Ozonosphere forecasting algorithm based on artificial intelligence

A technology of artificial intelligence and the ozone layer, applied in the direction of calculation, neural learning methods, computer-aided design, etc., can solve the problems of complex causes of atmospheric ozone pollution, cumbersome mathematical modeling process, inconvenient ozone concentration, etc., to achieve accurate and efficient ozone concentration, High generalization, accurate and efficient prediction effect

Active Publication Date: 2022-01-07
NAT UNIV OF DEFENSE TECH
2 Cites 0 Cited by

AI-Extracted Technical Summary

Problems solved by technology

However, ozone pollution has "increased instead of falling", becoming an urgent problem to be solved in the next stage of air pollution prevention and control
The causes of atmospheric ozone pollution are complex, which brings great difficulties to the actual treatment work
[0004] At present, there are still some problems in the...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Abstract

The invention discloses an ozonosphere forecasting algorithm based on artificial intelligence. The ozonosphere forecasting algorithm comprises the following steps: S1, establishing an ozone concentration monitoring station; S2, collecting and acquiring historical meteorological data; S3, selecting influence factors; S4, carrying out preliminary prediction on the O3-8 h value of one day; S5, establishing a new hyperchaotic system; S6, establishing an artificial neural network; S7, establishing a chaotic artificial neural network; and S8, performing long-term and short-term forecasting by using the chaos artificial neural network. The research process of a traditional numerical weather forecasting method can be simplified, the traditional numerical weather forecasting method is often complex and high in calculation requirement, and the CANN operation adopted by the method is similar to other neural networks in that the CANN operation does not depend on the complex relation between parameters and output, but depends on continuous changes of weights, therefore, parameters are closely associated with output, and tedious mathematical modeling is avoided.

Application Domain

Technology Topic

Chaotic systemsEngineering +9

Image

  • Ozonosphere forecasting algorithm based on artificial intelligence
  • Ozonosphere forecasting algorithm based on artificial intelligence
  • Ozonosphere forecasting algorithm based on artificial intelligence

Examples

  • Experimental program(1)

Example Embodiment

[0046] Example 1
[0047] See figure 1 The present invention provides a technical solution: based on artificial intelligence of ozone layer forecasting algorithms, including the following steps:
[0048] S1. Establish an ozone concentration monitoring site: Select the position that has no effect on the surrounding environment and the active contaminants as an ozone concentration monitoring site;
[0049] S2. Collection, acquisition, acquisition, get a daily concentration data of each ozone concentration monitoring site, each ozone concentration monitoring site history daily concentration data and each ozone concentration monitoring site history Daily reference As a result, each ozone concentration monitoring site history The daily reference results for each ozone concentration monitoring site history daily concentration data and each ozone concentration monitoring site history daily concentration data;
[0050] S3. Choose the impact factor: Select Yesterday O 3 -8H value, PM2.5 average concentration, NO2 average concentration, predicted daily average air pressure, daily average wind speed and daily average temperature are influential factors;
[0051]S4. One day o 3 -8H value Precaution: By fitting, the predicted value and measured value of meteorological parameters and the measured value are given to the forecast equation, by obtaining the equation to monitor the day of the day to monitor the site of each ozone concentration monitoring site 3 -8H value prediction;
[0052] S5. Establishing a new super chaotic system: proposing a new hyperotic system and its corresponding complex system to generate a neural network input layer and a hidden layer between the weight values, the neuron threshold in the implicit layer, more Good forecast results;
[0053] Establishing artificial neural network: Network is divided into three parts: input layer, hiding layers, and output layers, in the network, input layer, hidden layer, and output layer neuron completely connected;
[0054] S7. Establishing a chaotic artificial neural network: The chaos artificial neural network is mixed with new hyperotic systems and artificial neural networks, and the chaos artificial neural network is carried out by artificial neural network, BP and multi-line regression models to ozone concentrations predict;
[0055] S8. Long short-term forecasting using chaos artificial neural network.
[0056] In the present embodiment, preferred, contaminant concentration data in S1 includes sulfur dioxide SO2, nitric oxide NO2, O 3 O 3 -8H, fine particulate PM2.5 and aerodynamic diameter of 2.5 microns or less of the air kinetics of 10 microns or less.
[0057] In this embodiment, preferably, the S2 is collected, and the acquisition of historical meteorological data further includes acquiring point source discharge features corresponding to any historical time of each ozone concentration monitoring site, and each ozone concentration monitoring site The point source emission feature corresponding to historical moments is obtained by the following steps:
[0058] S101. Get a sensitive area, including all cities that are bordered with the cities where each ozone concentration monitoring site is located;
[0059] S102. The sensitive area is divided into several identical rectangles, acquiring the point source discharge subsystem corresponding to the respective rectangles, and obtains the source discharge feature according to the point source discharge of each rectangle.
[0060] In this embodiment, it is preferable that the prediction equation of the fitted method in the S4 is:
[0061]
[0062] Among them, c is the day of the day to be predicted. 3 -8H predictive value, X1, X2, ... 3 -8H predicted or measured value, A0, A1, ..., A6 is the regression coefficient.
[0063] In the present embodiment, preferred, the new hyperactic system in the S5 is described by the following formula:
[0064]
[0065] Among them, A, B, C, and D represent the normal number, and ξ1, ξ2, ξ3, and ξ4 represent real variables, points on the symbols represent derived derivatives relative to time T;
[0066] The corresponding super chaotic complex system is given by the following formula:
[0067]
[0068] Among them, η1 = u1 + ju2, η2 = u3 + ju4, η3 = u5, 4 = u6 + ju7 represents a return amount, j = -1 -0.5 The strip represents the roll yoke of the bar above the variable;
[0069] The real version of the system is as follows:
[0070]
[0071] In this embodiment, it is preferable that the S8 utilizes a chaotic artificial neural network for a long short-term forecasting formula:
[0072]
[0073]
[0074] Where N represents the number of samples, XOBs, i represents the observation value, XPRE, i represents the predicted value, and var indicates the sample.
[0075] In the present embodiment, it is preferable that the chaos artificial neural network in the S7 uses a CANN operation, the CANN operation is usually divided into two steps: first, set parameters, select activation functions, and mode of operation, for activation functions, use The Sigmoid function is set to regression; second, select 70% -80% of sample data for training, the rest as test data, weight, and thresholds are automatically set in CANN.
[0076] In this embodiment, it is preferable, including ozone pollution warning, the ozone pollution warning includes an early warning module, the early warning module for warning of ozone pollution, determining the interval and contamination level of ozone contamination.
[0077] In this embodiment, it is preferable that the ozone contamination warning method includes the following steps:
[0078] S201. By analyzing the external conditions of the atmospheric ozone generated, sensitive physical parameters affecting atmospheric ozone pollution; the physical parameters include temperature, total radiant irradiation, cloud amount, particulate concentration, and nitrogen oxide concentration;
[0079] S202. Determine the inflection point value of each of the physical parameters of S201 according to the atmospheric ozone generating conditions, and assign each interval after interval division by the inflection point value;
[0080] S203. Acquisition of the historical data of the physical parameters of the ozone concentration monitoring site within a period of time, using the Logistic regression model to obtain the weight of each physical parameter;
[0081] S204. According to the interval assignment value of S202, the weight of the physical parameter of S203 is calculated, and the ozone concentration affects the result value, and determines the early warning interval and the corresponding warning level.
[0082] The principles and advantages of the present invention are similar to that of the CANN operation and other neural networks in that it does not rely on complex relationships between parameters and output, but it depends on the continuous change of weight, so that the parameters are closely related to the output. Avoid cumbersome mathematical modeling; the present invention has high generalization, and can maintain a high prediction accuracy while reducing some input parameters, can achieve good results in long-term and short-term ozone predictions, and It is possible to accurately and efficiently predict the ozone concentration, which is advantageous to protect the environment.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

PropertyMeasurementUnit
Diameter10.0µm
tensileMPa
Particle sizePa
strength10

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Similar technology patents

Unified low sample relation extraction method and device based on multi-choice matching network

PendingCN114528400AReduce computational cost and computational speedImprove generalizationSemantic analysisCharacter and pattern recognitionLanguage modelNetwork architecture
Owner:INST OF SOFTWARE - CHINESE ACAD OF SCI

Classification and recommendation of technical efficacy words

Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products