CN116448966B - Air quality assessment method based on combination of intelligent Internet of things and deep learning - Google Patents
Air quality assessment method based on combination of intelligent Internet of things and deep learning Download PDFInfo
- Publication number
- CN116448966B CN116448966B CN202310705453.3A CN202310705453A CN116448966B CN 116448966 B CN116448966 B CN 116448966B CN 202310705453 A CN202310705453 A CN 202310705453A CN 116448966 B CN116448966 B CN 116448966B
- Authority
- CN
- China
- Prior art keywords
- air quality
- index
- deep learning
- air
- node position
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 70
- 238000001303 quality assessment method Methods 0.000 title claims abstract description 32
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims description 26
- 238000012937 correction Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 23
- 238000003915 air pollution Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000012876 topography Methods 0.000 claims description 11
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 5
- 238000013441 quality evaluation Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 239000003344 environmental pollutant Substances 0.000 description 8
- 231100000719 pollutant Toxicity 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- JCXJVPUVTGWSNB-UHFFFAOYSA-N Nitrogen dioxide Chemical compound O=[N]=O JCXJVPUVTGWSNB-UHFFFAOYSA-N 0.000 description 6
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 6
- 230000000306 recurrent effect Effects 0.000 description 5
- 239000000356 contaminant Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- MGWGWNFMUOTEHG-UHFFFAOYSA-N 4-(3,5-dimethylphenyl)-1,3-thiazol-2-amine Chemical compound CC1=CC(C)=CC(C=2N=C(N)SC=2)=C1 MGWGWNFMUOTEHG-UHFFFAOYSA-N 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- BWFPGXWASODCHM-UHFFFAOYSA-N copper monosulfide Chemical compound [Cu]=S BWFPGXWASODCHM-UHFFFAOYSA-N 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
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
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital
-
- 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
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—Specially adapted to detect a particular component
- G01N33/0037—Specially adapted to detect a particular component for NOx
-
- 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
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—Specially adapted to detect a particular component
- G01N33/0042—Specially adapted to detect a particular component for SO2, SO3
-
- G01N33/0068—
-
- 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
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0073—Control unit therefor
- G01N33/0075—Control unit therefor for multiple spatially distributed sensors, e.g. for environmental monitoring
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- 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 discloses an air quality assessment method and system based on combination of intelligent Internet of things and deep learning, which belong to the technical fields of rural agriculture, environment, intelligent Internet of things and artificial intelligence, wherein the method comprises the following steps: a plurality of sensor nodes are arranged to collect pollution factors and the like as monitoring data, and the air index score value of any node position is solved; processing the air index score value of any node by adopting a collaborative kriging interpolation calculation method to obtain a predicted air quality index of the unknown node position, and arranging a plurality of sensor nodes according to the predicted air quality index to obtain an actual air quality index of the unknown node position to construct a training set; training the deep learning cyclic neural network model, inputting the predicted air quality index of the unknown node position to be corrected into the trained model, obtaining the actual air quality index of the unknown node position and generating an air quality report. The method improves the accuracy of air quality assessment in terms of time and spatial density.
Description
Technical Field
The invention relates to the technical field of rural agriculture, environment, intelligent Internet of things and artificial intelligence, in particular to an air quality assessment method based on the combination of intelligent Internet of things and deep learning.
Background
The population structure corresponding to the traditional rural population in China is mainly the resident population of the middle-aged and the elderly, the special population structure determines, and the influence of the air quality on the health and life quality of the traditional rural resident population is more important. Among them, various human chronic diseases caused by different pollutants in the air, such as SO2 (sulfur dioxide), NO2 (nitrogen dioxide), PM2.5 and PM10, and the like, and various researches also show that the exposure to the highly polluted environment can cause cardiovascular diseases and respiratory diseases of human beings. However, the existing method for acquiring the air quality influence elements in the traditional rural areas is time-consuming and labor-consuming, has insufficient timeliness and low data reliability, and has no reliable air quality evaluation method.
Therefore, a method which is standard, time-saving, labor-saving, more timely, more reliable and more suitable for rural air quality assessment is needed.
Disclosure of Invention
The invention provides an air quality assessment method and system based on combination of intelligent Internet of things and deep learning, which are used for solving the technical problems that the collection of air quality influence elements in the traditional rural areas is time-consuming and labor-consuming in most cases, the timeliness is insufficient, the data reliability is low and meanwhile, a reliable air quality assessment method is not available.
In one aspect, an embodiment of the present invention provides an air quality assessment method based on combination of intelligent internet of things and deep learning, including:
step S1, arranging a plurality of sensor nodes according to preset requirements, and acquiring a plurality of pollution factors, wind speeds and wind directions in real time as monitoring data;
s2, processing the monitoring data through a concentration limit value reference table of the air pollution index and an air index score value to obtain the air index score value of any node position, and storing the air index score value into a preset database;
s3, processing the air index score value of any node position by adopting a collaborative kriging interpolation calculation method to calculate a predicted air quality index of an unknown node position, and storing the predicted air quality index into the preset database;
s4, a plurality of sensor nodes are arranged according to the air quality index of the unknown node position, the actual air quality index of the unknown node position is obtained, and the actual air quality index is stored in the preset database;
s5, reading the predicted air quality indexes of a plurality of node positions in the preset database and the actual air quality indexes of the corresponding plurality of node positions to construct a training set and a testing set;
s6, training the model based on the deep learning cyclic neural network by utilizing the training set to obtain an air quality index correction model based on the deep learning cyclic neural network;
and S7, inputting the predicted air quality index of the unknown node position to be corrected into the air quality index correction model based on the deep learning cyclic neural network to obtain the actual air quality index of the unknown node position, and establishing an air quality report according to the actual air quality index of the unknown node position.
In another aspect, an embodiment of the present invention provides an air quality assessment system based on combination of intelligent internet of things and deep learning, including:
the acquisition module is used for arranging a plurality of sensor nodes according to preset requirements so as to acquire a plurality of pollution factors, wind speeds and wind directions in real time as monitoring data;
the first processing module is used for processing the monitoring data through a concentration limit value reference table of the air pollution index and the air index score value to obtain the air index score value of any node position and storing the air index score value into a preset database;
the second processing module is used for processing the air index score value of any node position by adopting a collaborative kriging interpolation calculation method so as to calculate a predicted air quality index of an unknown node position and store the predicted air quality index into the preset database;
the arrangement module is used for arranging a plurality of sensor nodes according to the air quality index of the unknown node position, obtaining the actual air quality index of the unknown node position and storing the actual air quality index into the preset database;
the construction module is used for reading the predicted air quality indexes of the plurality of node positions in the preset database and the actual air quality indexes of the plurality of corresponding node positions so as to construct a training set and a testing set;
the training module is used for training the deep learning cyclic neural network model by utilizing the training set to obtain an air quality index correction model based on the deep learning cyclic neural network;
the correction module is used for inputting the predicted air quality index of the unknown node position to be corrected into the air quality index correction model based on the deep learning cyclic neural network, obtaining the actual air quality index of the unknown node position, and establishing an air quality report according to the actual air quality index of the unknown node position.
In still another aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the air quality assessment method based on the combination of intelligent internet of things and deep learning as described in the foregoing embodiment when executing the computer program.
In a further aspect, the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the air quality assessment method based on the combination of intelligent internet of things and deep learning as described in the above embodiment.
The technical scheme of the invention at least realizes the following beneficial technical effects:
the method adopts a deep learning convolutional neural network and a cyclic neural network to carry out multidimensional modeling aiming at the duty ratio weights of pollutants in different stages and different periods, so that the global air quality can be estimated and evaluated through known node data, and finally a scientific and standardized air quality evaluation report of time and space density under high precision is provided.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of an air quality assessment method based on the combination of intelligent Internet of things and deep learning according to one embodiment of the invention;
FIG. 2 is a schematic diagram of an air quality index correction model based on a deep learning recurrent neural network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an air quality assessment system based on combination of intelligent internet of things and deep learning according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The air quality evaluation method and system based on the combination of the intelligent internet of things and the deep learning, which are provided by the embodiment of the invention, are described below with reference to the accompanying drawings.
Fig. 1 is a flowchart of an air quality assessment method based on a combination of intelligent internet of things and deep learning according to an embodiment of the present invention.
As shown in fig. 1, the air quality assessment method based on the combination of intelligent internet of things and deep learning comprises the following steps:
in step S1, a plurality of sensor nodes are arranged according to preset requirements, so as to collect a plurality of pollution factors, wind speed and wind direction in real time as monitoring data.
Specifically, in the embodiment of the invention, intelligent sensors are required to be laid in advance, intelligent internet of things sensor nodes are used for air quality monitoring in rural areas, the sensor nodes can be arranged at different air pollution sources and places with maximized sensor density to detect air quality, and the sensors mainly comprise an air particle sensor, a sulfur dioxide sensor, a nitrogen dioxide sensor, a wind speed sensor and a wind direction sensor. The sensor nodes should be laid out in village with great population density, and the sensor erection height should be between 10m and 15 m.
The sensor nodes can collect various indexes in the air, collect monitoring data of main pollution factors (SO 2, NO2, PM2.5 and PM 10) and wind speed and wind direction every hour, and transmit the collected data to the server side to be used as monitoring data for monitoring air quality change in real time.
In step S2, the air pollution index concentration limit value reference table and the air pollution index score value process the monitoring data to obtain an air pollution index score value at any node position, and store the air pollution index score value in a preset database.
Further, in one embodiment of the present invention, step S2 specifically includes:
step S201, processing the monitoring data through a concentration limit value reference table and an air index score value of the air pollution index to obtain the air index score value of each air pollution factor;
step S202, comparing the air index score value of each air pollution factor, screening out the maximum air index score value, taking the maximum air index score value as the air index score value of any node position, and storing the air index score value into a preset database.
The air pollution index (Air Quality Index: AQI) calculation means: the data collected by the sensor nodes of the intelligent Internet of things can be processed by the server, and the daily average concentration is obtained through calculation of the time average concentration of each pollution factor.
Specifically, the reference table (GB 3095-2012 standard) is first referenced to the current concentration limits of AQI, as shown in Table 1 below:
TABLE 1
The air index (IAQI) is calculated as follows:
wherein ,is a contaminant item->Air mass fraction index of (2); />Inputting a value for the concentration of the pollutant; />For Table 1 and->A high value of the similar contaminant concentration limit; />For Table 1 and->A lower value of the similar contaminant concentration limit, wherein +.>The lower abbreviation refers to the lower state; />For Table 1 and->A corresponding air mass fraction index; />For Table 1 and->Corresponding air mass fraction index.
The air pollution factor IAQI values are calculated by the IAQI index calculation pollutant concentration limit value reference table and the air index score index (IAQI) calculation formula.
And comparing the IAQI values of all air pollution factors, if the IAQI values of other pollutants are smaller than those of one pollutant, setting the AQI value of the node position to be the maximum value of all IAQIs on the same day, and storing and recording the obtained AQI value of the node position.
In step S3, the air index score value of any node is processed by adopting a collaborative kriging interpolation calculation method, so as to calculate the predicted air quality index of the unknown node position, and the predicted air quality index is stored in a preset database.
Further, in one embodiment of the present invention, step S3 specifically includes:
step S301, introducing the topography and wind direction into a collaborative Kriging interpolation algorithm to obtain a collaborative half variation function;
step S302, fitting the half-collaborative variation function to calculate a weight coefficient, processing the air index score value of any node position according to the weight coefficient to solve the air quality index of the unknown node position, and sending the air quality index to a preset database.
It should be noted that in the layout of the nodes of the intelligent sensor of the internet of things, each point location of a village cannot be laid, so that when the area range of a village is large, the AQI value of a single node may not reflect the air quality indexes of all the points, so that the embodiment of the invention takes the maximum air index score value as the air index score value of any node position in advance, and then calculates the AQI value of the unknown point location by adopting the kriging interpolation calculation method.
Specifically, a synergistic kriging method of topography and wind direction is introduced. The collaborative kriging method (CoKriging) is an extension of the common kriging method, and the optimal estimation method of the regional variable is developed from a single attribute to two or more collaborative regional attributes, and one or more auxiliary variables are used for correcting the estimated value. In the synergistic kriging process, the process,、/>the calculation method of the semi-variance model functions respectively representing the variable 1 (wind direction) and the variable 2 (topography) is the same as that of the common Kriging interpolation method; />The covariance function is an expression for measuring the degree of spatial correlation between sample points of two variables:
wherein ,for the covariant function, ++>Is made of->Number of separated paired sample spots, +.>For sample spots +.>For the distance between two points>Property value of the point with respect to the wind direction variable +.>Is the attribute value of the point with respect to the topography variable.
And then fitting the fitting covariance function, wherein the following equation is adopted:
wherein , and />Sample point number respectively representing two attributes, +.> and />Is the weight parameter to be solved +.>Andare respectively-> and />Is a variant function model of->For Lagrangian coefficient, +.>For the 1 i-th sample point coordinate, +.>For the 2 j-th sample point coordinate, +.>For the ith sample point coordinate, +.>For the j-th sample point coordinate, +.>For the target point->Property value of the point with respect to the wind direction variable +.>Property values of points with respect to topography variables, +.> and />Is a variant function model of these two variables.
And (3) calculating a weight coefficient through the fitting function, and substituting the obtained weight coefficient into a formula below to calculate an unknown sample point predicted value, namely an Air Quality Index (AQI) of the unknown node position:
wherein ,air quality index for unknown node position, +.>For the sample node +.>Sample node number for wind direction variable, +.>Weight pending for wind direction variable, +.>Property value for wind direction variable, +.>Sample node number for the relief variable, +.>Weight pending for the topography variable, +.>Is the attribute value of the relief variable.
And finally, storing the calculated air quality value, longitude and latitude and other information of the predicted sample point into a preset database.
In step S4, a plurality of sensor nodes are further arranged according to the air quality index of the unknown node position, and the actual air quality index of the unknown node position is obtained and stored in a preset database.
It will be appreciated that since training of the neural network model is also required subsequently, it is necessary to obtain the input values: besides the air quality index of the unknown node position, the corresponding output value needs to be obtained: the actual air quality index of the node location is unknown to construct a training set and a test set.
The method comprises the steps of obtaining the position of an unknown node according to the air quality index of the position of the unknown node, arranging a plurality of sensor nodes according to the position, obtaining the actual air quality index of the position of the unknown node, storing the actual air quality index into a preset database, and constructing a training set and a testing set according to the preset database.
In step S5, the predicted air quality indexes of the plurality of node positions in the preset database and the actual air quality indexes of the plurality of corresponding node positions are read to construct a training set and a testing set.
In step S6, training the model based on the deep learning recurrent neural network by using the training set to obtain an air quality index correction model based on the deep learning recurrent neural network.
Further, in one embodiment of the present invention, step S6 specifically includes:
step S601, inputting predicted air quality indexes of a plurality of node positions in a training set into a hidden layer based on a deep learning cyclic neural network model to obtain a predicted result;
step S602, comparing the prediction result with actual air quality indexes of a plurality of node positions in a training set to obtain an error value;
and step S603, the error value is sent back to a hidden layer based on the deep learning cyclic neural network model through a back propagation method, and parameters based on the deep learning cyclic neural network model are adjusted and optimized through an Adam algorithm, so that an air quality index correction model based on the deep learning cyclic neural network is obtained.
Specifically, reading a sample point prediction AQI historical value and an AQI historical value of actual observation of a point position according to a collaborative Kriging interpolation algorithm from a preset database;
as shown in fig. 2, sample point prediction AQI data obtained by a covelline interpolation algorithm is input into each LSTM node, a plurality of LSTM cell units are used for cyclic connection in an intermediate hidden layer, the obtained prediction result is compared with an actual historical air index value, an error value is obtained, the error value is sent back to the LSTM hidden layer unit by a back propagation method, and parameters are continuously adjusted by an Adam algorithm to optimize the prediction result. The mathematical formula of the loss function is as follows:
where D is the number of samples in the test set,for the true value of the air quality index at that point in time,/->Is an air quality index predicted value.
Further, step S6 may further include:
step S604, inputting the predicted air quality indexes of the plurality of node positions in the test set into an air quality index correction model based on the deep learning cyclic neural network to obtain corrected predicted air quality indexes of the plurality of node positions, and comparing and verifying the corrected predicted air quality indexes of the plurality of node positions with actual air quality indexes of the plurality of node positions.
In step S7, the predicted air quality index of the unknown node position to be corrected is input into an air quality index correction model based on the deep learning cyclic neural network, an actual air quality index of the unknown node position is obtained, and an air quality report is established according to the actual air quality index of the unknown node position.
The air quality report can be issued and inquired in real time, so that the air quality condition and the like of the current rural area can be judged.
According to the air quality assessment method based on the combination of the intelligent Internet of things and the deep learning, which is provided by the embodiment of the invention, real-time data acquisition is performed based on the intelligent urban and rural Internet of things data acquisition platform, the air quality of the whole domain is estimated and assessed by adopting a deep learning cyclic neural network in a multi-dimensional modeling way aiming at the duty ratio weights of pollutants in different stages and different periods, and a scientific and standardized air quality assessment report of time and space density under high precision is provided for the region.
The air quality evaluation system based on the combination of intelligent Internet of things and deep learning, which is provided by the embodiment of the invention, is described with reference to the accompanying drawings.
Fig. 3 is a schematic structural diagram of an air quality assessment system based on combination of intelligent internet of things and deep learning according to an embodiment of the present invention.
As shown in fig. 3, the apparatus 10 includes: the system comprises an acquisition module 100, a first processing module 200, a second processing module 300, an arrangement module 400, a construction module 500, a training module 600 and a correction module 700.
The collection module 100 is configured to arrange a plurality of sensor nodes according to a preset requirement, so as to collect a plurality of pollution factors, wind speed and wind direction in real time as monitoring data.
The first processing module 200 is configured to process the monitoring data through the concentration limit value reference table of the air pollution index and the air index score value, obtain the air index score value of any node position, and store the air index score value in a preset database.
In one embodiment of the present invention, the first processing module 200 is specifically configured to:
processing the monitoring data through a concentration limit value reference table and an air index score value of the air pollution index to obtain the air index score value of each air pollution factor;
comparing the air index score value of each air pollution factor, screening out the maximum air index score value, taking the maximum air index score value as the air index score value of any node position, and storing the air index score value into a preset database
And processing the air index score value of any node by adopting a collaborative kriging interpolation calculation method to calculate the predicted air quality index of the unknown node position, and storing the predicted air quality index in a preset database.
The second processing module 300 is configured to process the air index score value of any node by using a collaborative kriging interpolation calculation method, so as to calculate a predicted air quality index of the unknown node position, and store the predicted air quality index in a preset database.
In one embodiment of the present invention, the second processing module 300 is specifically configured to:
introducing the topography and wind direction into a collaborative kriging interpolation algorithm to obtain a collaborative half variation function;
fitting the covariance function to obtain a weight coefficient, processing the air index score value of any node position according to the weight coefficient to solve the air quality index of the unknown node position, and sending the air quality index to a preset database.
The arrangement module 400 is configured to rearrange a plurality of sensor nodes according to the air quality index of the unknown node position, obtain an actual air quality index of the unknown node position, and store the actual air quality index in a preset database.
The construction module 500 is configured to read the predicted air quality indexes of the plurality of node positions in the preset database and the actual air quality indexes of the plurality of corresponding node positions, so as to construct a training set and a testing set.
The training module 600 is configured to train the model based on the deep learning recurrent neural network by using the training set, and obtain an air quality index correction model based on the deep learning recurrent neural network.
In one embodiment of the present invention, the training module 600 is specifically configured to:
inputting the predicted air quality indexes of a plurality of node positions in the training set into a hidden layer based on the deep learning cyclic neural network model to obtain a predicted result;
comparing the prediction result with actual air quality indexes of a plurality of node positions in the training set to obtain an error value;
and sending the error value back to a hidden layer based on the deep learning cyclic neural network model through a back propagation method, and adjusting and optimizing parameters based on the deep learning cyclic neural network model through an Adam algorithm to obtain an air quality index correction model based on the deep learning cyclic neural network.
The correction module 700 is configured to input a predicted air quality index of an unknown node position to be corrected into an air quality index correction model based on a deep learning cyclic neural network, obtain an actual air quality index of the unknown node position, and establish an air quality report according to the actual air quality index of the unknown node position.
It should be noted that, the foregoing explanation of the embodiment of the air quality assessment method based on the combination of the intelligent internet of things and the deep learning is also applicable to the air quality assessment system based on the combination of the intelligent internet of things and the deep learning of the embodiment, which is not repeated herein.
According to the air quality assessment system based on the combination of the intelligent Internet of things and the deep learning, which is provided by the embodiment of the invention, real-time data acquisition is performed based on the intelligent urban and rural Internet of things data acquisition platform, the air quality of the whole domain is estimated and assessed by adopting a deep learning cyclic neural network in a multi-dimensional modeling way aiming at the duty ratio weights of pollutants in different stages and different periods, and a scientific and standardized air quality assessment report of time and space density under high precision is provided for the region.
In order to achieve the above embodiments, the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the air quality assessment method based on the combination of intelligent internet of things and deep learning according to the foregoing embodiments when executing the computer program.
In order to achieve the above embodiments, the present invention further proposes a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements an air quality assessment method based on a combination of intelligent internet of things and deep learning as described in the previous embodiments.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (8)
1. An air quality assessment method based on combination of intelligent Internet of things and deep learning is characterized by comprising the following steps:
step S1, arranging a plurality of sensor nodes according to preset requirements, and acquiring a plurality of pollution factors, wind speeds and wind directions in real time as monitoring data;
s2, processing the monitoring data through a concentration limit value reference table of the air pollution index and an air index score calculation formula to obtain an air index score index of any node position, and storing the air index score index into a preset database;
step S3, processing the air index of any node position by adopting a collaborative kriging interpolation calculation method to calculate a predicted air quality index of an unknown node position, and storing the predicted air quality index into the preset database, wherein the method specifically comprises the following steps:
step S301, introducing the topography and wind direction into a collaborative Kriging interpolation algorithm to obtain a collaborative half variation function;
step S302, fitting the covariance function to calculate a weight coefficient, processing the air index of any node position according to the weight coefficient to solve the predicted air quality index of the unknown node position, and sending the predicted air quality index to a preset database;
s4, a plurality of sensor nodes are arranged according to the predicted air quality index of the unknown node position, the actual air quality index of the unknown node position is obtained, and the actual air quality index is stored in the preset database;
s5, reading the predicted air quality indexes of a plurality of node positions in the preset database and the actual air quality indexes of the corresponding plurality of node positions to construct a training set and a testing set;
step S6, training the model based on the deep learning cyclic neural network by utilizing the training set to obtain an air quality index correction model based on the deep learning cyclic neural network, and specifically comprises the following steps:
step S601, inputting predicted air quality indexes of a plurality of node positions in the training set into a hidden layer based on a deep learning cyclic neural network model to obtain a predicted result;
step S602, comparing the prediction result with actual air quality indexes of a plurality of node positions in the training set to obtain an error value;
step S603, the error value is sent back to a hidden layer based on a deep learning cyclic neural network model through a back propagation method, and parameters based on the deep learning cyclic neural network model are adjusted and optimized through an Adam algorithm, so that an air quality index correction model based on the deep learning cyclic neural network is obtained;
and S7, inputting the predicted air quality index of the unknown node position to be corrected into the air quality index correction model based on the deep learning cyclic neural network to obtain the actual air quality index of the unknown node position, and establishing an air quality report according to the actual air quality index of the unknown node position.
2. The air quality assessment method based on the combination of intelligent internet of things and deep learning according to claim 1, wherein the step S2 specifically includes:
step S201, processing the monitoring data through a concentration limit value reference table and an air index calculation formula of the air pollution index to obtain an air index of each air pollution factor;
step S202, comparing the air index of each air pollution factor, screening out the maximum air index, and taking the maximum air index score as the air index score of any node position, and storing the maximum air index score into a preset database.
3. The air quality assessment method based on combination of intelligent internet of things and deep learning according to claim 1, wherein the fitting collaborative semi-variation function is:
wherein ,for the covariant function, ++>Is made of->Number of separated paired sample spots, +.>For sample spots +.>For the distance between two points>Property value of the point with respect to the wind direction variable +.>Is the attribute value of the point with respect to the topography variable.
4. The air quality assessment method based on combination of intelligent internet of things and deep learning according to claim 1, wherein the predicted air quality index of the unknown node position is:
wherein ,predicted air quality index for unknown node position, +.>For the sample node +.>Sample node number for wind direction variable, +.>Weight pending for wind direction variable, +.>Property value for wind direction variable, +.>Sample node number for the relief variable, +.>Weight pending for the topography variable, +.>Is the attribute value of the relief variable.
5. The air quality assessment method based on the combination of intelligent internet of things and deep learning according to claim 1, wherein step S6 further comprises:
step S604, inputting the predicted air quality indexes of the plurality of node positions in the test set into the air quality index correction model based on the deep learning cyclic neural network, obtaining corrected predicted air quality indexes of the plurality of node positions, and comparing and verifying the corrected predicted air quality indexes of the plurality of node positions with the actual air quality indexes of the plurality of node positions.
6. Air quality evaluation system based on intelligent thing networking and degree of depth study combine together, characterized by comprising:
the acquisition module is used for arranging a plurality of sensor nodes according to preset requirements so as to acquire a plurality of pollution factors, wind speeds and wind directions in real time as monitoring data;
the first processing module is used for processing the monitoring data through a concentration limit value reference table of the air pollution index and an air index score index calculation formula to obtain an air index score index of any node position, and storing the air index score index into a preset database;
the second processing module is used for processing the air index of any node position by adopting a collaborative kriging interpolation calculation method so as to calculate a predicted air quality index of an unknown node position and storing the predicted air quality index into the preset database, and the second processing module is specifically used for:
introducing the topography and wind direction into a collaborative kriging interpolation algorithm to obtain a collaborative half variation function;
fitting the cooperative half variation function to calculate a weight coefficient, processing the air index of any node position according to the weight coefficient to solve the predicted air quality index of the unknown node position, and sending the predicted air quality index to a preset database;
the arrangement module is used for arranging a plurality of sensor nodes according to the predicted air quality index of the unknown node position, obtaining the actual air quality index of the unknown node position and storing the actual air quality index into the preset database;
the construction module is used for reading the predicted air quality indexes of the plurality of node positions in the preset database and the actual air quality indexes of the plurality of corresponding node positions so as to construct a training set and a testing set;
the training module is used for training the deep learning cyclic neural network model by utilizing the training set to obtain an air quality index correction model based on the deep learning cyclic neural network, and is specifically used for:
inputting the predicted air quality indexes of a plurality of node positions in the training set into a hidden layer based on a deep learning cyclic neural network model to obtain a predicted result;
comparing the prediction result with actual air quality indexes of a plurality of node positions in the training set to obtain an error value;
the error value is sent back to a hidden layer based on the deep learning cyclic neural network model through a back propagation method, parameters based on the deep learning cyclic neural network model are adjusted and optimized through an Adam algorithm, and an air quality index correction model based on the deep learning cyclic neural network is obtained;
the correction module is used for inputting the predicted air quality index of the unknown node position to be corrected into the air quality index correction model based on the deep learning cyclic neural network, obtaining the actual air quality index of the unknown node position, and establishing an air quality report according to the actual air quality index of the unknown node position.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the air quality assessment method according to any one of claims 1-5 based on a combination of intelligent internet of things and deep learning when executing the computer program.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the air quality assessment method based on a combination of intelligent internet of things and deep learning as claimed in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705453.3A CN116448966B (en) | 2023-06-15 | 2023-06-15 | Air quality assessment method based on combination of intelligent Internet of things and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705453.3A CN116448966B (en) | 2023-06-15 | 2023-06-15 | Air quality assessment method based on combination of intelligent Internet of things and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116448966A CN116448966A (en) | 2023-07-18 |
| CN116448966B true CN116448966B (en) | 2023-09-12 |
Family
ID=87130561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310705453.3A Active CN116448966B (en) | 2023-06-15 | 2023-06-15 | Air quality assessment method based on combination of intelligent Internet of things and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116448966B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537383A (en) * | 2018-04-09 | 2018-09-14 | 山东建筑大学 | A kind of room air prediction technique based on Model Fusion |
| CN109710598A (en) * | 2018-12-14 | 2019-05-03 | 吉林省中农阳光数据有限公司 | A kind of Meteorological Index insurance system and its implementation based on crops |
| CN109753631A (en) * | 2018-12-04 | 2019-05-14 | 西北工业大学 | It is a kind of that algorithm is speculated based on the air quality of Active Learning and Kriging regression |
| CN110346420A (en) * | 2019-06-09 | 2019-10-18 | 重庆工商大学融智学院 | A kind of space-time data intelligence polymerization |
| CN111798051A (en) * | 2020-07-02 | 2020-10-20 | 杭州电子科技大学 | Air quality space-time prediction method based on long-short term memory neural network |
| CN113486000A (en) * | 2021-09-08 | 2021-10-08 | 中国测绘科学研究院 | Surface evapotranspiration data downscaling method based on multi-source data and deep learning |
| US11143641B1 (en) * | 2021-04-05 | 2021-10-12 | Vivante Health, Inc. | Gas sensor calibration method |
| KR102387630B1 (en) * | 2020-11-19 | 2022-04-25 | (주)비트버스 | Qality Monitoring System |
| CN114444561A (en) * | 2021-08-23 | 2022-05-06 | 感知集团有限公司 | PM2.5 prediction method based on CNNs-GRU fusion deep learning model |
| CN114595639A (en) * | 2022-03-29 | 2022-06-07 | 太原则成信息技术有限公司 | Atmospheric pollutant diffusion numerical simulation method based on deep learning |
| CN114676822A (en) * | 2022-03-25 | 2022-06-28 | 东南大学 | Multi-attribute fusion air quality forecasting method based on deep learning |
| CN114819289A (en) * | 2022-04-01 | 2022-07-29 | 桂林电子科技大学 | Prediction method, training method, device, electronic device and storage medium |
| CN115730684A (en) * | 2022-12-09 | 2023-03-03 | 安徽大学 | Air quality detection system based on LSTM-CNN model |
| CN116011317A (en) * | 2022-11-29 | 2023-04-25 | 北京工业大学 | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion |
| CN116205748A (en) * | 2023-05-06 | 2023-06-02 | 吉林省中农阳光数据有限公司 | Intelligent Internet of things-based precise damage assessment method and device for cultivation insurance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766549A (en) * | 2021-01-07 | 2021-05-07 | 清华大学 | Air pollutant concentration forecasting method and device and storage medium |
-
2023
- 2023-06-15 CN CN202310705453.3A patent/CN116448966B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537383A (en) * | 2018-04-09 | 2018-09-14 | 山东建筑大学 | A kind of room air prediction technique based on Model Fusion |
| CN109753631A (en) * | 2018-12-04 | 2019-05-14 | 西北工业大学 | It is a kind of that algorithm is speculated based on the air quality of Active Learning and Kriging regression |
| CN109710598A (en) * | 2018-12-14 | 2019-05-03 | 吉林省中农阳光数据有限公司 | A kind of Meteorological Index insurance system and its implementation based on crops |
| CN110346420A (en) * | 2019-06-09 | 2019-10-18 | 重庆工商大学融智学院 | A kind of space-time data intelligence polymerization |
| CN111798051A (en) * | 2020-07-02 | 2020-10-20 | 杭州电子科技大学 | Air quality space-time prediction method based on long-short term memory neural network |
| KR102387630B1 (en) * | 2020-11-19 | 2022-04-25 | (주)비트버스 | Qality Monitoring System |
| US11143641B1 (en) * | 2021-04-05 | 2021-10-12 | Vivante Health, Inc. | Gas sensor calibration method |
| CN114444561A (en) * | 2021-08-23 | 2022-05-06 | 感知集团有限公司 | PM2.5 prediction method based on CNNs-GRU fusion deep learning model |
| CN113486000A (en) * | 2021-09-08 | 2021-10-08 | 中国测绘科学研究院 | Surface evapotranspiration data downscaling method based on multi-source data and deep learning |
| CN114676822A (en) * | 2022-03-25 | 2022-06-28 | 东南大学 | Multi-attribute fusion air quality forecasting method based on deep learning |
| CN114595639A (en) * | 2022-03-29 | 2022-06-07 | 太原则成信息技术有限公司 | Atmospheric pollutant diffusion numerical simulation method based on deep learning |
| CN114819289A (en) * | 2022-04-01 | 2022-07-29 | 桂林电子科技大学 | Prediction method, training method, device, electronic device and storage medium |
| CN116011317A (en) * | 2022-11-29 | 2023-04-25 | 北京工业大学 | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion |
| CN115730684A (en) * | 2022-12-09 | 2023-03-03 | 安徽大学 | Air quality detection system based on LSTM-CNN model |
| CN116205748A (en) * | 2023-05-06 | 2023-06-02 | 吉林省中农阳光数据有限公司 | Intelligent Internet of things-based precise damage assessment method and device for cultivation insurance |
Non-Patent Citations (1)
| Title |
|---|
| 基于BP神经网络的西安环境空气质量的预测;闫妍;张云鹏;李铠月;杨光美;;电子设计工程(21);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116448966A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | Ecomark 2.0: empowering eco-routing with vehicular environmental models and actual vehicle fuel consumption data | |
| CN110887790B (en) | Urban lake eutrophication simulation method and system based on FVCOM and remote sensing inversion | |
| Heine et al. | Development and comparison of approaches for automated mapping of stream channel networks | |
| CN110009037B (en) | Short-term engineering wind speed prediction method and system based on physical information coupling | |
| CN108571978A (en) | Discharge beyond standards vehicle shortest path tracking and matching method based on topology and weight | |
| KR101900777B1 (en) | Server for city enviromental analysis, and control method thereof | |
| CN109978275B (en) | Extreme strong wind speed prediction method and system based on mixed CFD and deep learning | |
| JP2021518528A (en) | Sensor calibration | |
| Schröter et al. | Estimation of catchment-scale soil moisture patterns based on terrain data and sparse TDR measurements using a fuzzy C-means clustering approach | |
| CN115342814B (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN112084672A (en) | Method for judging groundwater pollution based on fractal dimension | |
| CN113189014A (en) | Ozone concentration estimation method fusing satellite remote sensing and ground monitoring data | |
| CN114781576B (en) | Sound velocity profile estimation method and device based on random forest algorithm | |
| Acevedo et al. | New developments in the study of species distribution | |
| CN113051653A (en) | Urban planning road construction evaluation management system based on multi-dimensional data analysis | |
| CN116448966B (en) | Air quality assessment method based on combination of intelligent Internet of things and deep learning | |
| Barbaresi et al. | A method for the validation of measurements collected by different monitoring systems applied to aquaculture processing plants | |
| Carrier et al. | Climate models: How to assess their reliability | |
| CN112650740B (en) | Method and system for reducing uncertainty of online monitoring carbon emission data | |
| De Vos et al. | Accurate Measurements of Forest Soil Water Content Using FDR Sensors Require Empirical In Situ (Re) Calibration | |
| CN112836789A (en) | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm | |
| CN116626238A (en) | Dual-channel detection compass system for sensing air flow and air combination, air leakage detection method, data fusion and tracking method | |
| CN114814135B (en) | River water quality pollution tracing method and system based on multivariate monitoring | |
| CN115907204A (en) | Forest transpiration water consumption prediction method for optimizing BP neural network by sparrow search algorithm | |
| CN113868223A (en) | Water quality monitoring method, device and system and readable storage medium |
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 |