CN110531029B - Device for predicting air quality trend based on environmental protection Internet of things big data - Google Patents
Device for predicting air quality trend based on environmental protection Internet of things big data Download PDFInfo
- Publication number
- CN110531029B CN110531029B CN201910757242.8A CN201910757242A CN110531029B CN 110531029 B CN110531029 B CN 110531029B CN 201910757242 A CN201910757242 A CN 201910757242A CN 110531029 B CN110531029 B CN 110531029B
- Authority
- CN
- China
- Prior art keywords
- data
- air quality
- regional
- module
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to the technical field of air quality prediction, and particularly discloses a device for predicting air quality trend based on environment-friendly internet of things big data. According to the method, the regional environment-friendly big data collected by the terminal of the Internet of things are used for analyzing based on the artificial neural network and establishing a more accurate air quality prediction model, the regional and surrounding air quality under specific conditions can be accurately predicted by combining the regional real-time environment-friendly big data, so that data support is provided for reducing regional atmospheric pollution events, the problem of prediction deviation caused by neglecting pollution source fluctuation in the traditional air quality prediction method is solved, meanwhile, an intelligent pollution source control suggestion can be provided based on the data, and the occurrence of the atmospheric pollution events can be accurately prevented and controlled.
Description
Technical Field
The invention relates to the technical field of air quality prediction, in particular to a device for predicting air quality trend based on big data of an environment-friendly internet of things.
Background
With the continuous progress of industrialization and urbanization in China, the environmental conditions begin to worsen in recent years, wherein the reduction of air quality directly harms the physical health of residents and is easy to become a social focus. The air quality prediction can be used for early warning the air quality condition in a short period (three hours to three days) in the future, so that the atmospheric pollution event is avoided by means of pollution source control (emission limitation) and other measures, and the method has important social value.
At present, most of air quality prediction is carried out based on historical meteorological data and air quality data, the method mainly utilizes meteorological factors (wind speed and the like) to carry out air quality prediction, and fluctuation data of regional pollution sources are not collected and utilized. Although meteorological factors have important influence on air quality, the emission condition of pollution sources has important significance on the change trend of the air quality, and the method can only be used for predicting the air quality and cannot be used for providing reasonable pollution source control measures to avoid air pollution events because only meteorological factors are used for establishing a model and has great deviation in practical application.
Therefore, a device for predicting air quality trend based on big data of the environment-friendly internet of things is designed, a more accurate air quality prediction model is established, air quality prediction can be accurately and scientifically performed, and clear management and control measures can be provided to avoid the occurrence of air pollution events, so that the device has important significance for reducing the occurrence of the air pollution events.
Disclosure of Invention
The invention aims to provide a device for predicting air quality trend based on big data of an environment-friendly internet of things, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a device for predicting air quality trend based on big data of environment-friendly Internet of things comprises: the environment-friendly data monitoring system comprises an environment-friendly data monitoring module, an environment-friendly big data storage module, an atmospheric pollutant diffusion analysis module and an air quality prediction module which are sequentially connected, wherein the environment-friendly big data storage module is also connected with the air quality prediction module; the environmental protection data monitoring module is used for acquiring monitoring data in real time based on the Internet of things terminal and uploading the monitoring data to the environmental protection big data storage module; the environment-friendly big data storage module is used for receiving the monitoring data uploaded by the environment-friendly data monitoring module and forming environment-friendly big data for storage; the atmospheric pollutant diffusion analysis module is used for extracting the environmental protection big data stored by the environmental protection big data storage module and establishing a regional air quality prediction model through analysis based on an artificial neural network; the air quality prediction module is used for extracting the current regional monitoring data of a plurality of time intervals stored by the environment-friendly big data storage module, predicting the air quality condition of any point in a region based on the regional air quality prediction model, and pre-warning the air quality in a short time (3 hours to three days) in the future through air quality prediction so as to provide a refined pollution source control scheme; the environment-friendly big data storage module is a reliable distributed data storage service group, can store regional environment-friendly related data, ensures the integrity and the safety of the data, realizes the fast reading and writing of the data through a multi-machine concurrency mechanism, supports data backup, automatically backs up the data to a plurality of physical machines, and automatically migrates the data to other physical machines through backup when any physical machine fails.
As a further scheme of the invention: the monitoring data includes pollutant emission data at an exhaust emission point (e.g., a stack, etc.), pollutant concentration data at an air quality monitoring point, and meteorological data at a meteorological collection point.
As a still further scheme of the invention: the reliable distributed data storage service comprises a data storage service module, a data reading service module and a data authority control service module; the data storage service module and the data reading service module are used for improving the data processing speed through multi-machine concurrent reading and writing, and the data authority control service module is used for authorizing and verifying the data access authority by using an account, a user group, a secret key and the like, so that the illegal data access event is avoided.
As a still further scheme of the invention: the analysis and establishment of the regional air quality prediction model is to establish a regional air quality prediction model through a preset regional specific scene and based on a neural network, train the air quality prediction model by utilizing regional atmospheric pollutant diffusion real monitoring data (namely pollutant emission data of an exhaust emission point, pollutant concentration data of an air quality monitoring point and meteorological data of a meteorological acquisition point of a corresponding region), and learn regional pollutant diffusion characteristics.
As a still further scheme of the invention: the environmental protection data monitoring module comprises an exhaust emission monitoring module, an air quality monitoring module and a regional meteorological collection module.
As a still further scheme of the invention: the exhaust emission monitoring module is used for collecting pollutant emission data of all exhaust emission points (chimneys and the like) in an area in real time, and the pollutants comprise fine particulate matters, inhalable particulate matters, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide and the like.
As a still further scheme of the invention: the air quality monitoring module is used for collecting pollutant concentration data of all air quality monitoring points in an area in real time, and the pollutants comprise fine particles, inhalable particles, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide and the like.
As a still further scheme of the invention: the regional meteorological collection module is used for collecting meteorological data of all meteorological collection points in a region in real time, the regional meteorological collection module can be collection equipment deployed independently, and can also be integrated to a waste gas emission monitoring module or an air quality monitoring module, the meteorological data comprise data such as wind speed, wind direction, temperature, humidity, atmospheric pressure, weather conditions.
As a still further scheme of the invention: the device also comprises a power supply module used for supplying power to the device, wherein the power supply module can be alternating current, direct current, a disposable battery or a rechargeable battery; when the power supply module includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging.
Compared with the prior art, the invention has the beneficial effects that:
the invention is provided with an environment-friendly data monitoring module, an environment-friendly big data storage module, an atmospheric pollutant diffusion analysis module and an air quality prediction module, analyzes and establishes a more accurate air quality prediction model based on an artificial neural network by adopting regional environment-friendly big data collected by an Internet of things terminal, can accurately predict the air quality of a region and the periphery under specific conditions by combining regional real-time environment-friendly big data, further provides data support for reducing regional atmospheric pollution events, can automatically analyze the regional environment-friendly big data and establish the air quality prediction model due to the built-in atmospheric pollutant diffusion analysis module, can automatically predict the air quality based on the data due to the built-in air quality prediction module, solves the problem of prediction deviation caused by neglecting pollution source fluctuation in the traditional air quality prediction method, and can provide an intelligent pollution source control suggestion based on the data, the occurrence of atmosphere pollution events is accurately prevented and controlled.
Drawings
Fig. 1 is a block diagram of an apparatus for predicting air quality trend based on big data of the internet of things.
Fig. 2 is a block diagram of an environmental protection data monitoring module in the device for predicting air quality trend based on big data of the environmental protection internet of things.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
Referring to fig. 1-2, in an embodiment of the present invention, an apparatus for predicting an air quality trend based on big data of an internet of things includes: environmental protection data monitoring module, environmental protection big data storage module, atmospheric pollutants diffusion analysis module and the air quality prediction module that connect gradually, environmental protection big data storage module still is connected with air quality prediction module.
Further, in the embodiment of the present invention, the environmental protection data monitoring module is configured to collect monitoring data in real time based on the terminal of the internet of things and upload the monitoring data to the environmental protection big data storage module.
Specifically, environmental protection data monitoring module can be a set of pollutant on-line monitoring equipment, and is thing networking equipment, for example can include pollution sources monitoring equipment, air quality monitoring equipment, meteorological monitoring equipment etc. and the interval of uploading of monitoring data is one minute, uploads once per minute promptly.
Further, in embodiments of the present invention, the monitoring data includes pollutant emission data at an exhaust emission point (e.g., a stack, etc.), pollutant concentration data at an air quality monitoring point, and meteorological data at a meteorological collection point.
Further, in the embodiment of the present invention, the environmental protection data monitoring module includes an exhaust emission monitoring module, an air quality monitoring module and a regional weather collection module, and specifically may be a plurality of online pollutant monitoring devices based on the internet of things, and correspondingly, the exhaust emission monitoring module may be a pollution source monitoring device based on the internet of things, the air quality monitoring module may be an air quality monitoring device based on the internet of things, and the regional weather collection module may be a weather monitoring device based on the internet of things.
The pollution source monitoring equipment is fixed on a pollution source, and acquires all monitoring index information (emission details of various pollutants) of the pollution source, wherein the pollution source can be industrial waste gas emission equipment such as a chimney; the air quality monitoring equipment is deployed at the periphery of an area, collects all monitoring index information of the deployed position, can be fixed air quality monitoring equipment (an air quality monitoring station and the like), can also be movable air quality monitoring equipment (an air quality monitoring vehicle and the like), is specifically selected according to requirements, and is not limited here.
Further, in the embodiment of the present invention, the exhaust emission monitoring module is configured to collect, in real time, pollutant emission data of all exhaust emission points (chimneys, etc.) in the area, where the pollutants include fine particulate matters, inhalable particulate matters, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, etc.
Further, in the embodiment of the present invention, the air quality monitoring module is configured to collect pollutant concentration data of all air quality monitoring points in real time, where the pollutants include fine particulate matters, inhalable particulate matters, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, and the like.
Further, in the embodiment of the present invention, the regional weather collection module is configured to collect weather data of all weather collection points in real time, the regional weather collection module may be a collection device deployed separately, or may be integrated into the exhaust emission monitoring module or the air quality monitoring module, and the weather data includes data of wind speed, wind direction, temperature, humidity, atmospheric pressure, weather condition, and the like.
Further, in the embodiment of the present invention, the environment-friendly big data storage module is configured to receive the monitoring data uploaded by the environment-friendly data monitoring module and form environment-friendly big data for storage.
Furthermore, in the embodiment of the present invention, the environment-friendly big data storage module is a set of reliable distributed data storage services, and can store regional environment-friendly related data, ensure data integrity and security, and implement fast data reading and writing through a multi-machine concurrency mechanism, for example, the reliable distributed data storage services may be services deployed at a cloud end, or services deployed at a location where the monitoring device of the internet of things is located, and it can be understood that the reliable distributed data storage services support data backup and automatically backup data to multiple physical machines; when any physical machine fails, the data is automatically migrated to other physical machines through backup.
Specifically, the reliable distributed data storage service comprises a data storage service module, a data reading service module and a data authority control service module; the data storage service module and the data reading service module are used for improving the data processing speed through multi-machine concurrent reading and writing, and the data authority control service module is used for authorizing and verifying the data access authority by using an account, a user group, a secret key and the like, so that the illegal data access event is avoided.
Further, in the embodiment of the present invention, the atmospheric pollutant diffusion analysis module is configured to extract the environmental protection big data stored by the environmental protection big data storage module and establish a regional air quality prediction model by analyzing the real environmental protection big data in the corresponding region based on the artificial neural network.
The regional air quality prediction model is established through a preset regional specific scene based on a neural network, and is trained by using regional atmospheric pollutant diffusion real monitoring data (namely exhaust gas emission point pollutant emission data, air quality monitoring point pollutant concentration data and meteorological data of meteorological acquisition points of a corresponding region) to learn regional pollutant diffusion characteristics.
Specifically, the regional air quality prediction model is a prediction model based on a neural network, and comprises a plurality of convolution layers, an LSTM layer, a full-connection layer, a hidden layer, an activation layer and the like; the regional air quality prediction model inputs pollutant diffusion state data in the first N periods of a region, prediction data of a pollution source in a prediction period, regional meteorological prediction data in the prediction period and relative position information; the regional air quality prediction model outputs the air quality value of a target point, the characteristic value of each time period is extracted through the convolutional network, and the cyclic neural network further learns the time sequence characteristics by utilizing the output value of the convolutional network.
Further, in the embodiment of the present invention, the regional pollutant diffusion state data includes regional all pollution source data, regional meteorological data, regional air quality data, and the like; all pollution source data of the region comprise pollutant components, emission intensity and the like, chimney height and the like; the regional meteorological data comprise wind speed, wind direction, temperature, humidity and the like; the air quality value comprises the concentration of pollutants such as fine particulate matters, inhalable particulate matters, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide and the like; the regional weather prediction data refers to regional weather prediction values in a specific time period, and the source of the regional weather prediction data is prediction data published by national weather prediction departments; the relative position information comprises the distances between the predicted target point and all pollution sources, including horizontal coordinate distances and vertical distances, wherein the horizontal coordinate distances are downwind distances and downwind vertical distances of the pollution sources.
Further, in the embodiment of the present invention, the air quality prediction module is configured to extract the current regional monitoring data stored in the environmental-friendly big data storage module in a plurality of time periods, predict the air quality conditions of the industrial area and any peripheral point under specific conditions based on the regional air quality prediction model, and perform early warning on the air quality in a short time (3 hours to three days) in the future through air quality prediction, so as to provide a refined pollution source control scheme.
Further, in the embodiment of the present invention, the specific conditions include regional pollutant diffusion data of the current N periods of the region, prediction data of a pollution source in a prediction period, prediction data of regional weather in the prediction period, relative position information, and the like; the regional meteorological data comprise temperature, humidity, wind direction, wind power and the like; the regional weather prediction data source is data issued by the national weather forecast department; the air quality at any point includes fine particulate matter, respirable particulate matter, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, and the like.
Further, in the embodiment of the invention, the device for predicting the air quality trend based on the big data of the environmental protection internet of things further comprises a power module for supplying power to the device, wherein the power module can be alternating current, direct current, a disposable battery or a rechargeable battery; when the power supply module comprises a rechargeable battery, the rechargeable battery may support wired charging or wireless charging, wherein the non-involved parts are the same as or may be implemented using prior art.
Those skilled in the art will appreciate that the modules shown in fig. 1-2 are only block diagrams of the portions relevant to the present disclosure, and do not constitute a limitation of the apparatus for predicting air quality trend based on big data of the internet of things in the present disclosure, and a specific apparatus for predicting air quality trend based on big data of the internet of things in the present disclosure may include more or less components than those shown in the figures, or combine some components, or have different component arrangements.
In another embodiment provided by the invention, an air quality trend prediction method using the device for predicting air quality trend based on big data of the environment-friendly internet of things comprises the following steps:
1) collecting environmental protection big data: the environmental protection big data collection is carried out real-time acquisition monitoring data through the environmental protection data monitoring module based on the thing networking, simultaneously with monitoring data real-time upload to environmental protection big data storage module.
Specifically, the environmental protection data monitoring module is a set of pollutant on-line monitoring equipment, including pollution sources monitoring equipment, air quality monitoring equipment, meteorological monitoring equipment etc. current products.
The pollution source monitoring equipment is fixed on a pollution source, and collects all monitoring index information (various pollutant emission details) of the pollution source.
Wherein the pollution source is industrial waste gas emission equipment such as a chimney.
The air quality monitoring equipment is deployed at the periphery of an area, collects all monitoring index information of a deployment position, and can be fixed air quality monitoring equipment (an air quality monitoring station and the like) or movable air quality monitoring equipment (an air quality monitoring vehicle and the like).
Wherein, the monitoring indexes comprise sulfur dioxide, ozone, smoke dust, flow rate, temperature, pressure, humidity and the like.
The regional meteorological monitoring equipment can collect meteorological information of all meteorological collection points in real time, and the regional meteorological monitoring module can be deployed independently and also can be integrated into pollution source monitoring equipment or air quality monitoring equipment.
Wherein, the meteorological information comprises wind speed, wind direction, temperature, humidity, atmospheric pressure, weather condition and the like.
The interval time for uploading the monitoring data in real time is one minute, namely, the monitoring data is uploaded once per minute.
The environment-friendly big data storage module comprises a set of distributed storage system, can stably store massive environment-friendly data, and can quickly respond to an environment-friendly data query request.
2) Regional atmospheric pollutant diffusion analysis: and extracting the environmental protection big data stored by the environmental protection big data storage module through the atmospheric pollutant diffusion analysis module, and establishing a regional air quality prediction model through automatically analyzing regional atmospheric pollutant diffusion real data based on an artificial neural network.
The regional air quality prediction model is a prediction model based on a neural network and comprises a plurality of convolutional layers, an LSTM layer, a full-connection layer, a hidden layer, an activation layer and the like; the regional air quality prediction model input comprises state data (pollution sources, weather, air quality and the like) of the first N periods, weather data (predicted values comprising wind speed, wind power, temperature and the like) of the prediction periods, and prediction data (artificially set control values) of the pollution sources of the prediction periods; the output of the regional air quality prediction model is that the concentration value of the pollutants at the predicted point is obtained; furthermore, the regional air quality prediction model was fitted using real regional atmospheric pollutant diffusion monitoring data.
For example, the first N period status data may be expressed as S ═ S (S)1,s2...sn) The state data of a certain period of time can be represented as st＝(x,y,z,H,v,q,h,w,r)，stIs s ist+1Previous period status data; wherein x, y and z are respectively the downwind direction distance, the downwind vertical direction distance and the horizontal height distance of the monitoring point at the pollution source, are vector values and represent the position information of all the pollution sources and the prediction point; h is the sum of the height of the pollution source and the height of the upward punch for smoke plume emission, and is a vector value which represents the height of all the pollution sources; q is the unit emission intensity of the pollution sources, namely the pollutant emission amount in unit time, the unit is mg/s, and the vector value represents the emission intensity of all the pollution sources; v is wind speed (m/s); h is the sunlight intensity; w is weather conditions (cloudy, fog, rain and the like), represents meteorological information in the region, and is sourced from national meteorological prediction department data; r is the concentration value of atmospheric pollutants at the predicted point and has the unit of mg/m3。
The fitting of the diffusion monitoring data of the regional atmospheric pollutants refers to training an air quality prediction model by taking the regional historical monitoring data as a training sample after standardized processing.
The method for standardizing all historical monitoring data of the area comprises the following steps:
dividing the historical data into time period data at intervals of 30 minutes;
performing tail removal average on all the time period data to convert the time period data into the time period state data;
the data for N +1 consecutive time periods is converted into a training example.
Wherein, the calculation method for the average of the tail removal of the time-segment data comprises
Wherein v isiV is a time period state data value for the data after the tail is removed. Wherein, to the end of the time section data means, let DT be the end of the time section data, D be the original time section data, when
When it is, then
Wherein, the conversion of the data of continuous N +1 time periods into a training sample means that the input parameter x of the sample is(s) after being arranged in time sequence1,s2...sN,HN+1,vN+1,qN+1,hN+1,wN+1) The sample output target value y is rN+1. Wherein s is1To sNThe number of state data in 1 st to N th time periods, HN+1Is the sum of the pollution source height and the plume uprush height at the moment N +1, vN+1Wind speed at time N +1, qN+1The emission intensity of the pollution source at the moment of N +1, hN+1Intensity of sunlight at time N +1, wN+1Is the weather condition value at the moment N +1, rN+1And the air quality monitoring value is the air quality monitoring value of the monitoring point at the moment N + 1.
3) Regional air quality prediction: the air quality prediction module is used for extracting the current regional monitoring data of a plurality of time periods stored in the environmental-friendly big data storage module, and based on the current regional monitoring data of a plurality of time periods, an air quality prediction model is used for predicting the air quality conditions of a region and any peripheral points in a certain period (3 hours to three days) in the future under specific conditions.
The area monitoring data of the current several time periods refers to area monitoring data (pollution source, weather, air quality, position and the like) of N time periods before the current time period, and is represented as S ═ S (S ═ S1,s2...sn) (ii) a Under the specific condition, the specified pollution source condition and meteorological condition P ═ Hp,vp,qp,hp,wp) Wherein, the meteorological condition refers to a meteorological predicted value of a region in a future time period, the source is data issued by a national meteorological forecasting department, vpTo predict wind speed, hpTo predict the intensity of illumination, wpIn order to predict weather conditions, the pollutant source conditions are assumed values of pollutant emission of all pollutant sources in the area, including pollutant emission intensity, pollutant emission height and the like, qpFor a set pollutant emission intensity, HpThe set pollutant height can be set manually.
Wherein the air quality condition is predicted based on an air quality prediction model rp＝f(s1,s2...sn,Hp,vp,qp,hp,wp) Wherein, monitoring data S (S) N time intervals before any time is carried out1,s2...sn) For the determination of the value, the set value P (H) is set for the pollution source and the meteorological conditionsp,vp,qp,hp,wp) In the method, the meteorological condition is a determined predicted value, the pollution source condition is a control value, and different pollutant emission intensities q are setpThe values can be obtained to obtain different predicted values of air quality by controlling qpThe value can realize refined air quality treatment.
The steps in the above-described embodiment methods are not limited to be performed in the exact order provided they are explicitly described herein, and may be performed in other orders. Moreover, at least some of the steps are not necessarily performed at the same time, but may be performed at different times, and these steps are not necessarily performed in sequence, but may be performed alternately or alternately with other steps.
The invention has the beneficial effects that: the invention is provided with an environmental protection data monitoring module based on an internet of things terminal, an environmental protection big data storage module used for storing data, an atmospheric pollutant diffusion analysis module based on a deep learning technology and an air quality prediction module used for predicting air quality, wherein the environmental protection big data collected by the internet of things terminal is used for analyzing pollution sources, weather and atmospheric quality related influences in a region, an air quality prediction model based on a deep learning network is automatically generated, the air quality prediction model can be established by simultaneously utilizing weather data and pollutant emission time sequence data, and continuous regional air quality change data are learned by a latest artificial intelligence algorithm (a CNN network and an RNN network); moreover, based on an air quality prediction model and combined with regional real-time environmental protection big data, regional and surrounding air quality under specific conditions (weather conditions, pollutant emission conditions and the like) can be accurately predicted, and accurate air quality prediction can provide data support for reducing regional air pollution events.
According to the invention, the atmospheric pollutant diffusion analysis module is arranged in the air quality prediction model, so that the regional environment-friendly big data can be automatically analyzed, the air quality prediction model is established, the air quality prediction module is arranged in the air quality prediction model, so that the air quality can be automatically predicted based on the data, a refined air quality treatment scheme is provided, and the regional environment-friendly big data is automatically analyzed by means of a big data processing technology and an intelligent analysis algorithm to establish a more accurate air quality prediction model.
The method can solve the problem of prediction deviation caused by neglecting pollution source fluctuation in the traditional air quality prediction method, can provide intelligent pollution source control suggestions and accurately prevent and control the occurrence of the atmospheric pollution event based on data, can predict the air quality more accurately and scientifically, can provide definite control measures to avoid the occurrence of the atmospheric pollution event, and has important significance for reducing the occurrence of the atmospheric pollution event.
Those skilled in the art will appreciate that all or part of the processes in the method of the above embodiments may be implemented by instructing related hardware through a computer program, for example, the method of the present invention is implemented by Python language through programming, that is, the whole process of predicting the air quality trend based on the environmental protection big data for monitoring the internet of things is completed, the program may be stored in a computer readable storage medium, and the program may include the processes of the embodiments of the methods when executed. The storage medium may be a random access memory, a flash memory, a read only memory, a programmable read only memory, an electrically erasable programmable memory, a register, etc.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (1)
1. The utility model provides a device based on big data prediction air quality trend of environmental protection thing networking which characterized in that includes: the environment-friendly data monitoring system comprises an environment-friendly data monitoring module, an environment-friendly big data storage module, an atmospheric pollutant diffusion analysis module and an air quality prediction module which are sequentially connected, wherein the environment-friendly big data storage module is also connected with the air quality prediction module;
the environmental protection data monitoring module is used for acquiring monitoring data in real time based on the Internet of things terminal and uploading the monitoring data to the environmental protection big data storage module; the monitoring data comprises pollutant emission data of an exhaust emission point, pollutant concentration data of an air quality monitoring point and meteorological data of a meteorological acquisition point;
the environment-friendly data monitoring module comprises an exhaust emission monitoring module, an air quality monitoring module and a regional meteorological collection module; the exhaust emission monitoring module is used for collecting pollutant emission data of exhaust emission points in an area in real time; the contaminants include fine particulates, respirable particulates, sulfur dioxide, nitrogen dioxide, ozone, and carbon monoxide; the air quality monitoring module is used for collecting pollutant concentration data of air quality monitoring points in an area in real time; the regional meteorological acquisition module is used for acquiring meteorological data of meteorological acquisition points in a region in real time, wherein the meteorological data comprises wind speed, wind direction, temperature, humidity, atmospheric pressure and weather conditions;
the environment-friendly big data storage module is used for receiving the monitoring data uploaded by the environment-friendly data monitoring module and forming environment-friendly big data for storage;
the atmospheric pollutant diffusion analysis module is used for extracting the environmental protection big data stored by the environmental protection big data storage module and establishing a regional air quality prediction model through analysis based on an artificial neural network; the atmospheric pollutant diffusion analysis module is used for extracting the environmental protection big data stored by the environmental protection big data storage module and establishing a regional air quality prediction model by analyzing the real environmental protection big data in the corresponding region based on an artificial neural network; the regional air quality prediction model is established through a preset regional specific scene and based on a neural network, and is trained by using regional atmospheric pollutant diffusion real monitoring data to learn regional pollutant diffusion characteristics; the regional air quality prediction model is a prediction model based on a neural network and comprises a plurality of convolution layers, an LSTM layer, a full-connection layer, a hidden layer and an activation layer; the regional air quality prediction model inputs pollutant diffusion state data in the first N periods of a region, prediction data of a pollution source in a prediction period, regional meteorological prediction data in the prediction period and relative position information; outputting the air quality value of a target point by the regional air quality prediction model, extracting a characteristic value of each time period through a convolutional network, and further learning a time sequence characteristic by the recurrent neural network by utilizing an output value of the convolutional network;
the air quality prediction module is used for extracting the current regional monitoring data of a plurality of time periods stored by the environment-friendly big data storage module and predicting the regional air quality condition based on the regional air quality prediction model;
the regional pollutant diffusion state data comprise regional all pollution source data, regional meteorological data and regional air quality data; all pollution source data of the region comprise pollutant components, emission intensity and chimney height; the regional meteorological data comprise wind speed, wind direction, temperature and humidity; the air quality values include contaminant concentrations of fine particulates, respirable particulates, sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide; the regional weather prediction data refers to regional weather prediction values in a specific time period, and the source of the regional weather prediction data is prediction data published by national weather prediction departments; the relative position information comprises the distances between the predicted target point and all pollution sources, including horizontal coordinate distances and vertical distances, wherein the horizontal coordinate distances are downwind distances and downwind vertical distances of the pollution sources;
the device for predicting the air quality trend based on the environmental protection Internet of things big data further comprises a power supply module for supplying power to the device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910757242.8A CN110531029B (en) | 2019-08-16 | 2019-08-16 | Device for predicting air quality trend based on environmental protection Internet of things big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910757242.8A CN110531029B (en) | 2019-08-16 | 2019-08-16 | Device for predicting air quality trend based on environmental protection Internet of things big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110531029A CN110531029A (en) | 2019-12-03 |
| CN110531029B true CN110531029B (en) | 2022-02-25 |
Family
ID=68663425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910757242.8A Active CN110531029B (en) | 2019-08-16 | 2019-08-16 | Device for predicting air quality trend based on environmental protection Internet of things big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110531029B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI812051B (en) * | 2022-03-08 | 2023-08-11 | 國立臺灣師範大學 | Volatile organic compounds concentration forecast method |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111011247A (en) * | 2019-12-13 | 2020-04-17 | 巨星农牧股份有限公司 | Sustainable and intelligent pig raising method |
| CN111103220B (en) * | 2019-12-31 | 2021-04-27 | 西安交通大学 | Method and system for predicting and regulating concentration of atmospheric pollutants |
| CN111157682A (en) * | 2020-01-06 | 2020-05-15 | 上海应用技术大学 | Air quality monitoring and predicting system and method |
| CN111814964A (en) * | 2020-07-20 | 2020-10-23 | 江西省环境监测中心站 | Air pollution treatment method based on air quality condition prediction and storage medium |
| CN112769930A (en) * | 2020-12-31 | 2021-05-07 | 北京佳华智联科技有限公司 | Pollution trend prediction method and device, and pollution event monitoring device and equipment |
| CN112836952A (en) * | 2021-01-26 | 2021-05-25 | 华风气象传媒集团有限责任公司 | Travel recommendation method |
| CN113283630A (en) * | 2021-04-09 | 2021-08-20 | 中科三清科技有限公司 | Air quality prediction method, device, equipment and computer readable storage medium |
| CN113420071A (en) * | 2021-06-24 | 2021-09-21 | 天津大学 | Optimal selection method for joint defense joint control emergency regulation and control scheme of atmosphere pollution area |
| CN116029411A (en) * | 2022-05-23 | 2023-04-28 | 成都秦川物联网科技股份有限公司 | Smart city area management method and system based on Internet of things |
| CN116562712B (en) * | 2023-06-29 | 2023-09-19 | 内江师范学院 | System and method for predicting air quality |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106352914A (en) * | 2016-08-01 | 2017-01-25 | 孙扬 | Device for managing regional air quality |
| CN106651036A (en) * | 2016-12-26 | 2017-05-10 | 东莞理工学院 | Air quality forecasting system |
| CN106779165A (en) * | 2016-11-21 | 2017-05-31 | 山东大学 | Power system environment dispatching method based on urban air-quality Predicting Technique |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN109298136A (en) * | 2018-10-11 | 2019-02-01 | 北京大学 | Air Quality Evaluation method, apparatus, equipment and storage medium |
| CN109376443A (en) * | 2018-11-02 | 2019-02-22 | 唐山华洋环保科技有限公司 | Regional Atmospheric Pollution environmental simulation dynamic simulator system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492822B (en) * | 2018-11-24 | 2021-08-03 | 上海师范大学 | Air pollutant concentration time-space domain correlation prediction method |
| CN110070224A (en) * | 2019-04-20 | 2019-07-30 | 北京工业大学 | A kind of Air Quality Forecast method based on multi-step recursive prediction |
-
2019
- 2019-08-16 CN CN201910757242.8A patent/CN110531029B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106352914A (en) * | 2016-08-01 | 2017-01-25 | 孙扬 | Device for managing regional air quality |
| CN106779165A (en) * | 2016-11-21 | 2017-05-31 | 山东大学 | Power system environment dispatching method based on urban air-quality Predicting Technique |
| CN106651036A (en) * | 2016-12-26 | 2017-05-10 | 东莞理工学院 | Air quality forecasting system |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| CN109298136A (en) * | 2018-10-11 | 2019-02-01 | 北京大学 | Air Quality Evaluation method, apparatus, equipment and storage medium |
| CN109376443A (en) * | 2018-11-02 | 2019-02-22 | 唐山华洋环保科技有限公司 | Regional Atmospheric Pollution environmental simulation dynamic simulator system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI812051B (en) * | 2022-03-08 | 2023-08-11 | 國立臺灣師範大學 | Volatile organic compounds concentration forecast method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110531029A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110531029B (en) | Device for predicting air quality trend based on environmental protection Internet of things big data | |
| CN110531030B (en) | Method and device for analyzing atmospheric pollutants based on Internet of things big data | |
| CN112085241B (en) | Environmental big data analysis and decision platform based on machine learning | |
| Wang et al. | Regional prediction of ground-level ozone using a hybrid sequence-to-sequence deep learning approach | |
| CN114280695A (en) | Air pollutant monitoring and early warning method and cloud platform | |
| CN106651036A (en) | Air quality forecasting system | |
| CN102679935B (en) | System and method for calculating icing thickness of power transmission line | |
| CN110716512A (en) | Environmental protection equipment performance prediction method based on coal-fired power plant operation data | |
| CN110555551A (en) | air quality big data management method and system for smart city | |
| CN114048952B (en) | Iron-making plant safety situation sensing method based on edge internet of things technology and neural network | |
| CN114693003B (en) | Smart city air quality prediction method and system based on Internet of things | |
| CN115796434A (en) | Management and control method and device for power distribution network, electronic equipment and storage medium | |
| CN111060654A (en) | Unmanned aerial vehicle atmospheric pollution real-time supervision early warning platform based on digital twin | |
| CN115762169A (en) | Intelligent control system and method for unmanned driving of sanitation vehicle | |
| CN117708617B (en) | Atmospheric pollution tracing method based on multi-source big data and pollution characteristic space-time matching | |
| CN117312784A (en) | Pollution source tracing method based on receptor model and big data combination | |
| CN114819423B (en) | Carbon emission control system applying GIS technology and data information fusion system | |
| CN115471128A (en) | Big data-based device for predicting air quality trend | |
| CN114118678A (en) | Iron works management system based on edge internet of things and architecture method thereof | |
| CN113947013A (en) | Boiler short-term NO based on hybrid deep neural network modelingxEmission prediction method | |
| CN111060653A (en) | Atmospheric pollution real-time supervision early warning unmanned aerial vehicle based on digital twin | |
| CN117406608B (en) | Tunnel dust removal control method and system | |
| CN117542434B (en) | Air pollutant concentration analysis method based on data analysis | |
| CN117388445B (en) | Atmospheric environment monitoring system | |
| CN116522166B (en) | Air pollution monitoring system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |