71 results about "Smoke plume" patented technology

According to the spectrum-to-mass concentration imaging method and device based on physical mechanism deep learning provided by the invention, the actually measured spectrum and the reference spectrum of the pollution gas smoke plume are collected, the spectrum data set is constructed after differential processing, the meteorological data and the online mass concentration label are synchronously collected, and meanwhile, the spectrum-to-mass concentration imaging method and device based on physical mechanism deep learning are provided. A high-resolution gas absorption section is obtained and is convolved into a matrix; and constructing a deep learning model fusing a feature extraction module, an expanded least square module and a full connection module, taking the spectral data set, the meteorological data and the absorption cross section matrix as input, performing training in combination with labels to obtain an optimization model, and predicting the mass concentration of the target gas. According to the method, the problems of error accumulation, low calculation efficiency and poor interpretability caused by dependence on a complex physical model in a traditional method are solved, and high-precision, high-efficiency and interpretable real-time imaging of the mass concentration of the smoke plume of the pollution gas is realized.

The invention relates to the technical field of forest fire monitoring and power grid safety prevention and control, and discloses a fire scene spreading time sequence reconstruction method based on Doppler weather radar mountain fire echoes, which comprises the following steps: acquiring original data of the Doppler weather radar mountain fire echoes and carrying out quality control processing to obtain radar echo data; performing automatic segmentation of a smoke plume area on radar echo data by adopting an optimized Otsu-Unet network model, and extracting a centroid coordinate of a mountain fire echo area; a Kalman filtering algorithm is used and combined with external three-dimensional wind field data to predict a future motion trend of centroid coordinates of a forest fire echo region so as to reconstruct a continuous fire scene spreading time sequence voxel sequence; performing 3DTiles slicing processing on the fire scene spreading time sequence voxel sequence, and performing real-time rendering display on a power grid monitoring platform by using a WebGL technology; and obtaining an external expansion boundary of fire scene spreading based on the fire scene spreading time sequence voxel sequence, and calculating the distance between the external expansion boundary and the power transmission line GIS data in real time. The fire prevention and control capability of the power transmission line of the power grid is improved.

The invention discloses a wide-area gas traceability method and device based on multistage sensing asynchronous cooperative triggering, a medium and a product, and relates to the field of wide-area gas leakage traceability, and the method comprises the steps: carrying out the adaptive three-dimensional grid division of a to-be-detected region; environment background information is detected; smoke plume discovery is carried out by adopting a random walk strategy and introducing a weight avoidance mechanism; determining a threshold value of binary detection according to the mean value of the environment background noise, and carrying out binary calculation on the sampled data; determining a near-field region according to a binary calculation result; performing concentration tracking according to the near-field region, and performing near-field state evaluation in real time; adjusting the size of the near-field region according to an evaluation result; continuously judging whether to exit the concentration detection of the near-field region; when the concentration detection of the near-field area is quitted and switched to the far-field area, a binary detection cycle is entered; determining a concentration peak value according to the concentration detection data of all the near-field regions; according to the invention, efficient, accurate and low-cost pollution source positioning in a complex wide-area environment can be realized.

1. The name of the design product: white smoke elimination equipment (magnetic energy white elimination). 2. The use of the design product: separate the fine droplets and particulate matters in the flue gas, thereby achieving the effect of reducing the white smoke plume in flue gas emission. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view. 5. The bottom surface of the design product is the part that is not easy to see or cannot be seen during use, and the top view is omitted.

The invention relates to the technical field of toxic gas risk prediction of electrochemical energy storage boxes, in particular to an electrochemical energy storage box toxic gas risk prediction method based on multi-model fusion, which comprises the following steps: searching a preset number of similar transportation scenes in a preset weight scene library, obtaining preset optimal weights of the box-type model, the Gaussian plume model and the machine learning model in a preset number of similar transportation scenes; performing interpolation calculation based on a preset optimal weight and the similarity corresponding to the similar transportation scene to obtain target weights of the box-type model, the Gaussian smoke plume model and the machine learning model, and performing weighted summation based on the target weights to obtain target diffusion data; and obtaining a toxic gas risk prediction result of the electrochemical energy storage box at least based on the target diffusion data. Therefore, by fusing the box type model, the Gaussian plume model and the machine learning model, the accuracy and reliability of toxic gas risk prediction of the electrochemical energy storage box are improved.

The present application relates to a kind of white plume removal energy-saving control method and system, belong to the device field of handling smoke and waste gas.By control module, the real-time change of air parameter is collected, using air saturation humidity database, air temperature-enthalpy / density calculation model, establish white plume removal system operating cost mathematical model.According to the constantly changing atmospheric conditions, slagging condition etc., with operating cost as optimization goal, determine the best exhaust point, the best operation combination, using numerical analysis to seek global optimal solution, make actual operation curve quickly approach optimal curve, to adjust air cooler fan frequency, then on the basis of not affecting white plume removal effect, maximize the energy consumption of white plume removal is reduced, and make actual operating cost minimum.

This invention discloses an online assessment system, method, equipment, and medium for visual pollution and transparency of emission plumes based on image recognition. The system includes: an image acquisition module for continuously capturing images of the plume at the chimney outlet; an image preprocessing module for receiving pollutant concentration data from a continuous emission monitoring system; an intelligent assessment module for extracting visual features of the plume from the preprocessed images and outputting plume opacity level and morphodynamic characteristics; and a correlation analysis module for receiving the plume opacity level, morphodynamic characteristics, and pollutant concentration data, performing correlation analysis by calculating correlation coefficients, and determining whether emissions are abnormal based on a multivariate model. This invention achieves real-time online monitoring of emission plumes by continuously capturing images of the plume at the chimney outlet through the image acquisition module, overcoming the limitations of manual visual inspection in terms of time and space.

The application discloses a kind of wild fire smoke cluster and its boundary vector automatic identification method, system, storage medium and electronic equipment, belong to satellite remote sensing and disaster monitoring technical field.Method includes: obtaining satellite active fire point, fire event and UVAI data;Fire source area is positioned based on fire event geographic location and initial plume pixel is marked;The spatially continuous smoke cluster connected domain is identified by iterative region growing algorithm;According to the specific distribution form of connected domain pixel in satellite pixel matrix, the accurate closed boundary vector is automatically generated using matching geometric algorithm;Finally, using multiple criteria, the spatial isolated independent smoke cluster is screened out.The application avoids the defects that traditional image method is easily disturbed by environment from physical principle, realizes fully automated processing without training data, and can output vector boundary that can be directly used for diffusion and emission evaluation, significantly improves the accuracy, automation degree and application value of wild fire smoke cluster monitoring.

The invention discloses a gas leakage concentration prediction method and system based on an improved Gaussian plume model, belongs to the technical field of data processing, and aims to solve the technical problem of how to improve the accuracy and reliability of gas leakage concentration prediction. Comprising the following steps: selecting an adaptive grading calculation strategy from a multi-modal aperture adaptive leakage speed grading calculation model based on a leakage aperture, and predicting and calculating the leakage intensity of a pipeline based on the selected grading calculation strategy; an improved intelligent Gaussian plume model is constructed by introducing a logistic time growth function, a wind speed segmented intelligent compensation mechanism, diffusion coefficient lower limit constraint and concentration physical amplitude limiting, and for a gas leakage pipeline, the wind speed and the leakage intensity corresponding to the pipeline are used as input; and the diffusion concentration and the diffusion distance of the output leaked gas are predicted through the improved intelligent Gaussian plume model.

The application discloses a forest and grassland fire smoke and fire point simultaneous detection method. The method obtains visible light and infrared band images of a target area, registers and synthesizes into multi-band synthetic data; the data is input into a pre-trained multi-modal smoke and fire simultaneous detection network for feature extraction, the network adopts a feature fidelity down-sampling module containing a fixed kernel low-pass filter and average pooling during down-sampling, and is combined with a cross-layer connected background suppression and smoke and fire focusing module, a multi-scale smoke and fire shape perception module and a smoke and fire space information rearrangement amplification module for joint processing; finally, according to the feature channel set, the smoke and the fire point area are respectively located, and a fire monitoring distribution map is generated by superposition. The application realizes the simultaneous detection and mutual verification of multi-modal features of smoke and fire, effectively overcomes the loss problem of small fire points and smoke plume details, and improves the accuracy of early fire warning.

The present application relates to the technical field of image enhancement, in particular to a remote sensing image enhancement method for forest fire monitoring, which specifically comprises the following steps: firstly, pre-processing multispectral images, digital elevation models and fire point labels to obtain multi-source training samples; then, performing differentiated enhancement on different bands in combination with terrain shadow intensity, normalized burning ratio and short-wave infrared local anomaly response; then, generating a spatially restricted fire line expansion area based on wind direction, slope direction and vegetation conditions, and performing thermal radiation enhancement and smoke plume shielding modulation to obtain physically simulated augmented samples; finally, constructing a double-branch dynamic receptive field network for decoupling fire points and smoke, and jointly training the network using focal loss and boundary consistency loss, and outputting a pixel-level fire danger probability map. The present application can improve the detection accuracy of forest fires under complex terrain and the enhanced results can be directly used for fire point detection or auxiliary manual interpretation.

The utility model relates to the technical field of flue gas treatment, in particular to a wet-type electric precipitation energy-saving efficiency-increasing modified coupling waste heat recovery smoke plume deep treatment device. Comprising a reactor, and an emission reduction skid, a heat exchange skid and a circulating water skid are sequentially arranged in the reactor from top to bottom; a spraying device is arranged above the emission reduction skid; the circulating water skid is connected with the spraying device; a flue gas inlet is formed in the top of the reactor; and a flue gas outlet is formed in the reactor between the heat exchange skid and the circulating water skid. By integrating the waste heat utilization and water resource recycling technology, the functions of desulfurization, dust removal, denitration synergism, waste heat and condensate water resource recycling and smoke plume comprehensive treatment are synchronously achieved, an original high-energy-consumption and high-water-consumption environment-friendly device is upgraded to an energy-saving integrated facility, and the operation cost is converted from rigid expenditure to continuous earnings; the integrated design is adopted, and the comprehensive advantages of being small in occupied space, low in investment cost, small in operation energy consumption and high in energy-saving benefit are achieved.

Title of the invention: Chimney for plume reduction in a CO2 capture installation. A chimney for venting gas from a CO2 capture installation comprises an elongated hollow body open upwards to the atmosphere and means for bringing the NO2-containing gas into the elongated hollow body, the body comprising means for diluting the gas by mixing it with atmospheric air. No figure

The utility model relates to the technical field of thermal boiler production, and discloses a thermal gas-fired boiler regular-discharge steam recovery device which comprises a boiler regular-discharge flash tank. The air outlet pipe is communicated with the top of the boiler periodic blowdown flash tank, a heat exchanger is installed at the top end of the air outlet pipe, an exhaust pipe is arranged above the heat exchanger, and an extension pipe is communicated between the heat exchanger and the exhaust pipe; according to the utility model, the heat exchanger is additionally arranged at the exhaust port of the existing boiler periodic blowdown flash tank and is matched with the recycling mechanism for use, so that the waste heat of boiler blowdown dead steam is effectively recycled, the energy utilization efficiency is improved, the operation cost is reduced, and the dead steam is condensed in the heat exchanger to form high-quality condensed water; and the preheated demineralized water enters the deaerator, so that the steam demand is reduced, the deaerator operates more stably, the phenomenon of white smoke plume caused by direct discharge of dead steam can be eliminated, and the factory environment is improved.

The utility model discloses a flue gas water heat recovery and flue gas white smoke elimination device for a power plant. A centrifugal fan communicates with outside air; the flue gas heater is provided with a flue gas inlet and a flue gas outlet, and the flue gas inlet is communicated with the centrifugal fan; the steam generator is provided with a steam outlet, and the steam outlet is communicated with the flue gas outlet of the flue gas heater through the mixer; the heat exchanger is provided with a gas inlet, a gas outlet, a water inlet, a water outlet and a liquid outlet; the gas inlet is respectively communicated with the flue gas outlet and the steam outlet through the mixer; the circulating water tank is respectively communicated with the water inlet and the water outlet; and the condensation water tank is communicated with the liquid outlet. According to the device, the centrifugal fan and the flue gas heater simulate a power plant to provide high-temperature flue gas, the high-temperature flue gas is humidified through the steam generator and the mixer to form saturated wet flue gas, the saturated wet flue gas is subjected to heat exchange through the heat exchanger, and the saturated wet flue gas is dehumidified and cooled through cooling water, so that water in the flue gas is recycled; meanwhile, white smoke plume is eliminated.

The application provides a method for automatically identifying smoke plumes of global large point sources based on satellite data, which is based on the column concentration data retrieved by high-resolution satellite remote sensing, selects the region around the global large point source as the research region, and obtains the local concentration enhancement data by deducting the background concentration from the original column concentration. The best global segmentation threshold in the research region is obtained, and the median of the foreground pixels is further taken as the final threshold. The pixels greater than the final threshold in the concentration enhancement image are recorded as the final pixel group, and the information of the final pixel group is traversed to screen out the initial screening plume pixels that meet the conditions, so as to screen out the plume pixels that meet the conditions. The retrieved global large point source emission plume is artificially identified, and the false positive plume is removed, so that the global large point source pollution gas emission smoke plume is finally obtained. The application can automatically identify the emission plume of the preset global emission point source during satellite observation.

The invention discloses a zero-energy-consumption white smoke removal method and device for a primary flue gas diffusion chimney of a converter. The white smoke removal device comprises a converter primary flue gas diffusion chimney, a flue gas inlet pipeline, a water baffle, a segmented drainage system, a folded plate demister, a throat spiral fin cooler, a swirler, a water collector, an upper spiral fin cooler, an ignition device and a chimney sealing plate. Flue gas is sequentially subjected to pre-dehydration, primary white smoke removal, intensified cooling, sufficient cooling and secondary white smoke removal and then is discharged into the atmosphere, water vapor in the flue gas is sufficiently condensed and removed in a segmented mode, white smoke plume and various pollutants at an outlet of a diffusion chimney can be effectively reduced, meanwhile, consumption of external energy is not increased in the whole process, and the device is low in initial investment and low in cost. The method has good economical efficiency and is widely suitable for newly-built and reformed projects.

The invention discloses a methane smoke plume recognition and emission estimation method based on multi-constraint background selection, and belongs to the technical field of greenhouse gas remote sensing monitoring and hyperspectral inversion. According to the method, satellite-borne or airborne short-wave infrared hyperspectral observation data is subjected to preprocessing such as radiometric calibration, atmospheric correction and noise suppression, a multi-constraint background pixel screening model including same-column consistency constraint, spectrum slope consistency constraint and diffusion distance constraint is constructed, and a background spectrum library is automatically obtained; based on the background library, an enhanced matched filtering algorithm is adopted to extract the methane concentration enhancement amount, and the system deviation and the false alarm rate are remarkably reduced. A smoke plume area is accurately extracted through spatial filtering, morphological segmentation and connected domain analysis, and the methane emission flux is inverted by combining an integrated quality enhancement (IME) emission estimation model with meteorological wind field data.

The application provides a method and system for evaluating the whole range of radiation risk outside a nuclear power plant in a severe accident, and the method comprises the following steps: S1, a basic model architecture for evaluating the risk of radioactive accidents is built, the model requirements are adapted, and a corresponding basic database is established; S2, the characteristics of the radioactive plume after the accident are constructed; S3, the spatial gridding of the accident site and the discretization of the plume transmission are calculated; S4, the sampling meteorological conditions are obtained, and the plume transmission is simulated; S5, the radiation dose in the early stage of the grid domain is calculated, and the risk is evaluated; S6, the health effects in the early stage of the grid domain are evaluated; S7, the radiation dose in the medium and long term stage of the grid domain is calculated, and the dose risk is evaluated; S8, the health effect risk in the medium and long term stage is evaluated, and the consequences of the accident in the medium and long term stage are evaluated. The application simulates the whole transport process of the radioactive plume in a severe accident, considers the dry and wet deposition of the plume and the loss effects such as radioactive decay, and determines the activity of the radionuclide deposited on the ground and retained in the air within the spatial range outside the scene.

The invention discloses a high-emission ship screening method based on a spectral remote sensing technology, and the method comprises the steps: carrying out the multi-azimuth angle and multi-elevation angle observation of ship plume based on shore-based spectral remote sensing equipment, and carrying out the inversion to obtain the optical path integral concentration of SO2 and NO2 at different positions of smoke plume, the mass concentration result of SO2 and NO2 in the plume and the ratio RSN of SO2 and NO2 are obtained through background concentration deduction and in combination with optical path information; the method comprises the following steps: pre-processing RSN data and ship characteristic data, then performing data grouping, performing statistics on the RSN data in each group, determining a calculation key percentile, taking the calculation key percentile as an RSN upper limit of compliant emission to calculate a fuel oil sulfur content calculation factor corresponding to the group, and sorting fuel oil sulfur content calculation factor results subjected to grouping calculation into a structured table to form a lookup table. Based on the lookup table scheme, the fuel sulfur content of the newly observed ship is further calculated, whether the ship meets the standard or not is judged, early warning information is sent out for the high-emission ship, and ship supervision is assisted. The method is used for solving the problem of high-emission ship screening.

The invention provides a smoke exhaust flow guide cone for a thermal power plant chimney, and relates to the field of thermal power plant chimneys, the smoke exhaust flow guide cone comprises a conical flow guide cylinder, a mounting rod is arranged in the flow guide cylinder, a plurality of flow guide groups are arranged on the circumferential side of the mounting rod at equal intervals, a rotating assembly is arranged above the mounting rod, and a collecting assembly is arranged outside the flow guide cylinder. An adjusting assembly is arranged at the bottom end of the collecting assembly, and the flow guide assembly comprises a plurality of flow guide adsorption assemblies which are arranged on the circumferential side of the mounting rod at equal intervals. By means of the arranged flow guide adsorption assembly, flue gas exhausted by the chimney is heated through the flow guide adsorption assembly, after the flue gas is heated, water vapor is rapidly evaporated along with temperature rising, the white smoke plume phenomenon is prevented, meanwhile, carbon dioxide and part of harmful substances in the flue gas can be adsorbed, and the environment is protected. The content of water vapor and carbon dioxide in flue gas can be effectively reduced, the white smoke plume phenomenon is prevented, the carbon emission of a thermal power plant is reduced, and green and environment-friendly effects are achieved.

The invention discloses an efficient low-consumption white smoke removal device and method for a converter primary flue gas diffusion chimney. The white smoke removal device comprises the converter primary flue gas diffusion chimney, a flue gas inlet pipeline, a water baffle, a segmented drainage system, a cyclone dehydrator, a throat spiral fin cooler, a cyclone, a water collector, an upper spiral fin cooler and an ignition device. Flue gas is sequentially subjected to pre-dehydration, efficient cooling and white smoke removal, reinforced cooling and extreme cooling and white smoke removal and then is discharged into the atmosphere, water vapor in the flue gas is fully condensed and removed in a segmented mode, the moisture content of the flue gas is extremely reduced, white smoke plume and various pollutants at an outlet of a diffusion chimney can be efficiently reduced, and ultra-low emission can be achieved. The device is low in operation energy consumption, good in white smoke removal effect, high in cost performance, suitable for newly-built and reformed projects, and particularly suitable for the situation that the water content of smoke is high.

The application provides a method for evaluating radioactivity in a limited space based on a plume diffusion mode, which is mainly used for evaluating radioactivity concentration distribution in the limited space, and the method comprises the following steps: equivalent processing of a radioactivity diffusion process, regarding the radioactivity diffusion process as a plume bundle composed of a plurality of smoke clusters, and obtaining the radioactivity concentration distribution through a Gaussian smoke cluster diffusion model; improving a traditional Gaussian smoke cluster model by considering radioactivity source intensity variation, gravity settlement and environmental wind speed, considering the variation of the radioactivity intensity of the smoke cluster according to radioactivity decay, considering the offset amount of the gravity settlement to the center line of the plume according to Stokes formula, and synthesizing and superimposing diffusion speed according to the parallelogram rule to combine the environmental wind speed and the radioactivity self-diffusion speed; and superimposing the radioactivity concentrations of all the smoke clusters according to the improved smoke cluster model to evaluate the radioactivity concentration in the limited space.

The present application proposes a method for judging the plume type in advance and defining the tracking range of the pollution source of the unmanned aerial vehicle, which is used for gas leakage source positioning. The accuracy of the judgment is improved by calculating atmospheric stability, calculating plume expansion rate and calculating plume boundary slope. By determining the plume type, the boundary position of the plume is inferred, and the search range of the pollution source tracking is defined based on this, so that the unmanned aerial vehicle can reduce unnecessary space search when tracking, and improve the efficiency of pollution source tracking and positioning. Computer simulation verifies that the method can effectively improve the efficiency of pollution source tracking and positioning.

This application discloses an AI-based flue gas emission monitoring method and system, relating to the field of flue gas emission monitoring. It dynamically corrects the color and analyzes the physical characteristics of real-time flue gas videos, constructing a physical prediction baseline based on a Gaussian plume model in parallel. Based on this, an AI model driven by the macroscopic visual features of the plume is introduced. Visual feature vectors extracted by a deep network are used as key correction factors to dynamically compensate and finely refine the baseline concentration profile generated by the physical model, ultimately driving the generation of a high-precision pollutant concentration profile. In this way, by organically combining the universality of physical laws with the powerful learning capabilities of artificial intelligence, remote, non-contact, high-precision quantitative monitoring of flue gas emissions can be achieved, significantly improving the accuracy and robustness of visual monitoring solutions in quantitative pollutant concentration inversion in real industrial scenarios.

The invention relates to the technical field of intelligent fire control, in particular to an industrial enterprise-oriented emergency fire control event identification method and system, and provides the following scheme: collecting field sensing data through a visible light, thermal infrared and gas spectrum multi-mode sensing module; brightness change, temperature gradient and spectral line intensity features are extracted under a unified space-time reference framework, a multi-modal feature map is constructed, and a fire suspected area is extracted; and for the suspected region, constructing a thermal plume flow field model based on a thermal convection and smoke plume dynamics mechanism, generating a multi-modal prediction trajectory under a real fire assumption, carrying out space and time registration on the prediction trajectory and actual observation data, and calculating a cross-modal consistency score to judge the authenticity of the fire. According to the method, multi-source physical information can be fused, anti-fact disambiguation of pseudo-fire behaviors such as welding spots, steam and hot exhaust can be realized, and the accuracy and response timeliness of fire behavior identification in a complex industrial environment can be remarkably improved.

This utility model relates to a steam white plume elimination device, including a pipe, a cooler and a reheater installed inside the pipe, the cooler being located below the reheater, a flue pipe being detachably connected to the top of the pipe, a flue pipe cover with a filter screen being fixedly installed on the top of the flue pipe, a rotating nozzle for cleaning the filter screen being installed inside the flue pipe, a funnel plate for collecting water being installed on the lower inner side of the flue pipe, and a drain port being opened above the connection between the funnel plate and the flue pipe; this utility model has the advantage of ensuring overall operational performance.

This invention discloses a high-precision emission flux quantification method for plume velocity inversion, verification, and fusion imaging. The method includes: in plume velocity inversion measurement using the improved Farneback dense optical flow method, a clustering algorithm is used to extract plume features from the image and screen the main plume components; image texture intensity is calculated based on the main plume components, and the corresponding optical flow parameters are determined; forward optical flow is calculated based on the optical flow parameters; a consistency error field based on bidirectional optical flow is introduced, and time consistency correction is performed on the forward optical flow based on the consistency error field; the fusion weight factor is determined based on the gradient of the calculated forward optical flow; and the velocity is calculated after weighted total variation denoising of the forward optical flow to obtain the plume velocity inversion result; the plume velocity inversion result is verified; and the plume velocity inversion result is combined with hyperspectral remote sensing imaging to achieve high-precision emission flux quantification, thus improving the accuracy of emission flux calculation for organized industrial emissions.

This invention relates to the field of multimodal fire identification technology, specifically to a multimodal graded fire early warning and identification system and method for use in hot work spaces. The system includes a flame boundary extraction module, an edge behavior layering module, a flame fluctuation construction module, a disturbance ratio extraction module, and a grade identification module. In this invention, the trajectory is obtained by performing point-by-point comparison of pixel brightness changes in continuous images, and then the occurrence frequency of the multi-frame position offset trajectory is divided and eliminated, so that the flame outline can be preserved in a stable structural form in the oil fume disturbance environment. The flame cycle chain is obtained by judging the time sequence of the brightness peak occurrence time, and the disturbance structure is obtained by comparing the magnitude of the data changes in brightness jump, smoke plume diffusion speed and temperature increase. This enables the grade identification to maintain continuous expression under different fire source forms and interference conditions, solving the problems of boundary confusion, single trigger and grade offset in the prior art.

The invention discloses a wildfire puff and boundary vector automatic identification method and system thereof, a storage medium and electronic equipment, and belongs to the technical field of satellite remote sensing and disaster monitoring. The method comprises the following steps: acquiring satellite active fire points, fire events and UVAI data; positioning a fire source area based on the geographic position of the fire event and marking an initial smoke plume pixel; identifying a smoke puff connected domain with continuous space through an iterative region growing algorithm; automatically generating an accurate closed boundary vector by adopting a matched geometric algorithm according to the specific distribution pattern of the connected domain pixels in the satellite pixel matrix; and finally, screening out the independent puff with isolated space by utilizing multiple criteria. According to the method, the defect that a traditional image method is easily interfered by the environment is avoided from the physical principle, full-automatic processing without training data is achieved, the vector boundary which can be directly used for diffusion and emission evaluation can be output, and the accuracy, the automation degree and the application value of wildfire puff monitoring are remarkably improved.