CN115656446A - Air quality detection system and method based on Internet of things - Google Patents
Air quality detection system and method based on Internet of things Download PDFInfo
- Publication number
- CN115656446A CN115656446A CN202211670249.4A CN202211670249A CN115656446A CN 115656446 A CN115656446 A CN 115656446A CN 202211670249 A CN202211670249 A CN 202211670249A CN 115656446 A CN115656446 A CN 115656446A
- Authority
- CN
- China
- Prior art keywords
- air quality
- data
- quality detection
- detection area
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an air quality detection system and method based on the Internet of things, and belongs to the technical field of air quality detection. The system comprises an air quality detection area module, a data training module, an air quality change trend module and an early warning module; the output end of the air quality detection area module is connected with the input end of the data training module; the output end of the data training module is connected with the input end of the air quality variation trend module; the output end of the air quality change trend module is connected with the input end of the early warning module. In the invention, the influence degree of different regional environment factors on air quality detection is considered, and when a historical data set is selected for training, the historical data closest to the current regional environment is obtained by multiple screening, so that the air quality control effect is improved.
Description
Technical Field
The invention relates to the technical field of air quality detection, in particular to an air quality detection system and method based on the Internet of things.
Background
The air quality detection means detecting whether the air quality is good or not. The quality of the air reflects the concentration of pollutants in the air. Air pollution is a complex phenomenon, and the concentration of air pollutants at a particular time and place is influenced by many factors. The size of the emission of man-made pollutants from stationary and mobile sources is one of the most important factors affecting air quality, including exhaust gases from vehicles, ships, airplanes, industrial production emissions, residential and heating, waste incineration, etc. The development density of cities, landforms, weather and the like are also important factors influencing the air quality. However, in the current technical means, when the change of the air quality is predicted according to the air quality detection, the historical data in the same area is often adopted to perform the next estimation, but the continuous change of the environment causes the deviation of the historical data in the same area to be large, so that the accuracy of the prediction result is poor.
Disclosure of Invention
The invention aims to provide an air quality detection system and method based on the Internet of things, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an air quality detection method based on the Internet of things comprises the following steps:
s1, constructing an air quality detection area, acquiring environmental data in the air quality detection area, and outputting environmental influence factors of the current air quality detection area;
s2, constructing a historical database, wherein the historical database comprises air quality detection data and air pollution prevention data, constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model;
s3, setting a time period, acquiring real-time acquired data of the current air quality detection area under the time period, and outputting an air quality change trend curve according to a prediction data model;
and S4, establishing air pollution prevention threshold duration according to historical air pollution prevention data, updating the air pollution prevention threshold duration of the current air quality detection area according to the output air quality change trend curve, and giving an early warning prompt when the time point of reaching the air pollution prevention threshold is judged.
According to the technical scheme, the environmental data in the air quality detection area comprise area environmental landform characteristics, area building characteristics and area personnel density indexes;
the regional environmental landform characteristics comprise macroscopic landforms in an air quality detection region, such as multiple plateaus in basins and hills, are beneficial to agricultural lands, and often cause serious atmospheric pollution due to straw combustion and the like; the regional building characteristics include the industrial facilities in the current air quality detection region, and since the region is under constant development and planning, for example, some heavy industrial factory bases may not exist for several years ago, the obvious data bias of the prior historical data is excessive; the regional personnel density index comprises the living density of human beings in a region, and a high-density personnel region can cause a large amount of living pollution of personnel, similar to automobile exhaust emission and the like;
the output of the environmental influence factors of the current air quality detection area comprises respectively outputting the regional environmental landform characteristics, the regional building characteristics and the regional personnel density indexes of the current air quality detection area, wherein the regional environmental landform characteristics comprise regional environmental characteristics with natural landform influence, such as volcano, sand storm and the like, and regional environmental characteristics with artificial influence, such as straw burning and the like, and influence coefficients are respectively set
(ii) a Setting each corresponding regional environment characteristic, recording a numerical group value A, and generating a regional environment landform characteristic value of the current air quality detection region:
wherein the content of the first and second substances,
representing the regional environment landform characteristic value of the current air quality detection region;
respectively representing the quantity of regional environmental characteristics with natural landform influence and the quantity of regional environmental characteristics with artificial influence; taking the quantity value of industrial buildings in the regional buildings according to the regional building characteristics; the regional personnel density index calls a regional permanent population density index;
and carrying out normalization processing on data output by regional environment landform characteristics, regional building characteristics and regional personnel density indexes of the current air quality detection region.
According to the above technical solution, the constructing a data processing model includes:
randomly selecting values of N groups of data subjected to normalization processing from a historical database to serve as initial particle solutions, wherein each particle solution has a random position and speed;
constructing a fitness model of a particle solution
：
Wherein, the first and the second end of the pipe are connected with each other,
、
、
respectively representing the features of regional environment landformThe fitness influence coefficients of the regional building characteristics and the regional personnel density index;
、
、
respectively representing the normalized values of the ith group of data in the selected N groups of data, wherein i is more than or equal to 1 and less than or equal to N;
、
、
respectively representing the normalized values of the data in the current air quality detection area;
selecting
The minimum value is used as the optimal position G of the particle solution, all the particle solutions approach to the optimal position G and are recorded as the first iteration, and the motion equation of the approach is as follows:
wherein the content of the first and second substances,
representing the moving velocity vector corresponding to the random particle solution of the ith group of data at the c time, and setting a velocity maximum value
If, if
＞
Then get
；
Representing a position vector corresponding to a random particle solution of the ith group of data under the c time;
represents between
A random number in between;
represents the optimal position where the random particle solution of the ith group of data at the c-th time passes, P = G in the first iteration; g represents the optimal position among the positions traversed by all particle solutions, in the first iteration, i.e.
Minimum value of (d);
representing a learning factor;
represents an inertia factor, and is a non-negative value;
in the above steps, under the second iteration, P and G will change, where P is the optimal position of the particle solution itself in two times, and G is the minimum value of the fitness of all the particle solutions in two times, and so on, and the iteration is continued;
setting an iteration time threshold, acquiring a particle solution closest to the optimal position G when the iteration time meets the threshold, taking the particle solution as a unique output, selecting corresponding historical data as high-priority historical air quality detection data, sending the residual historical data back to a historical database, and performing random selection training again;
the system sets a quantity value of the historical data group which needs to participate in training, and stops data acquisition when the quantity of the high-priority historical air quality detection data meets the quantity value of the historical data group which participates in training.
According to the technical scheme, the selected high-priority historical air quality detection data are obtained, the corresponding latest air pollution prevention and control time points under the subsequent time are collected, the calculation interval time is long, and the calculation interval time is recorded as the following data set
Wherein
Respectively representing the interval time of n groups of data, wherein n represents the quantity value of the historical data group needing to participate in training;
performing gray accumulation generation processing on the data in the set U to generate a set U 1 ：
To set U 1 Performing weighted neighbor calculation on the middle data to generate a set U 2 ：
Constructing a set U 1 The whitening differential equation of (a) is:
wherein, the first and the second end of the pipe are connected with each other,
to develop ash;
controlling ash number for endogenesis;
representative set U 1 Any one of the data;
constructing a parameter vector to be estimated according to the sets U and U 1 、U 2 Writing the data into a matrix, and calculating by using a least square method, wherein the parameter vector to be estimated represents the ratio of the developed ash number to the endogenous control ash number;
and (3) constructing model output:
wherein the content of the first and second substances,
and representing the final output solution of the prediction data model, and taking the final output solution as the prediction duration of the distance pollution control of the current air quality detection area.
According to the technical scheme, a time period is set, R time points are selected under the time period, real-time acquisition data of a current air quality detection area under the R time points are obtained, the prediction duration of distance pollution prevention and control of the current air quality detection area under the R time points is output according to a prediction data model, and after the prediction duration is truly processed, a prediction curve is constructed and serves as an air quality change trend curve;
the real processing means adding the generated predicted time length of the distance pollution control to the time length between each time point and the initial time point in the calculation process;
setting a curve slope threshold value, and collecting the number I of points of an air quality change trend curve exceeding the curve slope threshold value;
according to historical air pollution prevention and control data, establishing an air pollution prevention and control threshold duration Y, and according to an output air quality change trend curve, establishing an air pollution prevention and control threshold duration of a current air quality detection area:
wherein, the first and the second end of the pipe are connected with each other,
representing the air pollution control threshold duration of the current air quality detection area;
represents an influencing factor;
and when the time reaches the air pollution prevention threshold of the current air quality detection area, giving an early warning prompt.
An air quality detection system based on the Internet of things comprises an air quality detection area module, a data training module, an air quality change trend module and an early warning module; the air quality detection area module is used for constructing an air quality detection area, acquiring environmental data in the air quality detection area and outputting environmental influence factors of the current air quality detection area; the data training module is used for constructing a historical database, the historical database comprises air quality detection data and air pollution prevention data, constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model; the air quality change trend module is used for setting a time period, acquiring real-time acquired data of a current air quality detection area under the time period, and outputting an air quality change trend curve according to the prediction data model; the early warning module is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data, updating the air pollution prevention threshold duration of the current air quality detection area according to an output air quality change trend curve, and giving early warning prompts when judging time points of reaching the air pollution prevention threshold;
and the air quality detection area module utilizes multiple sensors and radars to identify and analyze landforms and buildings, establishes connection between the identified data and the system host, and stores the data received by the system host into a database.
The output end of the air quality detection area module is connected with the input end of the data training module; the output end of the data training module is connected with the input end of the air quality change trend module; and the output end of the air quality change trend module is connected with the input end of the early warning module.
According to the technical scheme, the air quality detection area module comprises an area construction unit and an environment acquisition unit;
the area construction unit is used for constructing an air quality detection area; the environment acquisition unit is used for acquiring environment data in the air quality detection area and outputting environmental influence factors of the current air quality detection area;
and the output end of the area construction unit is connected with the input end of the environment acquisition unit.
According to the technical scheme, the data training module comprises a historical database unit and a data training unit;
the historical database unit is used for constructing a historical database and storing air quality detection data and air pollution prevention and control data; the data training unit is used for constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model;
and the output end of the historical database unit is connected with the input end of the data training unit.
According to the technical scheme, the air quality change trend module comprises a time point analysis unit and a curve analysis unit;
the time point analysis unit is used for setting a time period, dividing the time period into R time points and acquiring real-time acquisition data of the current air quality detection area in the R time points under the time period; the curve analysis unit is used for constructing an air quality change trend curve according to data output by the prediction data model; wherein R is a system setting constant;
the output end of the time point analysis unit is connected with the input end of the curve analysis unit.
The early warning module comprises a threshold updating unit and an early warning unit;
the threshold updating unit is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data and updating the air pollution prevention threshold duration of the current air quality detection area according to the output air quality change trend curve; and the early warning unit gives an early warning prompt when judging that the time point of the air pollution prevention threshold is reached.
Compared with the prior art, the invention has the following beneficial effects:
in the invention, the influence degree of different regional environment factors on air quality detection is considered, and when a historical data set is selected for training, the historical data closest to the current regional environment is obtained by multiple screening, so that the air quality control effect is improved. Meanwhile, corresponding curve slope discrimination points are added in the direction of the air prevention threshold, and when the curve has a large number of points of change, the uncertainty of the change of the ambient air quality in the current area can be known, so that the further updating and the discrimination of the threshold can be realized, and the air quality prevention is enhanced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow diagram of an air quality detection system and method based on the internet of things.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, in the first embodiment: provides an air quality detection method based on the Internet of things,
constructing an air quality detection area according to system requirements, acquiring environmental data in the air quality detection area, and outputting environmental influence factors of the current air quality detection area;
the environmental data in the air quality detection area comprise area environmental landform characteristics, area building characteristics and area personnel density indexes;
outputting the environmental influence factors of the current air quality detection area comprises respectively outputting the regional environmental landform characteristics, the regional building characteristics and the regional personnel density index of the current air quality detection area, wherein the regional environmental landform characteristics comprise regional environmental characteristics influenced by natural landform, such as volcano, sand, wind and sand, and regional environmental characteristics influenced by human, such as straw burning, and the like, and influence coefficients are respectively set
(ii) a Setting each corresponding area environment characteristic, recording an array value A, and generating an area environment landform characteristic value of the current air quality detection area:
wherein the content of the first and second substances,
representing the regional environmental landform characteristic value of the current air quality detection region;
respectively representing the quantity of regional environmental features with natural landform influence and the quantity of regional environmental features with artificial influence; for example, if volcano and sand exist in a certain area, it is recorded
=2；
Taking the quantity value of industrial buildings in the regional buildings according to the regional building characteristics; the regional personnel density index calls a permanent population density index in the region;
and carrying out normalization processing on data output by regional environment landform characteristics, regional building characteristics and regional personnel density indexes of the current air quality detection region.
Establishing a historical database, wherein the historical database comprises air quality detection data and air pollution prevention and control data, establishing a data processing model, and selecting high-priority historical air quality detection data to establish a prediction data model;
the constructing of the data processing model comprises:
randomly selecting a value of N groups of data subjected to normalization processing from a historical database as an initial particle solution, wherein each particle solution has a random position and speed;
fitness model for constructing particle solution
：
Wherein the content of the first and second substances,
、
、
respectively representing the fitness influence coefficients of the regional environment landform characteristics, the regional building characteristics and the regional personnel density index;
、
、
respectively representing the ith group of data of the selected N groups of dataNormalizing the value after treatment, i is more than or equal to 1 and less than or equal to N;
、
、
respectively representing the normalized values of the data in the current air quality detection area;
selecting
The minimum value is used as the optimal position G of the particle solution, all the particle solutions approach to the optimal position G and are recorded as the first iteration, and the motion equation of the approach is as follows:
wherein the content of the first and second substances,
a moving velocity vector corresponding to the solution of random particles representing the ith group of data at the c-th time is set with a velocity maximum value
If, if
＞
Then get
；
Representing a position vector corresponding to a random particle solution of the ith group of data at the c time;
represents between
A random number in between;
represents the optimal position where the random particle solution of the ith group of data at the c-th time passes, in the first iteration, P = G; g represents the optimal position among the positions traversed by all particle solutions, in the first iteration, i.e.
The minimum value of (d);
、
represents a learning factor;
represents an inertia factor, and is a non-negative value;
in the above steps, under the second iteration, P and G will change, where P is the optimal position of the particle solution itself in two times, and G is the minimum value of the fitness of all the particle solutions in two times, and so on, and the iteration is continued;
setting an iteration time threshold, when the iteration time meets the threshold, acquiring a particle solution closest to the optimal position G as a unique output, selecting corresponding historical data as high-priority historical air quality detection data, sending the remaining historical data back to a historical database, and performing random selection training again;
the system sets a quantity value of the historical data group which needs to participate in training, and stops data acquisition when the quantity of the high-priority historical air quality detection data meets the quantity value of the historical data group which participates in training.
Acquiring selected high-priority historical air quality detection data, acquiring corresponding nearest air pollution control time points at the subsequent time, calculating the time interval, and recording as a data set
In which
Respectively representing the interval time of n groups of data, wherein n represents the quantity value of the historical data group needing to participate in training;
performing gray accumulation generation processing on the data in the set U to generate a set U 1 ：
The gray accumulation generation includes:
wherein the content of the first and second substances,
representative set U 1 The b-th data of (1);
represents a serial number;
for example,
=
then there is U 1 =
For set U 1 The middle data is subjected to weighted neighbor value calculation to generate a set U 2 ：
The weighted neighbor computation includes:
wherein the content of the first and second substances,
representative set U 2 To (1)
A piece of data;
representing the weight ratio;
；
representative set U 1 To middle
A piece of data;
for example, in the case of a liquid,
representing the weight ratio, and taking 0.5; then the above-mentioned U 1 After treatment, the method comprises the following steps:
constructing a set U 1 The whitening differential equation of (a) is:
wherein the content of the first and second substances,
to develop ash;
controlling ash number for endogenesis;
representative set U 1 Any one of the data;
constructing a parameter vector to be estimated according to the sets U and U 1 、U 2 Writing the data into a matrix, and calculating by using a least square method, wherein the parameter vector to be estimated represents the ratio of the developed ash number to the endogenous control ash number;
and (3) constructing a model and outputting:
wherein the content of the first and second substances,
and representing the final output solution of the prediction data model, and taking the final output solution as the prediction duration of the distance pollution control of the current air quality detection area.
Setting a time period, selecting R time points under the time period, acquiring real-time acquisition data of a current air quality detection area under the R time points, outputting predicted time length of distance pollution prevention of the current air quality detection area under the R time points according to a predicted data model, and constructing a predicted curve after the predicted time length is really processed to be used as an air quality change trend curve;
the real processing means adding the generated prediction time length of the distance pollution control to the time length between each time point and the initial time point in the calculation process;
setting a curve slope threshold value, and collecting the number I of points, exceeding the curve slope threshold value, of an air quality change trend curve;
according to historical air pollution prevention and control data, establishing air pollution prevention and control threshold duration Y (duration generally takes about 30 days with the prevention time as the standard), and according to an output air quality change trend curve, establishing the air pollution prevention and control threshold duration of a current air quality detection area:
wherein the content of the first and second substances,
representing the air pollution control threshold duration of the current air quality detection area;
represents an influencing factor;
and when the time reaches the air pollution prevention threshold of the current air quality detection area, giving an early warning prompt.
In the second embodiment, an air quality detection system based on the internet of things is provided, and the system comprises an air quality detection area module, a data training module, an air quality change trend module and an early warning module; the air quality detection area module is used for constructing an air quality detection area, acquiring environmental data in the air quality detection area and outputting environmental influence factors of the current air quality detection area; the data training module is used for constructing a historical database, the historical database comprises air quality detection data and air pollution prevention and control data, constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model; the air quality change trend module is used for setting a time period, acquiring real-time acquired data of a current air quality detection area under the time period, and outputting an air quality change trend curve according to a prediction data model; the early warning module is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data, updating the air pollution prevention threshold duration of the current air quality detection area according to an output air quality change trend curve, and giving early warning prompts when judging time points of reaching the air pollution prevention threshold;
the output end of the air quality detection area module is connected with the input end of the data training module; the output end of the data training module is connected with the input end of the air quality change trend module; and the output end of the air quality change trend module is connected with the input end of the early warning module.
The air quality detection area module comprises an area construction unit and an environment acquisition unit;
the area construction unit is used for constructing an air quality detection area; the environment acquisition unit is used for acquiring environment data in the air quality detection area and outputting environmental influence factors of the current air quality detection area;
and the output end of the area construction unit is connected with the input end of the environment acquisition unit.
The data training module comprises a historical database unit and a data training unit;
the historical database unit is used for constructing a historical database and storing air quality detection data and air pollution prevention and control data; the data training unit is used for constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model;
and the output end of the historical database unit is connected with the input end of the data training unit.
The air quality change trend module comprises a time point analysis unit and a curve analysis unit;
the time point analysis unit is used for setting a time period, dividing the time period into R time points and acquiring real-time acquisition data of the current air quality detection area in the R time points under the time period; the curve analysis unit is used for constructing an air quality change trend curve according to data output by the prediction data model; wherein, R is a system setting constant;
the output end of the time point analysis unit is connected with the input end of the curve analysis unit.
The early warning module comprises a threshold updating unit and an early warning unit;
the threshold updating unit is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data and updating the air pollution prevention threshold duration of the current air quality detection area according to the output air quality change trend curve; and the early warning unit gives early warning prompt when judging that the time point of the air pollution prevention threshold is reached.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An air quality detection method based on the Internet of things is characterized in that: the method comprises the following steps:
s1, constructing an air quality detection area, acquiring environmental data in the air quality detection area, and outputting environmental influence factors of the current air quality detection area;
s2, constructing a historical database, wherein the historical database comprises air quality detection data and air pollution prevention data, constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model;
s3, setting a time period, acquiring real-time acquired data of a current air quality detection area under the time period, and outputting an air quality change trend curve according to a prediction data model;
and S4, establishing air pollution prevention threshold duration according to historical air pollution prevention data, updating the air pollution prevention threshold duration of the current air quality detection area according to the output air quality change trend curve, and giving an early warning prompt when the time point of reaching the air pollution prevention threshold is judged.
2. The air quality detection method based on the Internet of things according to claim 1, characterized in that: the environmental data in the air quality detection area comprise area environment landform characteristics, area building characteristics and area personnel density indexes;
outputting the environmental influence factors of the current air quality detection area comprises respectively outputting the regional environmental landform characteristics, the regional building characteristics and the regional personnel density index of the current air quality detection area, wherein the regional environmental landform characteristics comprise the regional environmental characteristics influenced by natural landforms and the regional environmental characteristics influenced by human beings, and influence coefficients are respectively set
(ii) a Setting each corresponding regional environment characteristic, recording a numerical group value A, and generating a regional environment landform characteristic value of the current air quality detection region:
wherein, the first and the second end of the pipe are connected with each other,
representing the regional environment landform characteristic value of the current air quality detection region;
respectively representing the quantity of regional environmental features with natural landform influence and the quantity of regional environmental features with artificial influence;
taking the quantity value of industrial buildings in the regional buildings according to the regional building characteristics; the regional personnel density index calls a regional permanent population density index;
and carrying out normalization processing on data output by regional environment landform characteristics, regional building characteristics and regional personnel density indexes of the current air quality detection region.
3. The air quality detection method based on the Internet of things as claimed in claim 2, wherein: the constructing of the data processing model comprises:
randomly selecting a value of N groups of data subjected to normalization processing from a historical database as an initial particle solution, wherein each particle solution has a random position and speed;
constructing a fitness model of a particle solution
：
Wherein the content of the first and second substances,
、
、
respectively representing the regionThe fitness influence coefficients of the regional environment landform characteristics, the regional building characteristics and the regional personnel density index;
、
、
respectively representing the normalized values of the ith group of data in the selected N groups of data, wherein i is more than or equal to 1 and less than or equal to N;
、
、
respectively representing the normalized values of the data in the current air quality detection area;
selecting
Taking the minimum value as the optimal position G of the particle solution, approaching all the particle solutions to the optimal position G, and recording as the first iteration, wherein the approaching motion equation:
wherein the content of the first and second substances,
representing the moving velocity vector corresponding to the random particle solution of the ith group of data at the c time, and setting a velocity maximum value
If at all
＞
Then get
；
Representing a position vector corresponding to a random particle solution of the ith group of data under the c time;
represents between
A random number in between;
represents the optimal position where the random particle solution of the ith group of data at the c-th time passes, in the first iteration, P = G; g represents the optimal position among the positions traversed by all the particle solutions, in the first iteration, i.e.
The minimum value of (d);
、
represents a learning factor;
represents an inertia factor, and is a non-negative value;
setting an iteration time threshold, acquiring a particle solution closest to the optimal position G when the iteration time meets the threshold, taking the particle solution as a unique output, selecting corresponding historical data as high-priority historical air quality detection data, sending the residual historical data back to a historical database, and performing random selection training again;
the system sets a historical data group quantity value which needs to participate in training, and stops data acquisition when the quantity of the high-priority historical air quality detection data meets the historical data group quantity value which participates in training.
4. The air quality detection method based on the Internet of things as claimed in claim 3, wherein: acquiring selected high-priority historical air quality detection data, acquiring corresponding recent air pollution control time points at the subsequent time of the selected high-priority historical air quality detection data, calculating the time interval, and recording the time interval as a data set
Wherein
Respectively representing the interval time of n groups of data, wherein n represents the number value of the historical data groups needing to participate in training;
performing gray accumulation generation processing on the data in the set U to generate a set U 1 ：
To set U 1 The middle data is subjected to weighted neighbor value calculation to generate a set U 2 ：
Constructing a set U 1 The whitening differential equation of (a) is:
wherein the content of the first and second substances,
to develop ash;
controlling ash number for endogenesis;
representative set U 1 Any one of the data;
constructing a parameter vector to be estimated according to the sets U and U 1 、U 2 The data of (2) is written into a matrix and calculated by utilizing a least square method, wherein the parameter vector to be estimated represents the ratio of the development ash number to the endogenous control ash number;
and (3) constructing a model and outputting:
wherein, the first and the second end of the pipe are connected with each other,
and representing the final output solution of the prediction data model, and taking the final output solution as the prediction duration of the distance pollution control of the current air quality detection area.
5. The air quality detection method based on the Internet of things as claimed in claim 4, wherein: setting a time period, selecting R time points under the time period, acquiring real-time acquisition data of a current air quality detection area under the R time points, outputting predicted time length of distance pollution prevention of the current air quality detection area under the R time points according to a predicted data model, and constructing a predicted curve after the predicted time length is really processed to be used as an air quality change trend curve;
the real processing means adding the generated predicted time length of the distance pollution control to the time length between each time point and the initial time point in the calculation process;
setting a curve slope threshold value, and collecting the number I of points, exceeding the curve slope threshold value, of an air quality change trend curve;
according to historical air pollution prevention and control data, establishing an air pollution prevention and control threshold duration Y, and according to an output air quality change trend curve, establishing an air pollution prevention and control threshold duration of a current air quality detection area:
wherein, the first and the second end of the pipe are connected with each other,
representing the air pollution control threshold duration of the current air quality detection area;
represents an influencing factor;
and when the time reaches the air pollution prevention threshold of the current air quality detection area, giving an early warning prompt.
6. The utility model provides an air quality detecting system based on thing networking which characterized in that: the system comprises an air quality detection area module, a data training module, an air quality change trend module and an early warning module; the air quality detection area module is used for constructing an air quality detection area, acquiring environmental data in the air quality detection area and outputting environmental influence factors of the current air quality detection area; the data training module is used for constructing a historical database, the historical database comprises air quality detection data and air pollution prevention data, constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model; the air quality change trend module is used for setting a time period, acquiring real-time acquired data of a current air quality detection area under the time period, and outputting an air quality change trend curve according to the prediction data model; the early warning module is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data, updating the air pollution prevention threshold duration of the current air quality detection area according to an output air quality change trend curve, and giving early warning prompts when judging time points of reaching the air pollution prevention threshold;
the output end of the air quality detection area module is connected with the input end of the data training module; the output end of the data training module is connected with the input end of the air quality variation trend module; the output end of the air quality change trend module is connected with the input end of the early warning module.
7. The air quality detection system based on the Internet of things as claimed in claim 6, wherein: the air quality detection area module comprises an area construction unit and an environment acquisition unit;
the area construction unit is used for constructing an air quality detection area; the environment acquisition unit is used for acquiring environment data in the air quality detection area and outputting environmental influence factors of the current air quality detection area;
and the output end of the area construction unit is connected with the input end of the environment acquisition unit.
8. The air quality detection system based on the Internet of things as claimed in claim 6, wherein: the data training module comprises a historical database unit and a data training unit;
the historical database unit is used for constructing a historical database and storing air quality detection data and air pollution prevention and control data; the data training unit is used for constructing a data processing model, and selecting high-priority historical air quality detection data to construct a prediction data model;
and the output end of the historical database unit is connected with the input end of the data training unit.
9. The air quality detection system based on the Internet of things as claimed in claim 6, wherein: the air quality change trend module comprises a time point analysis unit and a curve analysis unit;
the time point analysis unit is used for setting a time period, dividing the time period into R time points and acquiring real-time acquisition data of the current air quality detection area in the R time points under the time period; the curve analysis unit is used for constructing an air quality change trend curve according to data output by the prediction data model; wherein, R is a system setting constant;
and the output end of the time point analysis unit is connected with the input end of the curve analysis unit.
10. The air quality detection system based on the Internet of things as claimed in claim 6, wherein: the early warning module comprises a threshold updating unit and an early warning unit;
the threshold updating unit is used for constructing air pollution prevention threshold duration according to historical air pollution prevention data and updating the air pollution prevention threshold duration of the current air quality detection area according to the output air quality change trend curve; and the early warning unit gives an early warning prompt when judging that the time point of the air pollution prevention threshold is reached.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211670249.4A CN115656446B (en) | 2022-12-26 | 2022-12-26 | Air quality detection system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211670249.4A CN115656446B (en) | 2022-12-26 | 2022-12-26 | Air quality detection system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115656446A true CN115656446A (en) | 2023-01-31 |
| CN115656446B CN115656446B (en) | 2023-03-14 |
Family
ID=85022151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211670249.4A Active CN115656446B (en) | 2022-12-26 | 2022-12-26 | Air quality detection system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115656446B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129638A (en) * | 2023-10-26 | 2023-11-28 | 江西怡杉环保股份有限公司 | Regional air environment quality monitoring method and system |
| CN117706045A (en) * | 2024-02-06 | 2024-03-15 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330514A (en) * | 2017-07-10 | 2017-11-07 | 北京工业大学 | A kind of Air Quality Forecast method based on integrated extreme learning machine |
| 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 |
| CN109146121A (en) * | 2018-06-25 | 2019-01-04 | 华北电力大学 | The power predicating method stopped in the case of limited production based on PSO-BP model |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110598953A (en) * | 2019-09-23 | 2019-12-20 | 哈尔滨工程大学 | Space-time correlation air quality prediction method |
| CN110675006A (en) * | 2019-11-07 | 2020-01-10 | 桂林理工大学 | Indoor air quality real-time monitoring and formaldehyde attenuation prediction system |
| CN112734129A (en) * | 2021-01-21 | 2021-04-30 | 中国科学院地理科学与资源研究所 | Air pollution space-time trend prediction method based on unsupervised restrictive optimization |
| CN112818608A (en) * | 2021-02-22 | 2021-05-18 | 南方电网调峰调频发电有限公司 | Medium-and-long-term runoff forecasting method based on improved particle swarm optimization algorithm and support vector machine |
| CN113011660A (en) * | 2021-03-23 | 2021-06-22 | 上海应用技术大学 | Air quality prediction method, system and storage medium |
| CN113537515A (en) * | 2021-07-27 | 2021-10-22 | 江苏蓝创智能科技股份有限公司 | PM2.5 prediction method, system, device and storage medium |
| CN114676822A (en) * | 2022-03-25 | 2022-06-28 | 东南大学 | Multi-attribute fusion air quality forecasting method based on deep learning |
| CN114781538A (en) * | 2022-05-07 | 2022-07-22 | 东莞理工学院 | Air quality prediction method and system of GA-BP neural network coupling decision tree |
| CN114841461A (en) * | 2022-05-19 | 2022-08-02 | 重庆邮电大学 | Air quality integration prediction method based on time sequence missing perception and multi-source factor fusion |
| CN115542429A (en) * | 2022-09-20 | 2022-12-30 | 生态环境部环境工程评估中心 | XGboost-based ozone quality prediction method and system |
-
2022
- 2022-12-26 CN CN202211670249.4A patent/CN115656446B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330514A (en) * | 2017-07-10 | 2017-11-07 | 北京工业大学 | A kind of Air Quality Forecast method based on integrated extreme learning machine |
| 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 |
| CN109146121A (en) * | 2018-06-25 | 2019-01-04 | 华北电力大学 | The power predicating method stopped in the case of limited production based on PSO-BP model |
| CN110363347A (en) * | 2019-07-12 | 2019-10-22 | 江苏天长环保科技有限公司 | The method of neural network prediction air quality based on decision tree index |
| CN110598953A (en) * | 2019-09-23 | 2019-12-20 | 哈尔滨工程大学 | Space-time correlation air quality prediction method |
| CN110675006A (en) * | 2019-11-07 | 2020-01-10 | 桂林理工大学 | Indoor air quality real-time monitoring and formaldehyde attenuation prediction system |
| CN112734129A (en) * | 2021-01-21 | 2021-04-30 | 中国科学院地理科学与资源研究所 | Air pollution space-time trend prediction method based on unsupervised restrictive optimization |
| CN112818608A (en) * | 2021-02-22 | 2021-05-18 | 南方电网调峰调频发电有限公司 | Medium-and-long-term runoff forecasting method based on improved particle swarm optimization algorithm and support vector machine |
| CN113011660A (en) * | 2021-03-23 | 2021-06-22 | 上海应用技术大学 | Air quality prediction method, system and storage medium |
| CN113537515A (en) * | 2021-07-27 | 2021-10-22 | 江苏蓝创智能科技股份有限公司 | PM2.5 prediction method, system, device and storage medium |
| CN114676822A (en) * | 2022-03-25 | 2022-06-28 | 东南大学 | Multi-attribute fusion air quality forecasting method based on deep learning |
| CN114781538A (en) * | 2022-05-07 | 2022-07-22 | 东莞理工学院 | Air quality prediction method and system of GA-BP neural network coupling decision tree |
| CN114841461A (en) * | 2022-05-19 | 2022-08-02 | 重庆邮电大学 | Air quality integration prediction method based on time sequence missing perception and multi-source factor fusion |
| CN115542429A (en) * | 2022-09-20 | 2022-12-30 | 生态环境部环境工程评估中心 | XGboost-based ozone quality prediction method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129638A (en) * | 2023-10-26 | 2023-11-28 | 江西怡杉环保股份有限公司 | Regional air environment quality monitoring method and system |
| CN117129638B (en) * | 2023-10-26 | 2024-01-12 | 江西怡杉环保股份有限公司 | Regional air environment quality monitoring method and system |
| CN117706045A (en) * | 2024-02-06 | 2024-03-15 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
| CN117706045B (en) * | 2024-02-06 | 2024-05-10 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115656446B (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115656446B (en) | Air quality detection system and method based on Internet of things | |
| CN108426812B (en) | PM2.5 concentration value prediction method based on memory neural network | |
| Brunelli et al. | Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy | |
| Ma et al. | Spatiotemporal prediction of PM2. 5 concentrations at different time granularities using IDW-BLSTM | |
| CN110363347B (en) | Method for predicting air quality based on neural network of decision tree index | |
| CN108268935B (en) | PM2.5 concentration value prediction method and system based on time sequence recurrent neural network | |
| CN108064047B (en) | Water quality sensor network optimization deployment method based on particle swarm | |
| Hrust et al. | Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations | |
| CN112085163A (en) | Air quality prediction method based on attention enhancement graph convolutional neural network AGC and gated cyclic unit GRU | |
| CN110727717B (en) | Monitoring method, device, equipment and storage medium for gridding atmospheric pollution intensity | |
| CN109214570A (en) | A kind of urban area tail gas pollution prediction technique based on depth space-time correction model | |
| KR102100739B1 (en) | Method for predicting fine dust occurrence of target area | |
| CN113011455B (en) | Air quality prediction SVM model construction method | |
| Perez et al. | Forecasting of hourly PM2. 5 in south-west zone in Santiago de Chile | |
| CN112782050A (en) | Bioaerosol concentration prediction method based on long-short term memory neural network | |
| Brunelli et al. | Three hours ahead prevision of SO2 pollutant concentration using an Elman neural based forecaster | |
| CN116187822A (en) | Model prediction-based pollutant meshing monitoring and evaluating method | |
| CN109376903B (en) | PM2.5 concentration value prediction method based on game neural network | |
| CN114822709A (en) | Method and device for analyzing multi-granularity accurate cause of atmospheric pollution | |
| Lababede et al. | Mosques smart domes system using machine learning algorithms | |
| Shayeghi et al. | STLF based on optimized neural network using PSO | |
| CN115757534A (en) | Air quality prediction method of deep learning model based on potential source contribution analysis | |
| CN114942480A (en) | Ocean station wind speed forecasting method based on information perception attention dynamic cooperative network | |
| Sharma et al. | Efficient air pollutants prediction using ANFIS trained by modified PSO algorithm | |
| Gavrila | Ozone concentration prediction using artificial neural networks |
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 |