CN117706045B

CN117706045B - Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things

Info

Publication number: CN117706045B
Application number: CN202410168271.1A
Authority: CN
Inventors: 王春艳; 肖勇; 吴加禄; 杨净; 叶智; 高韦韦; 黄麟杰; 尹彦羽
Original assignee: Deyang Ecological Environment Monitoring Center Station Sichuan Province
Current assignee: Deyang Ecological Environment Monitoring Center Station Sichuan Province
Priority date: 2024-02-06
Filing date: 2024-02-06
Publication date: 2024-05-10
Anticipated expiration: 2044-02-06
Also published as: CN117706045A

Abstract

The invention relates to the technical field of ozone monitoring, and discloses a combined control method and a system for realizing atmospheric ozone monitoring equipment based on the Internet of things, wherein the combined control method comprises the following steps: inputting monitoring site data into a target ozone prediction neural network to obtain predicted site test data, calculating precision training data sets under different monitoring site densities, inputting the current static monitoring data and the monitoring site density sets into the target precision test neural network to obtain a current precision grade set, selecting a target dynamic monitoring site set according to the target monitoring site density, and carrying out ozone joint monitoring on the static monitoring site set and the target dynamic monitoring site set. The invention further provides a joint control system, electronic equipment and a computer readable storage medium for realizing the atmospheric ozone monitoring equipment based on the Internet of things. The invention can solve the problems of low monitoring efficiency and poor cooperativity in the current atmospheric ozone monitoring.

Description

Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things

Technical Field

The invention relates to the technical field of ozone monitoring, in particular to a combined control method and system for realizing atmospheric ozone monitoring equipment based on the Internet of things.

Background

With the industrial development and urban expansion, the atmospheric pollution problem is increasingly serious, and ozone is generated) Is a greenhouse gas, the concentration of which rises to cause global climate change, and high concentration of ozone stimulates eyes and respiratory tract of human body and affects cardiopulmonary function. Thus, monitoring atmospheric ozone is particularly important.

Currently, researchers develop various types of atmospheric ozone monitoring devices and perform regional monitoring on atmospheric ozone in a manner of forming a monitoring network by deploying the atmospheric ozone monitoring devices at a plurality of monitoring sites. However, the current atmospheric ozone monitoring equipment of each monitoring site usually works independently and lacks cooperative control, so that the regional global pollution condition is difficult to master in real time, and an effective pollution control strategy is difficult to formulate, so that the current atmospheric ozone monitoring has the problems of low monitoring efficiency and poor cooperative performance.

Disclosure of Invention

The invention provides a combined control method and a system for realizing atmospheric ozone monitoring equipment based on the Internet of things, and mainly aims to solve the problems of low monitoring efficiency and poor cooperativity in the current atmospheric ozone monitoring.

In order to achieve the above purpose, the invention provides a joint control method for realizing atmospheric ozone monitoring equipment based on the internet of things, which comprises the following steps:

An initial ozone prediction neural network is constructed according to a preset monitoring bit set and a preset prediction bit set, wherein an input layer node set of the initial ozone prediction neural network consists of a static bit input node set and a dynamic bit input node set, an output layer node set is a prediction bit output node set, and the monitoring bit set comprises a static monitoring bit set and a dynamic monitoring bit set;

training the initial ozone prediction neural network by using a pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network;

Constructing an initial precision test neural network according to a static monitoring bit set, wherein an input layer node set of the initial precision test neural network consists of a static bit input node set and bit density input nodes, and an output layer node is a precision grade output node;

acquiring an atmospheric ozone test data set, and sequentially extracting the atmospheric ozone test data in the atmospheric ozone test data set;

Sequentially extracting monitoring site densities in a pre-constructed monitoring site density set, extracting monitoring site data from the atmospheric ozone test data according to the monitoring site densities, and inputting the monitoring site data into the target ozone prediction neural network to obtain predicted site test data, wherein the monitoring site data comprises static monitoring data of a static monitoring site set;

Extracting real test site data of a predicted site set from the atmospheric ozone test data, and calculating the prediction accuracy of the monitoring site density according to the predicted site test data and the real test site data to obtain a prediction accuracy set of the atmospheric ozone test data under different monitoring site densities;

Summarizing static monitoring data, a monitoring site density set and a prediction precision set corresponding to all the atmospheric ozone test data to obtain a precision training data set;

training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network;

Receiving current static monitoring data, and inputting the current static monitoring data and a monitoring site density set into the target precision test neural network to obtain a current precision grade set;

Receiving a target precision grade input by a user, identifying target monitoring site density corresponding to the target precision grade according to the current precision grade set, and selecting a target dynamic monitoring site set from the dynamic monitoring site set according to the target monitoring site density;

And carrying out ozone joint monitoring on the static monitoring position set and the target dynamic monitoring position set by using the target ozone prediction neural network and the pre-constructed ozone monitoring Internet of things, so as to complete joint control of the atmospheric ozone monitoring equipment based on the Internet of things.

Optionally, training the initial ozone prediction neural network by using the pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network, including:

sequentially extracting atmospheric ozone monitoring data in the atmospheric ozone training data set, and sequentially extracting monitoring site densities in a preset monitoring site density set;

extracting training monitoring data from the atmospheric ozone monitoring data according to the monitoring site density;

identifying a monitoring site of each training monitoring value in the training monitoring data, and identifying an input layer node of the monitoring site;

inputting the training monitoring value into the initial ozone prediction neural network by using an input layer node of the monitoring site to obtain training input data;

calculating and outputting predicted site training data according to the training input data by utilizing the input layer weight, the hidden layer weight and the activation function in the initial ozone predicted neural network, wherein the predicted site training data consists of output data of all output layer nodes;

Extracting training site real data of a predicted site set from the training monitoring data, and calculating a training difference value according to the training site real data and the predicted site training data;

And carrying out feedback regulation on the initial ozone prediction neural network according to the training difference value and the predicted site training data to obtain a target ozone prediction neural network.

Optionally, before the initial ozone prediction neural network is constructed according to the preset monitoring position point set and the prediction position point set, the method further includes:

meshing a preset target area to obtain a target mesh area, and extracting a mesh intersection point set and a mesh center point set of the target mesh area;

receiving static monitoring distances of static monitoring sites input by a user, and selecting a static monitoring site set from the grid intersection point set according to the static monitoring distances;

removing the static monitoring point set from the grid intersection point set to obtain a dynamic monitoring point set;

summarizing the static monitoring bit point set and the dynamic monitoring bit point set to obtain a monitoring bit point set;

And taking the grid center point set as a predicted bit point set.

Optionally, the extracting monitoring site data from the atmospheric ozone test data according to the monitoring site density includes:

Selecting an enabled monitoring site set from the dynamic monitoring site sets according to the monitoring site density;

Respectively extracting static monitoring position point sets and static monitoring position point data corresponding to the starting monitoring position point sets from the atmospheric ozone test data;

And summarizing the static monitoring site data and starting the monitoring site data to obtain the monitoring site data.

Optionally, the calculating the prediction accuracy of the monitoring site density according to the prediction site test data and the test site real data to obtain a prediction accuracy set of the atmospheric ozone test data under different monitoring site densities includes:

sequentially extracting predicted sites in the predicted site set;

Respectively extracting a predicted site test value and a predicted site real value of the predicted site from the predicted site test data and the predicted site real data;

taking the predicted site test value and the predicted site real value as predicted value pairs of the predicted sites, and summarizing the predicted value pairs of all the predicted sites to obtain a predicted value pair set;

calculating the prediction precision of the atmospheric ozone test data under the monitoring site density by using the prediction numerical value pair set according to a pre-constructed prediction precision formula, wherein the prediction precision formula is as follows:

Wherein τ represents prediction precision, k represents a precision adjustment factor, I represents a sequence number of predicted sites, I represents a total number of predicted sites, y _i ^c represents a predicted site test value in a predicted value pair set of the I-th predicted site, yi ^z represents a predicted site true value in the predicted value pair set of the I-th predicted site, μ represents a preset standard predicted difference value, and I represents an absolute value symbol;

And summarizing the prediction precision of the atmospheric ozone test data under the density of all monitoring sites to obtain the prediction precision set.

Optionally, training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network, including:

Extracting prediction precision sets corresponding to all atmospheric ozone test data from the precision training data set;

Performing precision value range division on the prediction precision sets corresponding to all the atmospheric ozone test data to obtain a prediction precision grade set;

Sequentially extracting precision training data from the precision training data set, wherein the precision training data comprises static monitoring data, a monitoring site density set and a prediction precision set;

Sequentially extracting monitoring site densities in the monitoring site density set, extracting prediction precision corresponding to the monitoring site densities in the prediction precision set, and identifying a prediction precision grade to which the prediction precision belongs;

And performing iterative training on the initial precision test neural network according to static monitoring data, monitoring site density and prediction precision grade corresponding to all the precision training data in the precision training data set to obtain the target precision test neural network.

Optionally, after the current static monitoring data and the monitoring site density set are input into the target precision test neural network to obtain the current precision grade set, the method further includes:

sequentially extracting current precision grades from the current precision grade set, and acquiring a monitoring site density set corresponding to the current precision grade;

And constructing a site density set-precision grade comparison table according to the corresponding relation between the current precision grade and the monitoring site density set.

Optionally, the identifying, according to the current precision level set, the target monitoring site density corresponding to the target precision level includes:

Extracting a target site density set corresponding to the target precision grade from the site density set-precision grade comparison table;

and extracting the maximum monitoring site density in the target site density set to obtain the target monitoring site density.

Optionally, the ozone joint monitoring of the static monitoring point set and the target dynamic monitoring point set by using the target ozone prediction neural network and the pre-constructed ozone monitoring internet of things includes:

Identifying a static site monitoring equipment set and a target dynamic monitoring equipment set corresponding to the static monitoring site set and the target dynamic monitoring site set;

Utilizing the ozone monitoring internet of things to carry out ozone joint control on the static site monitoring equipment set and the target dynamic monitoring equipment set, and monitoring the atmospheric ozone concentration to obtain an ozone monitoring concentration set, wherein the ozone monitoring concentration set comprises: static monitoring concentration set and target dynamic monitoring concentration set;

sequentially extracting ozone monitoring concentration in the ozone monitoring concentration set, and identifying a target input layer node corresponding to the ozone monitoring concentration to obtain a target input layer node set;

inputting all the ozone monitoring concentrations in the ozone monitoring concentration set into the target input layer node set correspondingly to obtain predicted site target data of the predicted site set;

Calibrating the ozone concentration of the target area according to the current static monitoring data and the predicted site target data to obtain an ozone concentration calibration chart;

And performing ozone concentration curve fitting on the ozone concentration calibration graph to obtain an ozone concentration fitting curve.

In order to solve the above problems, the present invention further provides a joint control system for implementing an atmospheric ozone monitoring device based on the internet of things, the system comprising:

The initial ozone prediction neural network training module is used for constructing an initial ozone prediction neural network according to a preset monitoring position set and a preset prediction position set, wherein an input layer node set of the initial ozone prediction neural network consists of a static position input node set and a dynamic position input node set, an output layer node set is a prediction position output node set, and the monitoring position set comprises a static monitoring position set and a dynamic monitoring position set; training the initial ozone prediction neural network by using a pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network;

The initial precision test neural network construction module is used for constructing an initial precision test neural network according to the static monitoring site set, wherein an input layer node set of the initial precision test neural network consists of a static site input node set and site density input nodes, and an output layer node is a precision grade output node;

The precision training data set acquisition module is used for acquiring an atmospheric ozone test data set, and sequentially extracting atmospheric ozone test data in the atmospheric ozone test data set; sequentially extracting monitoring site densities in a pre-constructed monitoring site density set, extracting monitoring site data from the atmospheric ozone test data according to the monitoring site densities, and inputting the monitoring site data into the target ozone prediction neural network to obtain predicted site test data, wherein the monitoring site data comprises static monitoring data of a static monitoring site set; extracting real test site data of a predicted site set from the atmospheric ozone test data, and calculating the prediction accuracy of the monitoring site density according to the predicted site test data and the real test site data to obtain a prediction accuracy set of the atmospheric ozone test data under different monitoring site densities; summarizing static monitoring data, a monitoring site density set and a prediction precision set corresponding to all the atmospheric ozone test data to obtain a precision training data set;

The initial precision test neural network training module is used for training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network;

the current ozone concentration monitoring module is used for receiving current static monitoring data, inputting the current static monitoring data and a monitoring site density set into the target precision test neural network, and obtaining a current precision grade set; receiving a target precision grade input by a user, identifying target monitoring site density corresponding to the target precision grade according to the current precision grade set, and selecting a target dynamic monitoring site set from the dynamic monitoring site set according to the target monitoring site density; and carrying out ozone joint monitoring on the static monitoring position set and the target dynamic monitoring position set by utilizing the target ozone prediction neural network and the pre-constructed ozone monitoring Internet of things.

In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to implement the above-described joint control method for implementing the atmospheric ozone monitoring device based on the internet of things.

In order to solve the above problems, the present invention further provides a computer readable storage medium, where at least one instruction is stored, where the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned combined control method for implementing an atmospheric ozone monitoring device based on the internet of things.

Compared with the background art, the method comprises the following steps: the current static monitoring data is analyzed through a target precision test neural network to obtain a current precision grade set of the current static monitoring data under different monitoring site densities, then the target monitoring site density is extracted from the current precision grade set according to the target precision grade input by a user, so that a target dynamic monitoring site set can be selected in the dynamic monitoring site set according to the target monitoring site density, the static monitoring site set and the target dynamic monitoring site set are subjected to ozone joint monitoring by utilizing the target ozone prediction neural network and a pre-built ozone monitoring internet of things, when the target ozone prediction neural network is built, an initial ozone prediction neural network is required to be built, wherein an input layer node set of the initial ozone prediction neural network consists of a static site input node set and a dynamic site input node set, an output layer node set is a prediction site output node set, and therefore the starting of the dynamic monitoring site can be met, after the current dynamic monitoring site set is obtained, the static dynamic monitoring site set can be directly monitored, the static dynamic monitoring site set and the target dynamic monitoring site set can be predicted, the ozone prediction neural network is required to be built when the target ozone prediction neural network is built, the ozone prediction neural network is not predicted, the ozone is required to be predicted, the ozone prediction neural network is required to be predicted, and the ozone is not required to be predicted, and the ozone is predicted, the target dynamic monitoring site set is different in the target ozone network, the method comprises the steps of constructing a target precision test neural network to judge the prediction precision of different static monitoring data under different monitoring site densities, wherein an input layer node set of the initial precision test neural network consists of a static site input node set and a site density input node, an output layer node is an accuracy grade output node, when the initial precision test neural network is trained, a precision training data set needs to be acquired firstly, the target ozone prediction neural network is utilized to judge the prediction precision of the monitoring site data under different monitoring site densities, firstly, the monitoring site data is required to be extracted from the atmospheric ozone test data according to the monitoring site densities, the monitoring site data is input into the target ozone prediction neural network to obtain predicted site test data, then the test site real data of the predicted site set is extracted from the atmospheric ozone test data, accordingly, the prediction precision of the monitoring site densities is calculated according to the predicted site test data and the test site real data, the predicted precision of the atmospheric ozone test data under different monitoring site densities is obtained, finally, the target ozone test neural network is subjected to the combined according to the precision training data set to obtain the prediction precision of the initial test site data under different monitoring site densities, and finally, the target dynamic ozone test grade is dynamically predicted according to the target ozone test network is obtained, and the target ozone test site dynamic grade is extracted from the target ozone test network. Therefore, the combined control method, the system, the electronic equipment and the computer readable storage medium for realizing the atmospheric ozone monitoring equipment based on the Internet of things can solve the problems of low monitoring efficiency and poor cooperativity in the current atmospheric ozone monitoring.

Drawings

Fig. 1 is a schematic flow chart of a combined control method for implementing an atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention;

Fig. 2 is a functional block diagram of a joint control system for implementing an atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device for implementing the combined control method for implementing the atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention.

In the figure, 1-an electronic device; 10-a processor; 11-memory; 12-bus; 13-a communication interface; 100-realizing a joint control system of the atmospheric ozone monitoring equipment based on the Internet of things; 101-an initial ozone prediction neural network training module; 102-an initial accuracy test neural network construction module; 103-an accuracy training data set acquisition module; 104-an initial accuracy test neural network training module; 105-current ozone concentration monitoring module.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the application provides a joint control method for realizing atmospheric ozone monitoring equipment based on the Internet of things. The execution main body of the combined control method for realizing the atmosphere ozone monitoring equipment based on the Internet of things comprises at least one of electronic equipment, such as a server, a terminal and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the joint control method for realizing the atmospheric ozone monitoring device based on the internet of things can be executed by software or hardware installed in the terminal device or the server device. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Example 1:

Referring to fig. 1, a flow chart of a combined control method for implementing an atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention is shown. In this embodiment, the method for implementing the joint control of the atmospheric ozone monitoring device based on the internet of things includes:

S1, constructing an initial ozone prediction neural network according to a preset monitoring position set and a preset prediction position set.

The set of monitoring sites is interpretable as a set of monitoring sites of an atmospheric ozone monitoring device. The predicted site set refers to a site set for predicting the concentration of ozone in the atmosphere. The initial ozone predicting neural network may be an untrained BP neural network.

In detail, the input layer node set of the initial ozone prediction neural network consists of a static site input node set and a dynamic site input node set, the output layer node set is a prediction site output node set, and the monitoring site set comprises a static monitoring site set and a dynamic monitoring site set.

Further, the static site input node set refers to an input layer node set for inputting the atmospheric ozone concentration monitored at the static monitoring site set, and the dynamic site input node set refers to an input layer node set for inputting the atmospheric ozone concentration monitored at the dynamic monitoring site set. The static monitoring point set refers to a point set which needs to be monitored every time atmospheric ozone is monitored, and the dynamic monitoring point set refers to a point set which can be selected whether to monitor every time atmospheric ozone is monitored.

As will be appreciated, the predicted site output node set refers to a set of output nodes for outputting the atmospheric ozone concentration of each predicted site in the predicted site set, for example: when the predicted bit point set is a predicted bit point a, a predicted bit point b, and a predicted bit point c, the predicted bit point output node set may be a predicted bit point a output node, a predicted bit point b output node, and a predicted bit point c output node.

In the embodiment of the present invention, before the initial ozone prediction neural network is constructed according to the preset monitoring site set and the prediction site set, the method further includes:

And taking the grid center point set as a predicted bit point set.

It will be appreciated that the target area is an area where atmospheric ozone monitoring is required, for example: a city. The target mesh region refers to a region obtained by mesh division of the target region, for example: and dividing the target area by utilizing a square grid. The grid intersection point set refers to an intersection point set of grid lines in the target grid region, and the grid center point set refers to a center point set of grids in the target grid region, for example: when the meshing division mode is square meshing division, the grid center point set refers to a square center point set.

Further, the static monitoring distance refers to the distance of the static monitoring sites along the grid lines, for example: when the static monitoring distance is 20km, each grid in the target grid area is a grid with a side length of 5km, and the distance between the static monitoring sites on the grid line is 20 grid side lengths.

It can be explained that all grid intersection points in the target grid area can be divided into static monitoring sites and dynamic monitoring sites, and when the static monitoring site sets are removed from the grid intersection point sets, the obtained natural monitoring sites are dynamic monitoring sites.

It should be appreciated that the set of predicted bits may be represented by the center points of the mesh in the target mesh region, for example: when the grid is square and the side length is 100m, then the prediction site may be the intersection of the diagonal lines of the square grid.

S2, training the initial ozone prediction neural network by using a pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network.

It is understood that the atmospheric ozone training dataset refers to historical atmospheric ozone concentration data for each monitoring site and prediction site in the target area.

In the embodiment of the present invention, training the initial ozone prediction neural network by using the pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network includes:

The atmospheric ozone monitoring data may be interpreted as atmospheric ozone concentration data at a monitoring site set and a position of a predicted site set at a time point in the past. The monitoring site density set refers to the number of monitoring sites in a unit area region in the target region. For example: when the area of the target area is square with 3600 square kilometers, the static monitoring distance is 20km, the number of the static monitoring sites can be 16, the grid side length is 5km, the number of the dynamic monitoring sites between every two adjacent static monitoring sites is 3, and the number of the dynamic monitoring sites is 243. Where 24 represents the number of grid edges consisting of two adjacent static monitoring sites. The input layer nodes of the initial ozone prediction neural network are 16 static site input nodes and 24/>3 Dynamic site input nodes. At this time, the monitoring site density set was 16/3600// >, when none of the dynamic monitoring sites were monitored for ozone; When 24 of the dynamic monitoring sites were subjected to ozone monitoring (i.e., one dynamic monitoring site was added to each grid side), it was (16+24)/3600// >; When the dynamic monitoring site has 24+24/>2 (16+24+24) For ozone monitoring (i.e. 3 dynamic monitoring sites are added to each grid side)2) 3600// >The dynamic monitoring sites are all monitored by atmospheric ozone at this time. It should be noted that the target area will not generally be strictly square, and that a square or rectangle covering the target area may be used for monitoring.

Further, the number of dynamic monitoring sites should be increased uniformly when the number of dynamic monitoring sites is increased, i.e. the number of dynamic monitoring sites on each grid edge should be consistent. Therefore, when the target area is covered with a square of 3600 square kilometers (the side length is 60 km), the static monitoring distance is 20km, the number of static monitoring sites is 16, the grid side length is 5km, and the monitoring site density set includes: 16/3600-(Dynamic monitoring site Enable number is 0), (16+24)/3600// >(Dynamic monitoring site Enable number is 24) and (16+24+24/>)2) 3600// >(Dynamic monitoring site Enable number is 24+24/>)2) These three. Of course, the adjustment can be performed according to the actual situation. However, in the process of adding, the dynamic monitoring sites added to each grid are required to be uniformly added, namely the number and the positions of the dynamic monitoring sites are necessarily the same, and a small area is avoided from being added.

It is understood that the training monitoring data includes atmospheric ozone concentration data at a monitoring site that needs to be input at a time in the history and at a predicted site at a corresponding time.

Further, the training monitoring value needs to be input into the initial ozone prediction neural network correspondingly, namely, the atmospheric ozone concentration of the monitoring site at the time needs to be input into the input node corresponding to the monitoring site correspondingly. The training process of the initial ozone prediction neural network may refer to the training process of the BP neural network, which is not described herein.

And S3, constructing an initial precision test neural network according to the static monitoring bit set.

The initial accuracy test neural network may be a BP neural network.

In detail, the input layer node set of the initial precision test neural network consists of a static site input node set and site density input nodes, and the output layer node is a precision grade output node.

S4, acquiring an atmospheric ozone test data set, and sequentially extracting the atmospheric ozone test data in the atmospheric ozone test data set.

It is understood that the atmospheric ozone test data refers to data of atmospheric oxygen concentration of each monitoring site and prediction site at a certain moment in history. The atmospheric ozone test data set refers to data of atmospheric oxygen concentration of each monitoring site and prediction site at a plurality of historical moments. The atmospheric ozone test dataset is defined as the atmospheric ozone training dataset, but for training and testing purposes, the two datasets need to be different.

S5, sequentially extracting monitoring site densities in the pre-constructed monitoring site density set, extracting monitoring site data from the atmospheric ozone test data according to the monitoring site densities, and inputting the monitoring site data into the target ozone prediction neural network to obtain predicted site test data.

Further, the monitoring site data includes static monitoring data for a set of static monitoring sites. Dynamic monitoring data, which may or may not include dynamic monitoring sites. The selection of whether to include dynamic monitoring data or not and how much dynamic monitoring data to include may be made based on the monitoring site density.

It is understood that the monitoring site density refers to the number of monitoring sites per unit area in a square or rectangle covering the target area, and may be a fraction. The predicted site test data refer to the atmospheric ozone concentration of each predicted site calculated by the target ozone predicted neural network according to the monitoring site data.

In the embodiment of the present invention, the extracting monitoring site data from the atmospheric ozone test data according to the monitoring site density includes:

S6, extracting real test site data of a predicted site set from the atmospheric ozone test data, and calculating the prediction precision of the monitoring site density according to the predicted site test data and the real test site data to obtain a prediction precision set of the atmospheric ozone test data under different monitoring site densities.

It is understood that the test site real data refers to a set of real values for each predicted site in the atmospheric ozone test data. The prediction accuracy refers to the prediction accuracy of the prediction site test data.

In the embodiment of the present invention, the calculating the prediction accuracy of the monitoring site density according to the predicted site test data and the real test site data to obtain the prediction accuracy set of the atmospheric ozone test data under different monitoring site densities includes:

sequentially extracting predicted sites in the predicted site set;

And S7, summarizing static monitoring data, a monitoring site density set and a prediction precision set corresponding to all the atmospheric ozone test data to obtain a precision training data set.

And S8, training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network.

In the embodiment of the present invention, training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network includes:

It is understood that the prediction precision set may be 5, 9, 20, 41, 54, 80, etc., and the prediction precision set may be divided into precision ranges, for example: the precision value range can be divided into prediction precision grades such as excellent precision 0-10, good precision 11-20, precision general 21-40, precision poor 41-60, precision extremely poor 61-80 and the like, and then 5 and 9 belong to excellent precision, 20 belong to good precision, 41 and 54 belong to poor precision, and 80 belong to extremely poor precision.

S9, receiving current static monitoring data, and inputting the current static monitoring data and the monitoring site density set into the target precision test neural network to obtain a current precision grade set.

It is understood that the current static monitoring data refers to the atmospheric ozone concentration data monitored by the current static site. The current precision grade set refers to a prediction precision grade set of the current static monitoring data under different monitoring site densities.

In the embodiment of the present invention, after the current static monitoring data and the monitoring site density set are input into the target precision test neural network to obtain the current precision grade set, the method further includes:

It is understood that the site density set-precision level comparison table refers to a table describing the correspondence between the current precision level and the monitoring site density set.

S10, receiving a target precision grade input by a user, identifying target monitoring site density corresponding to the target precision grade according to the current precision grade set, and selecting a target dynamic monitoring site set from the dynamic monitoring site set according to the target monitoring site density.

As can be appreciated, the target level of accuracy refers to a level of accuracy required by the user, for example: the user needs to predict that the accuracy class is good.

In the embodiment of the present invention, the identifying, according to the current precision level set, the target monitoring site density corresponding to the target precision level includes:

It can be appreciated that since there may be multiple monitoring site densities to achieve the target level of accuracy, the maximum monitoring site density may be selected to enhance accuracy. The minimum or intermediate monitoring site density may also be selected.

S11, utilizing the target ozone prediction neural network and the pre-constructed ozone monitoring Internet of things to perform ozone joint monitoring on the static monitoring position set and the target dynamic monitoring position set, and completing joint control of the atmospheric ozone monitoring equipment based on the Internet of things.

It can be understood that the ozone monitoring internet of things refers to the internet of things which can control all monitoring devices of dynamic monitoring sites and monitoring devices of static monitoring sites to start monitoring at the same time.

In the embodiment of the present invention, the method for performing ozone joint monitoring on the static monitoring point set and the target dynamic monitoring point set by using the target ozone prediction neural network and the pre-constructed ozone monitoring internet of things includes:

It will be appreciated that the ozone concentration calibration map indicates a map of atmospheric ozone concentrations for each static monitoring site, each dynamic monitoring site (active dynamic monitoring site), and the predicted site. The ozone concentration fitting curved surface refers to a curved surface which is fit according to the ozone concentration values at each monitoring site and the predicted site in the ozone concentration calibration chart.

Example 2:

fig. 2 is a functional block diagram of a joint control system for implementing an atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention.

The joint control system 100 for realizing the atmospheric ozone monitoring device based on the internet of things can be installed in electronic equipment. According to the implemented functions, the joint control system 100 for implementing the atmospheric ozone monitoring device based on the internet of things may include an initial ozone prediction neural network training module 101, an initial precision test neural network construction module 102, a precision training data set acquisition module 103, an initial precision test neural network training module 104, and a current ozone concentration monitoring module 105. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

The initial ozone prediction neural network training module 101 is configured to construct an initial ozone prediction neural network according to a preset monitoring bit set and a preset prediction bit set, where an input layer node set of the initial ozone prediction neural network is composed of a static bit input node set and a dynamic bit input node set, and an output layer node set is a prediction bit output node set, and the monitoring bit set includes a static monitoring bit set and a dynamic monitoring bit set; training the initial ozone prediction neural network by using a pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network;

The initial precision test neural network construction module 102 is configured to construct an initial precision test neural network according to a static monitoring site set, where an input layer node set of the initial precision test neural network is composed of a static site input node set and site density input nodes, and an output layer node is a precision grade output node;

the precision training data set obtaining module 103 is configured to obtain an atmospheric ozone test data set, and sequentially extract atmospheric ozone test data in the atmospheric ozone test data set; sequentially extracting monitoring site densities in a pre-constructed monitoring site density set, extracting monitoring site data from the atmospheric ozone test data according to the monitoring site densities, and inputting the monitoring site data into the target ozone prediction neural network to obtain predicted site test data, wherein the monitoring site data comprises static monitoring data of a static monitoring site set; extracting real test site data of a predicted site set from the atmospheric ozone test data, and calculating the prediction accuracy of the monitoring site density according to the predicted site test data and the real test site data to obtain a prediction accuracy set of the atmospheric ozone test data under different monitoring site densities; summarizing static monitoring data, a monitoring site density set and a prediction precision set corresponding to all the atmospheric ozone test data to obtain a precision training data set;

the initial precision test neural network training module 104 is configured to train the initial precision test neural network according to the precision training data set to obtain a target precision test neural network;

The current ozone concentration monitoring module 105 is configured to receive current static monitoring data, input the current static monitoring data and a monitoring site density set into the target precision test neural network, and obtain a current precision grade set; receiving a target precision grade input by a user, identifying target monitoring site density corresponding to the target precision grade according to the current precision grade set, and selecting a target dynamic monitoring site set from the dynamic monitoring site set according to the target monitoring site density; and carrying out ozone joint monitoring on the static monitoring position set and the target dynamic monitoring position set by utilizing the target ozone prediction neural network and the pre-constructed ozone monitoring Internet of things.

In detail, the modules in the combined control system 100 for implementing the atmospheric ozone monitoring device based on the internet of things in the embodiment of the present invention adopt the same technical means as the above-mentioned combined control method for implementing the atmospheric ozone monitoring device based on the internet of things in fig. 1, and can produce the same technical effects, which are not described herein.

Example 3:

Fig. 3 is a schematic structural diagram of an electronic device for implementing a method for implementing a joint control of an atmospheric ozone monitoring device based on the internet of things according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11, a bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a joint control program for implementing an atmospheric ozone monitoring device based on the internet of things.

The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various data, such as codes of a joint control program for implementing an atmospheric ozone monitoring device based on the internet of things, but also to temporarily store data that has been output or is to be output.

The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory 11 (for example, a joint Control program for implementing an atmospheric ozone monitoring device based on the internet of things, etc.), and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.

The bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.

For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.

Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.

The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

The joint control program stored in the memory 11 of the electronic device 1 and used for implementing the atmospheric ozone monitoring device based on the internet of things is a combination of a plurality of instructions, and when running in the processor 10, the joint control program can implement:

Specifically, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 2, which are not repeated herein.

Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. The combined control method for realizing the atmospheric ozone monitoring equipment based on the Internet of things is characterized by comprising the following steps of:

Utilizing the target ozone prediction neural network and a pre-constructed ozone monitoring internet of things to perform ozone joint monitoring on the static monitoring position set and the target dynamic monitoring position set, and completing joint control of atmospheric ozone monitoring equipment based on the internet of things;

training the initial precision test neural network according to the precision training data set to obtain a target precision test neural network, wherein the training comprises the following steps:

2. The method for implementing the joint control of the atmospheric ozone monitoring device based on the internet of things according to claim 1, wherein training the initial ozone prediction neural network by using the pre-constructed atmospheric ozone training data set to obtain a target ozone prediction neural network comprises:

3. The method for implementing joint control of atmospheric ozone monitoring devices based on the internet of things according to claim 2, wherein before the initial ozone prediction neural network is constructed according to the preset monitoring point set and the prediction point set, the method further comprises:

And taking the grid center point set as a predicted bit point set.

4. The joint control method for implementing an atmospheric ozone monitoring device based on the internet of things according to claim 1, wherein the extracting monitoring site data from the atmospheric ozone test data according to the monitoring site density comprises:

5. The method for implementing the joint control of the atmospheric ozone monitoring device based on the internet of things according to claim 1, wherein the calculating the prediction accuracy of the monitoring site density according to the prediction site test data and the test site real data to obtain the prediction accuracy set of the atmospheric ozone test data under different monitoring site densities comprises:

sequentially extracting predicted sites in the predicted site set;

6. The method for implementing joint control of atmospheric ozone monitoring equipment based on the internet of things according to claim 1, wherein after the current static monitoring data and the monitoring site density set are input into the target precision test neural network to obtain the current precision level set, the method further comprises:

7. The method for implementing joint control of atmospheric ozone monitoring devices based on the internet of things according to claim 6, wherein the identifying the target monitoring site density corresponding to the target precision grade according to the current precision grade set comprises:

8. The method for implementing joint control of atmospheric ozone monitoring equipment based on the internet of things according to claim 3, wherein the performing ozone joint monitoring on the static monitoring point set and the target dynamic monitoring point set by using the target ozone prediction neural network and a pre-constructed ozone monitoring internet of things comprises:

9. A joint control system for implementing an atmospheric ozone monitoring device based on the internet of things, for implementing the joint control method for implementing an atmospheric ozone monitoring device based on the internet of things according to claim 1, characterized in that the system comprises: