61 results about "Air pollutant concentrations" patented technology

The invention discloses an air pollutant concentration prediction method and related equipment thereof, and relates to the technical field of data processing. The method comprises the following steps: acquiring current pollutant concentration data, current meteorological data and target site geographic position data corresponding to a target environment monitoring site; taking the current pollutant concentration data, the current meteorological data and the geographic position data of the target station as target input data of the prediction model; wherein an input module of the prediction model is used for performing modal decomposition processing on input data to obtain multiple pieces of modal data; the time feature extraction module is used for extracting time feature data; the spatial feature extraction module is used for extracting spatial feature data; the space-time fusion convolutional network module is used for extracting space-time features; the output module is used for outputting a prediction result; determining a prediction result of the air pollutant concentration corresponding to the target environment monitoring station according to the output result; the method achieves the effects of improving the comprehensiveness and accuracy of a prediction result and expanding application scenes.

The invention discloses an urban low-altitude dynamic wind field and air quality refined forecasting method and system in the technical field of environmental weather forecasting, and the method comprises the steps: generating a static sub-urban scale low-altitude wind field map under different weather background wind directions, and carrying out the correction, thereby obtaining a static sub-urban scale low-altitude non-uniform wind field map; generating a sub-city scale low-altitude horizontal wind field dynamic map based on the moment-by-moment time sequence data of the background wind speed and direction and the static sub-city scale low-altitude non-uniform wind field map; calculating a horizontal transmission track and a propulsion dynamic state of the target atmospheric pollutants in the urban low altitude in the dynamic wind field to obtain an external background transmission concentration of the target city; calculating the concentration of atmospheric pollutants formed by local emission in the dynamic wind field; and calculating a high-temporal-spatial-resolution forecasting result of the urban low-altitude atmospheric pollutant concentration. The method can be used for diagnosis, prediction and early warning of ventilation galleries and atmospheric pollutant diffusion and transmission channels in the urban low-altitude environment.

The invention discloses an air quality index prediction method based on CNN-GRU, and belongs to the technical field of environment monitoring and air quality prediction. The method comprises the following steps: (1) acquiring historical air pollutant concentration data and meteorological data to form a data set; (2) preprocessing the data set, and dividing the preprocessed data set into a training set and a test set; (3) constructing a parallel CNN-GRU double-branch architecture; (4) performing model training and optimization on the parallel CNN-GRU double-branch architecture based on the training set; (5) operating the optimal parallel CNN-GRU double-branch architecture based on the test set, and outputting a pollutant concentration prediction basic value; and (6) carrying out reverse normalization on the predicted basic value of the pollutant concentration, reducing the predicted basic value of the pollutant concentration into an actual concentration unit to obtain the pollutant concentration, calculating a subindex IAQI of the pollutant concentration, and taking a maximum value as a final AQI. According to the method, the parallel double-branch architecture is constructed, so that the parameter quantity is reduced, the prediction speed is increased, and the prediction result accuracy is improved.

The invention discloses an air quality forecasting method fusing monitoring image data. The method comprises the following steps: constructing an LSTM single-channel deep learning network for feature extraction of historical air quality data, meteorological data and time data; a CNN-LSTM single-channel deep learning network used for monitoring image feature extraction is constructed; integrating two single-channel networks, and constructing a dual-channel integrated deep learning model for air quality forecasting; the method comprises the following steps: collecting multi-source data such as monitoring images, air quality and weather, and constructing an air quality multi-source data set; generating a sequence sample for the constructed air quality multi-source data set by using a sliding window method and a'T1: T2 'mode; training the dual-channel integrated deep learning model by using the sequence sample training set to obtain a multi-step multivariable output regression model with forecasting capability; and inputting to-be-detected sequence sample data into the regression model, and outputting a plurality of air quality index forecast results at a plurality of moments in the future. According to the method, the two single-channel neural networks are combined, a relation model among the air pollutant concentration, the monitoring image, the weather and the time is constructed, time sequence forecasting of the air quality is achieved, outdoor monitoring image data are fused, and the forecasting precision of the air quality is improved.

According to one embodiment, a method, computer system, and computer program product for dynamic image reconstruction is provided. The present invention may include training a physics-informed neural network (PINN) using received training data; receiving wind field velocity measurements in a geographical domain from one or more weather information sources and air pollutant concentration measurements of one or more air pollutants from the geographical domain using a sparse sensor network to produce a plurality of input data; processing the plurality of input data through multiple physics-informed masked convolutional layers in the trained PINN to perform a three-dimensional partial convolution process; and performing the dynamic image reconstruction on the processed plurality of input data using the trained PINN to generate a reconstructed continuous spatial map of the geographical domain.

The invention provides a traffic flow prediction method fusing air pollution factors, and the method comprises the steps: obtaining a traffic topological structure, historical traffic flow and air pollutant concentration data, constructing a traffic feature matrix, an adjacent matrix, a related pollutant concentration attribute matrix, and a mapping function, the air pollutant concentration data are fused through an attribute enhancement unit; adopting K-means clustering to screen pollutants with the highest correlation with the traffic flow, and utilizing an attribute enhancement unit to integrate the pollutants into traffic flow features; and building and training a deep learning model for traffic flow prediction. According to the method, by combining the relevance between the spatial-temporal characteristics of the traffic flow and the air pollutants, the limitation that an existing method only depends on traffic flow data is overcome, and the prediction accuracy is effectively improved.

The invention relates to a GAI-BRI-based air pollutant concentration interpolation prediction method and device and a medium, and the method comprises the steps: carrying out the interpolation prediction of the concentration of air pollutants according to the extracted air pollutant concentration, meteorological data and satellite data of a plurality of distribution sites in a given region within a given time range; constructing an air pollutant concentration diagram for describing pollutant conditions in a given time range and a given area range; inputting the numerical value of the air pollutant concentration diagram into a GAT-BRI prediction model to obtain an air pollutant concentration interpolation prediction result in a period of time in the future; wherein the GAT-BRI prediction model comprises a graph attention network GAT which is arranged at a bottom layer and is used for extracting spatial features from an air pollutant concentration graph, and a bidirectional cyclic interpolation network BRI which is arranged at a middle layer and is used for extracting time sequence features from the spatial features output by the graph attention network; and the feed-forward network is arranged at a high layer and is used for outputting an interpolation prediction result. Compared with the prior art, the method has the advantages that the spatial dependence and time dependence relationship among multiple cities can be fully mined, and the prediction accuracy is high.

The invention discloses an underground powerhouse cavern group air pollutant concentration prediction method based on an improved space-time diagram convolutional network, and belongs to the technical field of air pollutant concentration prediction. Comprising the steps of obtaining initial monitoring data; acquiring a sensor arrangement diagram, constructing a normalized self-loop adjacent matrix, and describing PM2.5 interaction difficulty between monitoring stations by using a simplified diffusion distance; constructing a multi-scale spatio-temporal feature fusion model, and fusing PM2.5 concentration spatio-temporal information under different scales; and constructing a space-time diagram convolutional neural network, taking the output result of the self-loop adjacent matrix and the multi-scale space-time feature fusion model as the input of the space-time diagram convolutional neural network, splicing and outputting by adopting a multi-space-time block output fusion method, then accessing the multi-head self-attention model, and outputting a prediction result. According to the method, different information embedded in the time data under different scales can be considered, so that the model can learn the correlation between different sequences on each scale, and the prediction accuracy and generalization ability are improved.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention provides an air purification method and device based on big data, electronic equipment and a storage medium, and relates to the technical field of data processing. The air purification method based on the big data comprises the steps that indoor air data detected by a plurality of air purifiers and environment sensing data detected by a plurality of associated sensors are obtained, and the actual air quality change trend is determined according to the indoor air data and the environment sensing data; according to the actual air quality change trend, the initial air pollutant concentration, the highest pollutant concentration and the air quality change attribute are determined, and the overall air quality in the current environment is determined according to the initial air pollutant concentration, the highest pollutant concentration and the air quality change attribute; according to the actual air quality change trend, the indoor air data and the environment sensing data, a pollution source and a corresponding pollution source type are determined; and according to the air influence data, the overall air quality, the pollution source and the pollution source type in the preset distance range, a target purification mode is determined.

The utility model relates to the technical field of environmental air pollutant concentration monitoring, and provides a peroxy radical chemical amplification device which comprises a sampling-amplification channel, a first acquisition control circuit module is arranged in the sampling-amplification channel and used for controlling an electric control program of a device system, and a second acquisition control circuit module is arranged in the sampling-amplification channel. An HO photolysis module is arranged in the sampling-amplification channel, a second acquisition control circuit module is arranged in the sampling-amplification channel and used for controlling an electric control program of the device system, and a gas path module is arranged in the sampling-amplification channel and used for controlling the gas flow direction of the device system; according to the utility model, the sampling-amplifying channel is arranged, so that the device is simple in structure, simple to operate, low in manufacturing cost and high in time resolution; the inhibition effect of the environment humidity on the amplification reaction is solved to a certain extent, and the actual effects of accurate measurement, simple operation and stable operation are obtained.

The invention discloses a multi-stage waste gas purification device, and belongs to the technical field of waste gas purification, the multi-stage waste gas purification device comprises a spray tower, a gas inlet pipe and a gas outlet pipe, one side of the spray tower is provided with a liquid storage cavity, a variable speed water pump is arranged between the liquid storage cavity and the spray tower, a gas quality sensor is arranged in the gas inlet pipe, and a gas outlet pipe is arranged in the gas outlet pipe. The bottom end of the spraying frame is rotationally connected with a spraying main pipe, a hydraulic driving mechanism for driving the spraying main pipe to rotate is arranged on the spraying frame, the output end of the variable-speed water pump is communicated with the hydraulic driving mechanism, and the spraying main pipe is provided with multiple layers of spraying mechanisms communicated with the spraying main pipe from top to bottom; an adjusting piston is arranged in the spraying main pipe in a sliding and sealing manner, and a centrifugal self-adjusting driving mechanism for driving the adjusting piston to slide along the spraying main pipe is arranged at the bottom end of the spraying main pipe. The multi-stage waste gas purification device provided by the invention can be used for monitoring the concentration of air pollutants and is provided with a plurality of layers of spraying mechanisms, and the spraying liquid flow and the spraying layers are automatically adjusted according to the concentration of the waste gas pollutants.

The invention discloses an urban pollutant distribution prediction method based on multi-source data dynamic and static feature fusion, and the method comprises the following steps: S1, collecting multi-source heterogeneous data in a research region, and constructing a multi-source heterogeneous data set; s2, preprocessing the collected multi-source heterogeneous data; s3, processing the remote sensing image blocks, the population density information and the altitude information by using a block feature extraction module to obtain regional long-term static features; s4, processing a part of stations around the calculation target site by using an air data reference module, and obtaining air reference dynamic characteristics of pollutant distribution from surrounding air monitoring stations; s5, performing feature fusion on the block long-term static features and the air reference dynamic features of the to-be-predicted target, and calculating and predicting the air pollutant concentration of the target; s6, optimizing the model to optimal parameters; according to the method, multi-source public data easy to collect is used, dynamic and static characteristics are fused, and air pollutant concentration distribution prediction in an area without a monitoring station is effectively achieved.

The invention relates to the technical field of data processing, and particularly discloses a data processing method for an intelligent environmental protection monitoring platform, which utilizes a gas sensor to monitor the concentration of air pollutants in real time, and introduces historical normal pollutant concentration data corresponding to the current monitoring time period as a dynamic reference system. Therefore, a dynamically changing judgment threshold value is constructed based on statistical characteristics, normal periodic pollutant concentration fluctuation is effectively filtered out, and an abnormal air pollutant concentration peak value different from a normal background is identified. Further, deep time sequence correlation analysis is carried out on pollutant concentration data and real-time meteorological data in a corresponding time period, so that the cause of an abnormal peak value of the pollutant concentration is comprehensively judged. According to the method, the pollutant concentration standard exceeding event can be accurately identified, and the causes behind the pollutant concentration standard exceeding event, such as sensor instantaneous errors, pollutant accumulation in static and stable weather or sudden pollution events, are disclosed, so that powerful support is provided for a subsequent differential management and control strategy.

The invention relates to an emergency processing system and method for atmospheric pollution source influence based on DeepSeek, and belongs to the technical field of environmental monitoring, and the method comprises the steps: collecting atmospheric pollutant concentration data, meteorological data and basic information data of surrounding buildings; preprocessing the data; carrying out deep analysis on the preprocessed data based on a DeepSeek model, and judging whether to trigger early warning or not and the early warning degree in combination with a pollutant exceeding standard knowledge base; when abnormal data is found, the constructed knowledge base is retrieved; combining the data retrieved by the knowledge base; the current atmospheric pollution and building influence conditions are retrieved and compared with existing plan cases; and a detailed alarm condition is output, and a targeted emergency plan is generated at the same time. According to the method, based on the DeepSeek data analysis and learning ability, the influence of multiple factors is fully considered, the position of the influenced building is accurately identified, the influence degree is evaluated, and a more reliable basis is provided for environment decision making.

The invention discloses an air pollutant concentration dynamic hourly prediction method based on a machine learning model, and the method comprises the steps: a, extracting historical data, report starting data and prediction data: the historical data comprises meteorological mode historical hour data and air pollutant concentration historical hour data in N months before the report starting time of a certain year, a certain month and a certain day in a certain region, the report starting data comprises air pollutant concentration data at a report starting moment, the prediction data comprises meteorological mode prediction hour data at x moments after the report starting moment, N is greater than or equal to 6, and x is greater than or equal to 2; b, processing the historical data and the prediction data; c, determining the trained machine learning model as an air pollutant concentration prediction model; and d, inputting meteorological mode prediction hour data at x moments after the report starting moment into the air pollutant concentration prediction model to obtain dynamic hourly prediction data of the air pollutant concentration. According to the method, air pollutant emission source data is not needed, the used meteorological factors are comprehensive and reasonable, the prediction precision is high, and dynamic hourly prediction is realized.

The invention discloses an urban public space optimization method based on crowd behavior simulation. The method comprises the following steps: acquiring urban wind field parameters, urban air pollutant concentration data and geometrical characteristics of buildings; calculating a turbulence diffusion coefficient by adopting a computational fluid dynamics simulation method; acquiring real-time meteorological data according to the real-time meteorological data API to calculate atmospheric stability; determining concentration distribution of pollutants at different time and spatial positions by adopting a pollutant Lagrange particle tracking method; constructing a crowd behavior pattern classification model, and determining crowd behavior patterns in different public spaces; determining an optimal green belt and ventilation corridor configuration and an optimal public space ventilation optimization scheme; and the influence of different configurations on the ventilation effect and pollution inhibition is evaluated. According to the method, a more accurate and more efficient optimization scheme is provided for urban public space design by integrating multi-dimensional factors such as meteorology, building distribution, crowd behaviors and air flow, and the living quality of citizens and the comfort level of the public space are remarkably improved.

The invention relates to the technical field of atmosphere quality monitoring, and discloses an underway atmosphere quality monitoring method and system, and the method comprises the steps: constructing a vehicle-mounted underway atmosphere quality monitoring system based on a front-end sensor assembly, a data collection module, a wireless transmission unit, a positioning system and a power supply system, and generating an underway monitoring execution scheme; driving the vehicle to collect atmospheric pollutant concentration and meteorological parameter data; performing timestamp matching and fusion processing with the original GPS position data to obtain atmospheric pollutant spatial distribution data; transmitting to an environment monitoring cloud platform in real time, and generating an atmospheric pollutant concentration distribution thermodynamic diagram; and performing air quality grading evaluation and pollution source identification on the monitored area, and generating an area air quality risk grade map and pollution early warning information, thereby realizing stable acquisition of environmental parameters in the mobile monitoring process, effectively eliminating interference of vehicle vibration and environmental change on monitoring data, and improving the monitoring accuracy. And the accuracy of atmosphere quality monitoring is improved.

The invention belongs to the technical field of air pollution assessment, and relates to an urban air pollutant change amplitude assessment and ranking method and system, and the method comprises the steps: 1) obtaining the concentrations of a plurality of air pollutants of a plurality of cities in different time dimensions, and carrying out the standardization processing of the concentrations; 2) performing multi-dimensional time sequence analysis on the air pollutant concentration to obtain a multi-dimensional time sequence analysis result; 3) calculating a comprehensive score of each city according to the air pollutant concentration and the multi-dimensional time sequence analysis result; 4) calculating a dynamic evaluation score of each city and dynamically ranking the plurality of cities according to the dynamic evaluation scores; and 5) evaluating the change amplitude of the pollutant concentration of each city, and evaluating the plurality of cities according to the multi-dimensional time sequence analysis result and the change amplitude to obtain the risk level of each city. Evaluation is carried out based on the multi-dimensional time sequence analysis result and the dynamic weight, and the evaluation result is comprehensive and accurate.

The present invention provides an indoor environment adaptive adjustment system based on the Internet of Things, which relates to the field of Internet of Things technology and includes: a data acquisition module for dividing the indoor space into three functional areas, and deploying a multi-parameter sensor group in each functional area through the Internet of Things network to collect raw environmental data in real time, including temperature, relative humidity, and air pollutant concentration data; a spatial heterogeneity analysis module for calculating the difference between the maximum and minimum values ​​of the same environmental parameter in each functional area as the regional range. When the regional range of any parameter exceeds a set threshold, a spatial heterogeneity correction factor K is generated, where the K value is proportional to the maximum regional range. The present invention realizes adaptive adjustment of the indoor environment through precise perception of zoning, dynamic correction, multi-parameter fusion evaluation, equipment collaborative control, and continuous optimization, effectively improving comfort, ensuring air quality, and reducing energy consumption.

The invention discloses an air exposure evaluation system and an evaluation method thereof, and relates to the field of pollutant exposure evaluation, the system comprises a respiratory rate monitor, an air pollutant detector and an intelligent terminal; the respiratory rate monitor is used for monitoring the respiratory rate of the to-be-researched object in real time; the air pollutant detector is used for detecting the concentration of air pollutants in real time; the intelligent terminal is connected with the respiratory rate monitor and the air pollutant detector and used for obtaining the air pollutant exposure concentration corresponding to the respiratory rate data according to the respiratory rate data and the air pollutant concentration data and displaying the air pollutant exposure concentration. According to the invention, the accuracy of evaluating the air pollutant exposure level of the environment where the to-be-researched object is located can be improved.

The embodiment of the invention provides an environment data processing method, device and equipment. The method comprises the following steps: acquiring a plurality of environment data packets of each preset grid of a target area in a target time period; wherein each environment data packet comprises at least one kind of air pollutant concentration data collected by the vehicle; for each preset grid, determining initial environment data of the preset grid in the target time period according to the air pollutant concentration data in the environment data packet of the preset grid in the target time period; acquiring environment monitoring data of an environment monitoring station to which the preset grid belongs in a target time period; based on the environment monitoring data of the target time period, performing correction processing on the initial environment data of the preset grid in the target time period to obtain target environment data of the preset grid in the target time period; and determining an environment pollution area of the target area according to the target environment data of each preset grid in the target time period. The method is used for achieving the effect of improving the accuracy of the environmental data.

The present invention relates to the technical field of air detection, and particularly relates to an air pollutant concentration detection device, which includes a housing. The housing includes an upper housing and a lower housing. A circuit board is provided between the upper housing and the lower housing. A laser detection component is provided on the lower surface of the circuit board. An "M"-shaped channel is arranged inside the lower housing. The "M"-shaped channel includes a "U"-shaped part and a "|"-shaped part. Pressure-receiving parts are provided at the corners of the "U"-shaped part. The pressure-receiving parts detect the air flow pressure flowing through the "U"-shaped part. A piezoelectric air supply component is arranged outside the "U"-shaped part, and a cross-section regulation component is arranged inside the "U"-shaped part; by setting the piezoelectric air supply component and the cross-section regulation component, when the piezoelectric air supply component provides power to the cross-section regulation component, the cross-section regulation component generates deformations in different directions to adjust the cross-sectional area of the "M"-shaped channel, so as to clean the dust adhering in the "U"-shaped part and ensure the accuracy of the detection by the laser detection component.

The invention provides an atmospheric pollution monitoring method and device, and belongs to the technical field of atmospheric monitoring, and the method comprises the steps: processing atmospheric pollutant concentration data based on a principal component analysis algorithm, and obtaining target pollutant concentration data; analyzing the target pollutant concentration data based on a wavelet decomposition algorithm, and determining time characteristics of the target pollutant concentration data; determining spatial features of the target pollutant concentration data based on a Gaussian diffusion model; wherein the time characteristic of the target pollutant concentration data and the spatial characteristic of the target pollutant concentration data are monitoring results of atmospheric pollution. According to the atmospheric pollution monitoring method and device provided by the invention, the accuracy and reliability of atmospheric pollution monitoring can be improved.

The present invention discloses a method for predicting air pollutant concentration and related equipment, which relates to the technical field of data processing. The method includes: obtaining the current pollutant concentration data, current meteorological data, and target site geographical location data corresponding to a target environmental monitoring site; using the current pollutant concentration data, current meteorological data, and geographical location data of the target site as target input data for a prediction model. Among them, the input module of the prediction model is used to perform modal decomposition processing on the input data to obtain multiple modal data; the time feature extraction module is used to extract time feature data; the spatial feature extraction module is used to extract spatial feature data; the convolutional network module for spatio-temporal fusion is used to extract spatio-temporal features; the output module is used to output a prediction result; and determining the prediction result of the air pollutant concentration corresponding to the target environmental monitoring site according to the output result. It realizes the effects of improving the comprehensiveness and accuracy of the prediction result and expanding the applicable scenarios.

The embodiment of the invention provides an air pollutant concentration three-dimensional modeling method, and belongs to the technical field of data processing, and the method specifically comprises the steps: setting a cruise region, and dividing the cruise region into initial grids; setting a global cruise path strategy and a local cruise path strategy; all the initial grids are traversed, and the pollutant concentration is collected at the end point of each initial grid; calculating a real-time gradient mode of two end points and calculating an average gradient mode of each initial grid according to the real-time gradient mode; die-cutting a next initial grid according to the average gradient; traversing all the global grids according to a hierarchical cruise path strategy, uniformly collecting pollutant concentrations of a plurality of points on each edge of each global grid, and performing PCHIP interpolation fitting; obtaining point cloud data corresponding to the global grid and establishing a transition layer between grids with different densities according to the point cloud data; and constructing a three-dimensional space contour surface concentration field model according to the point cloud data and the concentration interpolation curve and outputting the three-dimensional space contour surface concentration field model. Through the scheme disclosed by the invention, the modeling efficiency and accuracy are improved.

This invention discloses an air quality prediction method based on a deep learning model using potential source contribution analysis. Applied to the field of air quality prediction technology, it addresses the problem that existing technologies only consider the geographical distance of the research object, lacking a deeper exploration of its spatial diffusion impact. This invention utilizes potential source contribution analysis based on airflow trajectories to construct a spatial impact map to represent the spatial correlation between cities. Then, by using a graph convolution algorithm, it extracts effective spatial features from the spatial impact map in conjunction with the pollution status of each city. Furthermore, it employs a long short-term memory model to learn the temporal characteristics of past air pollutant concentration data, generating prediction results. First, the results of potential source contribution analysis are applied to a graph convolutional network, and then combined with the long short-term memory model to predict urban air pollution data. The method of this invention can accurately predict urban air pollutants on both spatiotemporal scales.

The invention discloses an air pollutant concentration prediction method and device, equipment and a medium, and relates to the technical field of deep learning, and the method comprises the steps: obtaining site monitoring data and site longitude and latitude, carrying out the missing value filling and normalization processing of the site monitoring data, obtaining a time sequence, and constructing a geographic relation graph; performing trend feature extraction and feature processing on the time sequence by using an exponential moving average method and based on a gating circulation unit to obtain trend component features; performing periodic feature extraction on the time sequence; performing batch normalization processing, function activation and vector splicing on the noise sequence to obtain noise component features; splicing and fusing the trend component feature, the periodic component feature and the noise component feature to obtain a first prediction feature; solving and coding the time sequence to obtain a second prediction feature; and performing gating fusion and graph attention fusion on the first prediction feature and the second prediction feature based on a geographic relation graph to obtain an air pollutant concentration prediction result.

The invention discloses an environmental air quality monitoring method based on artificial intelligence. The method comprises the following steps: S1, collecting and processing air pollutant concentration data, meteorological parameter data and spatial geographic information data; s2, constructing an improved deep belief network model, wherein the improved deep belief network model comprises an input layer, a multi-layer restricted Boltzmann machine hidden layer, a multi-layer physical prior embedding layer, a space-time dependent modeling module and an output layer; s3, performing layer-by-layer unsupervised pre-training operation on the improved deep belief network model; s4, performing global fine tuning optimization on the improved deep belief network model; s5, performing adaptive dynamic adjustment on the weight of the physical consistency error term; s6, inputting monitoring data collected in real time into the improved deep belief network model after global fine tuning optimization, and executing forward reasoning operation; and S7, executing abnormal pollution event detection. According to the invention, the improved deep belief network model is adopted, and accurate prediction and intelligent early warning of the ambient air quality are realized.

The invention provides a welding fume collecting device which comprises a pipeline truss arranged on a ship body; the first walking mechanism is connected to the pipeline truss in a sliding mode and slides along the pipeline truss in a reciprocating mode; the second walking mechanism is connected to the pipeline truss in a sliding mode, the second walking mechanism and the first walking mechanism are arranged in a spaced mode, and the second walking mechanism slides along the pipeline truss in a reciprocating mode; the environment detection assembly is connected to the first walking mechanism and used for detecting the concentration of pollutants in the air; the dust collection pipeline is connected to the second walking mechanism; and the purification mechanism is connected with the dust collection pipeline and used for absorbing pollutants through the dust collection pipeline and purifying the pollutants. The device is suitable for purifying regional welding fume with unfixed operation points.