and the detection method comprises the following steps: S1, setting a threshold value; s2, initializing a background value, updating the detection value at regular time, and updating the background value to initialize the background value; s3, identifying the aerosol type; s4, identifying the movement condition of the personnel; s5, identifying a high-humidity environment; s6, identifying a high-temperature environment; and S7, judging a fire alarm. The detection system comprises a threshold setting module, an initialization module, a smoke detection module, a radar system, a humidity detection module, a temperature detection module, a background value updating module and an alarm module. According to the invention, the radar system is used for judging and detecting the motion state of environmental personnel, detection is carried out in combination with factors such as smoke, temperature and humidity, and different levels of alarm thresholds are set for judgment, so that the identification capability of the fire detector on non-fire smoke is enhanced, and the false alarm probability under the non-fire smoke condition is reduced.

The invention discloses an efficient fire smoke detection method based on lightweight convolution and cross channel feature fusion. The method belongs to the field of deep learning in computer vision, and comprises the following steps: capturing a video signal by using a camera, segmenting the video signal into independent images, and carrying out image preprocessing; and detecting the images by using a trained fire detection model, and displaying a detection result. According to the method, through lightweight convolution fitting and cross channel feature fusion, the detection precision and the real-time performance of the model are improved; on the basis of a YOLOv11 model, a lightweight convolution structure is adopted to reduce the calculation overhead, and meanwhile, the distinguishing capability of fire smoke features is enhanced through a cross channel feature fusion mechanism, so that the detection robustness and precision of the model in a complex scene are further improved. The improvement provides a new technical path for a fire early warning system.

The invention relates to the technical field of tunnel fire smoke exhaust, and discloses a tunnel fire smoke exhaust method and system, and the method comprises the steps: receiving a fire signal, and recognizing the fire position information; dividing the tunnel into three functional areas including a fire disaster area, an upstream evacuation area and a downstream evacuation area according to the fire position information; calculating control parameters required for forming an air pressure isolation belt; the control instruction is sent to smoke exhaust equipment, the fire disaster area is kept in a negative pressure state, and upstream and downstream evacuation areas are kept in a positive pressure state; data are collected in real time, control parameters are dynamically adjusted, and the air pressure difference between the fire disaster area and the evacuation area is maintained. According to the method, safety evacuation passages on the two sides of the tunnel are guaranteed through regional differential air pressure control strategies; continuously optimizing control parameters by adopting a model predictive control method; and a multi-objective optimization algorithm is adopted, so that the system operation cost is reduced while efficient smoke discharge is realized.

The invention relates to a power transmission line fire smoke identification method based on improved YOLOv9. The method comprises the following steps: constructing a fire smoke image data set; constructing a power transmission line fire smoke detection model; inputting the training set into the power transmission line fire smoke detection model for training, and storing the optimal power transmission line fire smoke detection model obtained through training; and inputting a to-be-identified power transmission line fire smoke picture into the optimal power transmission line fire smoke detection model to obtain a power transmission line fire smoke picture detection result. According to the method, depth separable convolution is introduced, so that the calculation amount can be reduced, parameters are reduced, and the network detection speed is increased; a parallel weighted mixed domain attention module is adopted to enhance extraction of target features in the fire smoke image; the up-sampling content perception feature recombination network structure CARAFE has a larger receptive field, the perception of important content is enhanced, and the lightweight level of the model can be kept due to the fact that the operation amount is small.

The invention discloses an expressway tunnel abnormal event recognition method based on multi-scale polarization fusion, relates to the technical field of intelligent recognition of road traffic videos, and is used for solving the problem of robust recognition of trailing collision, fire smoke and abnormal static behaviors in an expressway tunnel scene. The method comprises the following steps: acquiring polarization angle and polarization degree information of each pixel point in a vehicle driving process; then, the image is divided into a plurality of partitions according to longitudinal illumination changes, a time sequence locking window is established in each partition, and the difference between traffic flow reflection characteristics and background interference is extracted; and identifying a smoke area by constructing a disturbance graph and a direction texture graph, calibrating a trailing collision risk, and judging an abnormal static behavior. And finally, an event atlas is generated, full-process identification closed loop and response cooperation are ensured through structure fingerprints and version numbers, and a high-robustness identification means is provided for fire, trailing and abnormal static targets in a tunnel scene.

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.

The invention belongs to the technical field of tunnel catastrophe, and particularly relates to an intelligent feedback type tunnel catastrophe monitoring method, which comprises the following steps of: 1, deploying a tunnel monitoring system; a temperature sensor, a smoke sensor, an air velocity sensor and a gas concentration sensor are arranged in the tunnel; the temperature sensor is used for monitoring temperature changes in the tunnel. According to the intelligent feedback type tunnel catastrophe monitoring method, the safety and the emergency response capability of the tunnel are effectively improved through real-time data monitoring and analysis and an automatic control mechanism. Firstly, through temperature, smoke, gas concentration and air velocity sensors, the system can detect and identify potential catastrophe risks in a tunnel in time, such as fire, smoke diffusion and harmful gas leakage. Once an abnormality occurs, the system performs catastrophe prediction through an algorithm model, and performs accurate evaluation on a fire propagation path and smoke diffusion in combination with a simulation analysis result, thereby providing reliable data support for quick response.

The invention discloses an intelligent layering and guiding device for highway tunnel fire smoke and a control method, and relates to the technical field of tunnel fire safety, a smoke flow Froude number is introduced as a direct control target, the parameter represents the ratio of smoke flow inertia force to buoyancy force, the numerical value directly determines the stability of a layering interface, and the layering interface can be directly controlled. The Froude number of each subarea of the tunnel is calculated in real time through a sensing network and is compared with a critical value calibrated through an experiment, when a real-time value is lower than the critical value, it is indicated that inertia force is relatively insufficient, the buoyancy effect is dominant, and instability and entrainment are likely to happen to an interface between a smoke layer and lower cold air, and then according to a control algorithm, the smoke layer and the lower cold air are controlled. The micro jet fan applies directional inertia force to a smoke layer by adjusting the angle and the speed, the intelligent induction smoke outlet optimizes local pressure difference and flow by adjusting the opening degree and assists in maintaining flowing, the smoke flowing state is actively locked in a stable layered flow interval, and mixing and sedimentation caused by flow state instability are prevented.

The invention relates to the technical field of smoke particle detection, in particular to a fire smoke particle detection method and system for intelligent fire fighting, and the method comprises the steps: obtaining the fire smoke particle concentration and temperature of each position in each time window, acquiring a fire smoke particle abnormal fluctuation coefficient and a temperature rise saliency value of each position in each time window, further acquiring a smoke particle diffusion saliency of each position in each time window, and predicting the smoke particle diffusion saliency of an adjacent position of each position at the current moment. Obtaining a smoke particle state influence coefficient of each position at the current moment; and predicting the fire smoke concentration data of each position at the current moment, and optimizing the smoothing coefficient of the prediction algorithm according to the smoke particle state influence coefficient of each position at the current moment in the prediction process so as to obtain the fire smoke particle concentration through the predicted value. According to the invention, the accuracy of fire smoke particle concentration distribution detection can be improved.

The invention relates to the technical field of image data processing, in particular to a belt material conveying fire early warning method based on image processing. The method comprises the following steps: firstly, acquiring a reference RGB image when a conveyor belt is normally not on fire, and extracting an ROI from the reference RGB image; the method comprises the following steps: firstly, acquiring an actual scene image at the same shooting angle position, performing smoke analysis on an ROI region of the actual scene image to obtain smoke confidence of each ROI pixel point in the ROI region, and performing fire early warning identification on the actual scene image based on the smoke confidence of each ROI pixel point so as to detect whether a conveyor belt has a fire or not. And early fire smoke generated by comparing flames is detected, so that fire signs can be found in advance, and measures can be taken earlier.

The invention discloses a fire smoke detection method based on an improved YOLOv8 model, and the method comprises the steps: 1), replacing a Neck layer of the YOLOv8 model with a Gather-Distribate module, and adding a SimAM attention mechanism in front of an SPPF layer of a backbone network Backbone of the YOLOv8 model, and obtaining a fire smoke detection model; 2) iteratively training the fire smoke detection model by using a training set; and 3) inputting a to-be-identified fire smoke image into the trained fire smoke detection model to obtain a detection and identification result. The improved YOLOv8 model has strong generalization ability, improves multi-scale feature extraction ability, especially small targets in fire smoke, focuses network attention on the to-be-detected targets, reduces interference of uncorrelated backgrounds, and effectively improves the detection precision of the model.

The invention relates to the technical field of fire alarm devices, in particular to a fire-fighting fire alarm structure which comprises a protective shell, a ventilation cover is detachably mounted at the bottom end of the protective shell, a stabilizing plate is fixedly mounted at the inner end of the protective shell, a speed reduction disc is rotatably mounted at the center of the stabilizing plate, and a driving rod is arranged at the bottom end of the speed reduction disc. Fan blades are fixedly installed at the ends, away from the speed reduction disc, of the driving rods through bolts, an air suction barrel used for sucking air is fixedly installed at the upper end of the inner side of the stabilizing plate, a stabilizing frame is fixedly installed at the bottom end of the inner side of the stabilizing plate and located on the left side of the air suction barrel, and a metering device used for recognizing whether smoke is fire gas or not is arranged at the inner end of the stabilizing frame; according to the invention, by weighing the mass of the smoke particles, whether the smoke is fire smoke or not is judged, so that the fire smoke and the cigarette smoke can be distinguished, and false alarms can be reduced.

The invention discloses an early forest fire smoke automatic detection system and method, and belongs to the field of forest fire monitoring and early warning. The system comprises a YOLOv7-Smokey small-range smoke detection network, a PyTorch framework, a TensorRT technology and an NVIDIA Jetson Nano embedded platform, and is characterized in that the YOLOv7-Smokey small-range smoke detection network is connected with the TensorRT technology through the NVIDIA Jetson Nano embedded platform. The method comprises the following steps: S1, carrying out image data collection and data enhancement on early forest fire smoke through a network and public data; s2, making an early forest fire smoke detection data set; s3, a YOLOv7-Smokey backbone network is designed, and training is carried out; s4, deploying the YOLOv7-Smokey network model to an NVIDIA (Noise Visual Identity Architecture) Jetson Nano embedded platform; s5, performing reasoning acceleration processing on the YOLOv7-Smokey network by using a TensorRT technology; s6, performing real-time early forest fire smoke detection on an NVIDIA Jetson Nano platform by using a network camera; and S7, transmitting a reasoning result to a server in a video stream pushing mode. The method is used for deploying an early forest fire smoke detection system on an NVIDIA Jetson Nano embedded platform, the real-time performance of detection is ensured while the detection precision is ensured, the operation consumption is reduced, and marginalized intelligent detection is realized.

The invention relates to the technical field of smoke exhaust fan control, in particular to a fire-fighting smoke exhaust fan control method and system based on fire smoke spreading self-starting and self-stopping. A fire detector is adopted to detect whether a fire exists in a set area or not; real-time temperature information and real-time shielding information in the protected area are collected in real time; fire information is obtained based on the real-time temperature information and the real-time shielding information; judging whether a fire early warning criterion is met or not according to the fire information; when the fire hazard early warning criterion is met, controlling the motor speed of the smoke exhaust fan corresponding to the protected area set by the fire hazard detector to be increased; when the fire hazard early warning criterion is not met, the motor speed of the smoke exhaust fan corresponding to the protected area set by the fire hazard detector is controlled to be kept unchanged at the existing running speed, and a comprehensive fire hazard environment sensing system is constructed by collecting real-time temperature information and real-time shielding information at the same time; therefore, the system can judge the development condition of the fire and the spreading trend of the smoke more accurately.

The invention relates to the technical field of smoke alarm, and particularly discloses an anti-false-alarm fire-fighting smoke alarm method and system and a storage medium, and the method comprises the steps: carrying out the deep analysis through the refined obtaining of the data collection process parameters of a fire-fighting smoke sensing device, obtaining the data collection sensitivity factors, and combining with the data analysis process parameters to obtain the false alarm of the fire-fighting smoke sensing device. The step is crucial for improving the accuracy of the fire-fighting smoke sensing device, a scientific basis is provided for judging whether the performance of the fire-fighting smoke sensing device is optimized or not, the false alarm rate is effectively reduced, and the overall efficiency of the fire-fighting smoke sensing device is improved. The environment parameters of the target area are collected in real time through the fire-fighting smoke sensing device, the smoke fire-fighting demand coefficient of the target area can be accurately evaluated in combination with the response precision factor, the coefficient directly guides whether false alarm prevention and early warning measures need to be carried out on the target area or not, and therefore the fire risk is effectively prevented.

The invention relates to the technical field of intelligent sensors, in particular to an intelligent fire-fighting fire smoke particle detection method, which comprises the following steps: acquiring multiple frames of target images of a target area, and determining whether the smoke area in each frame of target image is a fire smoke area according to the gray value of the smoke area in each frame of target image; determining the actual brightness of each sub-region in the fire smoke region under the condition that the fire smoke region is the fire smoke region; determining the global concentration of the fire smoke area according to the original brightness, the actual brightness of each sub-area and the number of pixels, and determining the instantaneous acceleration of the smoke concentration based on the global concentration of the fire smoke area in the target image of the current frame and the global concentration of the fire smoke area in the target image of the previous frame; and determining a fire risk grade by using the instantaneous speed increase of the smoke concentration and triggering an alarm of the corresponding grade. Therefore, the accuracy and reliability of the detection result of the fire smoke particles are improved.

The invention provides a fire smoke target detection method based on improved YOLOv11. The method comprises the following steps: constructing a fire smoke image data set; a CIB module is added to C3K2 in a YOLOv11 model, an inverted residual structure and depth separable convolution are used for improvement, and a fire smoke target detection model is constructed based on the improvement; selecting a data enhancement mode, and setting training parameters; training a fire smoke target detection model based on the improved YOLOv11; and testing the trained fire smoke target detection model based on the improved YOLOv11 to obtain a test result. The invention further provides a fire smoke target detection system based on the improved YOLOv11. On the basis of original YOLOv11, a CIB module is introduced into a core structure C3K2, an inverted residual structure and depth separable convolution are utilized, and the feature expression ability is kept while the calculated amount is reduced.

The invention relates to the technical field of intelligent fire protection of a thermal power plant, and discloses an intelligent fire smoke detection method and system for intelligent fire protection of the thermal power plant, and the method comprises the steps: collecting a video stream of a fire protection monitoring region through video monitoring disposed in the fire protection monitoring region of the thermal power plant, and extracting a video frame in the video stream; performing spatial texture feature extraction and time change feature extraction on the video frames to obtain a fire smoke spatial texture feature map and a fire smoke time change feature map; performing feature fusion on the fire smoke space texture feature map and the fire smoke time change feature map to obtain fire smoke fusion features; identifying the fire smoke fusion feature through a pre-trained fire smoke identification model to determine a fire smoke identification result and identification confidence of the fire-fighting monitoring area; and acquiring sensor data acquired by a fire-fighting sensor deployed in the fire-fighting monitoring area, and determining a fire smoke detection result of the fire-fighting monitoring area based on the fire smoke identification result, the identification confidence and the sensor data.

The invention relates to the technical field of tunnel fire smoke accident data processing, and discloses a tunnel fire smoke intelligent control method and an emergency disposal system, and the system comprises a tunnel fire smoke accident identification module, a tunnel fire smoke accident rescue information analysis module, and a tunnel fire smoke accident rescue information feedback module. The tunnel fire smoke accident occurrence type is accurately analyzed by scientifically presetting tunnel fire smoke accident occurrence type image parameters in combination with a deep learning intelligent algorithm and standard tunnel field real-time image data, and the occurrence reason type of the tunnel fire smoke accident is accurately evaluated and generated based on the deep learning intelligent algorithm. And according to the tunnel fire smoke accident occurrence type analysis parameters, the tunnel fire smoke accident rescue scheme is scientifically judged in combination with the intelligent search algorithm and the tunnel fire smoke accident rescue scheme parameters, and personalized customization of the tunnel fire smoke accident specific rescue scheme is achieved.

The invention discloses fire smoke alarm equipment based on a satellite positioning function, and belongs to the technical field of fire smoke alarm systems. Comprising a smoke alarm and a base, and double interchangeable collecting cylinders are arranged in the smoke alarm. The first collecting cylinder is used for a high-dust environment, and 80% of coarse dust is pre-separated through a large aperture and a settling table. The second collecting cylinder is used for high-humidity environment, small aperture and chimney effect condensation prevention, and the ventilation rate is larger than or equal to 96%. A smoke channel is integrated in an inner cavity of the upper connecting disc, an annular spraying array is arranged on the outer ring of the lower connecting disc, and the integration of detection, positioning and fire extinguishing is achieved. The satellite baseband chip and the infrared maze share an antenna guiding assembly, NMEA coordinates are frozen when smoke exceeds a threshold value, the NMEA coordinates are directly sent to a platform through NB-IoT, the positioning error is smaller than or equal to 2 m, and a platform map is a second-level flash point. The drawer type smoke detection module can be disassembled quickly in 5s, double silica gel sealing and pulse water spraying hole cooling are adopted, and long-term maintenance-free under high-temperature, high-dust and high-humidity conditions is ensured.

The invention discloses a forest fire smoke particle adsorption degree prediction method, system and device and a medium, and belongs to the field of power systems, and the method comprises the steps: obtaining forest fire data of a to-be-predicted overhead transmission line under a forest fire condition in a preset time period; inputting the forest fire data into a simulation calculation model, so that the simulation calculation model constructs a simulation model corresponding to the overhead transmission line to be predicted according to the forest fire data, determining a corresponding relation between coordinate data of each smoke particle and each simulation area according to the simulation model, and calculating the number and quality of the smoke particles in each simulation area, and outputting an adsorption degree prediction result corresponding to the target simulation area, the simulation model comprising a plurality of simulation areas, and each simulation area being obtained by division according to the space field intensity of the to-be-predicted overhead transmission line, so that through implementation of the method, the adsorption degree of the smoke particles in the overhead transmission line can be accurately predicted, and the prediction accuracy of the adsorption degree of the smoke particles in the overhead transmission line is improved. And the safety of the power system is improved.

The invention relates to the technical field of warehouse environment risk monitoring, in particular to a warehouse environment risk monitoring method and system, and the method comprises the following steps: obtaining a scheduling table and current operation time of forklift drivers or inspectors in a target warehouse, collecting a task load factor of a current task type and the temperature and noise level of an operation area, and obtaining a task load factor of a current task type; and calculating to obtain a scene fatigue risk value. According to the invention, by analyzing the scheduling data and real-time task load and environmental pressure indexes of the forklift driver and the inspector, the comprehensive influence of the personnel operation state and the environmental condition on the fatigue risk is quantitatively evaluated, so that the risk evaluation basis is more comprehensive and specific, and the oneness of risk judgment is avoided; according to the method, a warehouse layout map and cargo distribution information are obtained in real time, and multi-source risk factors are associated into specific warehouse grid units in combination with readings of fire smoke and toxic gas sensors in the warehouse, so that fusion of finer space granularity and more comprehensive risk information is realized.

The invention discloses a fire smoke detection method based on an improved YOLOv8 network, and the method comprises the steps: carrying out the data preprocessing, and building a data set: building the data set through employing a fire smoke image, and enabling the data set to comprise two kinds of scene cities and forests; comprising annotation fire disasters and smog of two target categories, large targets and small targets of the fire disasters and the smog, and interference images without the fire disasters and the smog; establishing a target detection network which comprises a feature extraction network, a feature fusion network and a detection head; the feature extraction network generates a multi-scale primary feature map; the feature fusion network optimizes semantic and spatial information of the multi-scale primary feature map through cross-scale connection, and outputs an enhanced feature pyramid; the detection head executes fractional-scale dense prediction based on the pyramid, and outputs a detection result through non-maximum suppression; and sending the test set sample to a target detection network, and performing category classification and position regression on test data to obtain a final detection result.

The invention discloses a tunnel fire smoke diffusion detection method based on deep learning and image segmentation, and belongs to the technical field of fire smoke diffusion detection. The method comprises the following steps: S1, data acquisition and processing: acquiring a monitoring video in a tunnel environment by using an image acquisition module, obtaining diversified smoke image data when a fire occurs in a tunnel, and storing the obtained smoke image data in a data storage module; s2, smoke image segmentation and enhancement: utilizing an image processing module to segment and enhance the smoke image data acquired in the S1; s3, smoke recognition: after image segmentation and enhancement are completed, smoke target detection is performed on the processed image by using a YOLO v5 deep learning model based on a smoke detection module; s4, result analysis and visualization: utilizing a result analysis and visualization module to display the smoke recognition result obtained in the S3 in real time; and S5, data storage: storing a result displayed in the S4 in real time in a data storage module. Compared with the prior art, fire smoke diffusion can be accurately monitored in real time, timely control and early warning are achieved, and the influence of smoke diffusion on the tunnel environment and the external environment is reduced.

The invention relates to a UHPC-based fabricated fire-fighting smoke exhaust fan room structure and a construction method thereof, the room structure comprises a main body structure, and the main body structure is prefabricated by adopting an ultra-high performance concrete UHPC material; a fan is arranged in the internal space of the main body structure; the main body structure is provided with a machine room enclosure bulkhead cylinder body and an end cover side wall. Wherein the machine room enclosure bulkhead cylinder body is provided with a bottom plate, a first side wall and a second side wall, the first side wall and the second side wall are connected with the bottom plate and vertically arranged in parallel, and a first opening end and a second opening end which are oppositely arranged are arranged at the two ends of the machine room enclosure bulkhead cylinder body in the horizontal direction respectively; the end cover side wall is provided with a first end cover and a second end cover which are respectively arranged at the first opening end and the second opening end; the first end cover and the second end cover are each provided with a smoke suction and exhaust port, and the smoke suction and exhaust ports are used for being connected with a ventilation pipeline. The UHPC shell is adopted, the advantages of being high in strength and good in fire resistance are achieved, the prefabricated assembly type structure is adopted, construction is convenient, and efficiency is high.

The invention discloses an intelligent temperature control axial flow type fire-fighting smoke exhaust fan, and belongs to the technical field of smoke exhaust fans. Blades of an impeller of the smoke exhaust fan comprise a connecting piece, a rotating piece and a connecting shaft, two sets of symmetrical thermal deformation metal pieces are arranged between the connecting piece and the rotating piece, the characteristic that the thermal deformation metal pieces contract or extend along with the temperature is utilized, the rotating piece is driven to deform bidirectionally so as to adjust the angle of the blades, intelligent temperature control is achieved, and the air volume of the impeller can be automatically adjusted. A heat dissipation and self-cleaning integrated component is further arranged on the machine shell, the functions of oscillation of cleaning liquid, heat dissipation and self-cleaning can be achieved, the smoke exhaust fan can be self-cleaned while heat dissipation is conducted on the whole smoke exhaust fan, a large amount of dust is prevented from standing and precipitating on blades, and the heat absorption and dissipation capacity of the whole smoke exhaust fan can be enhanced. Intelligent adjustment is achieved through mechanical structure linkage, complex electric control is not needed, and the smoke exhaust efficiency, operation stability and maintenance convenience are improved.

The invention relates to an assembly type integrated fire-fighting smoke exhaust fan room structure which comprises a machine room enclosure bulkhead cylinder body which is provided with a bottom plate, a first side wall and a second side wall, the first side wall and the second side wall are connected with the bottom plate and vertically arranged in parallel, and the two ends of the machine room enclosure bulkhead cylinder body in the horizontal direction are provided with a first opening end and a second opening end which are oppositely arranged correspondingly; the end cover side wall is provided with a first end cover and a second end cover which are respectively arranged at the first opening end and the second opening end; smoke suction and exhaust ports are formed in the first end cover and the second end cover and are used for being connected with a ventilation pipeline; the machine room access door is arranged on the first side wall or the second side wall and can be opened and closed; the fan is arranged in an internal space formed by the machine room enclosure bulkhead cylinder body, the first end cover and the second end cover; the machine room enclosure bulkhead cylinder body, the first end cover, the second end cover and the machine room access door are all of a prefabricated concrete structure. The fabricated integrated design is adopted, the cost is low, the self weight is light, fireproof performance is achieved, and the advantages of being stable, reusable, attractive and the like are achieved.