Air quality early warning and forecasting visualization system based on AI technology

Abstract

The invention relates to the technical field of computers, in particular to an air quality early warning and forecasting visualization system based on an AI technology. The system comprises a monitoring micro station, a data preprocessing module, a first data processing module, a second data processing module and a data display processing module. The monitoring micro station is used for collecting various air component parameters at various positions to obtain various air component parameter data sets; the data preprocessing module is used for performing normalization processing on the various air component parameter data sets and cleaning the air component parameter data sets to obtain preprocessed data sets; the first data processing module is used for calculating air quality data based on the preprocessed data set and judging whether the air quality data exceed a preset threshold value or not; the second data processing module is used for predicting an air quality change trend to obtain trend data based on the exceeding signal and historical air pollution data obtained in advance; and the data display processing module is used for storing and displaying the data generated by each module.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a visualization system for air quality early warning and forecasting based on AI technology. Background Art

[0002] With the transformation of environmental quality management from an extensive mode to a refined mode, grid-based environmental supervision has become an important means of environmental improvement. Construction of grid-based supervision systems has been successively carried out for various urban problems. As an important part of grid-based environmental supervision, grid-based management of air pollution prevention and control constructs a normalized management system with responsibilities in place, supervision in place, implementation in place, and supervision in place in accordance with the principles of territorial management, hierarchical responsibility, combination of vertical and horizontal, and seamless connection; taking districts and counties, sub-districts, townships, and communities (villages) as units, grid-based management of air pollution prevention and control is hierarchically delimited, and grid inspectors, grid leaders, etc. are set up within the regional grids to construct a grid-based management system for air pollution prevention and control with the participation of the whole people.

[0003] The existing air quality early warning system cannot accurately monitor air quality and cannot issue accurate early warnings and forecasts. To solve this technical problem, a visualization system for air quality early warning and forecasting based on AI technology is now proposed. Summary of the Invention

[0004] To solve the technical problems existing in the above-mentioned prior art, the present invention provides a visualization system for air quality early warning and forecasting based on AI technology.

[0005] To achieve the above object, the embodiments of the present invention provide the following technical solutions:

[0006] In a first aspect, in an embodiment provided by the present invention, a visualization system for air quality early warning and forecasting based on AI technology is provided. The system includes: a monitoring microsite, a data preprocessing module, a first data processing module, a second data processing module, and a data display and processing module;

[0007] The monitoring microsite is used to collect various air component parameters at various positions to obtain various air component parameter data sets;

[0008] The data preprocessing module is used to perform normalization processing on various air component parameter data sets, clean them to obtain a preprocessed data set, and send the preprocessed data set to the first data processing module;

[0009] The first data processing module is used to calculate air quality data based on the preprocessed data set, and determine whether the air quality data exceeds a preset threshold. If it exceeds, an over-signal is sent to the second data processing module;

[0010] The second data processing module is used to predict the changing trend of air quality based on the excess signal and the pre-acquired historical air pollution data, so as to obtain trend data. The trend data is used to predict the air quality in a future period of time. The trend data is judged to determine whether the future weather quality exceeds a preset pollution threshold. If it exceeds, a warning signal is issued.

[0011] The data display processing module is used to connect to the monitoring microsite, the data preprocessing module, the first data processing module and the second data processing module, and store and display the data generated by each module.

[0012] As a further solution of the present invention, the air component parameters include PM10 particle concentration, PM2.5 particle concentration, SO2 gas concentration, NO2 gas concentration, CO gas concentration and O3 gas concentration.

[0013] As a further solution of the present invention, the first data processing module calculates air quality data based on the air warning model and judges whether the control quality data exceeds a preset threshold.

[0014] As a further solution of the present invention, the first data processing module includes an analysis and processing sub-module and a judgment and processing sub-module;

[0015] The analysis and processing sub-module is used to obtain air quality data based on the air warning model.

[0016] The judgment and processing sub-module is used to judge whether the air quality data exceeds a preset threshold. If it exceeds, an excess signal is sent to the second data processing module.

[0017] As a further solution of the present invention, the air warning model is the GAFSA-SVM model.

[0018] As a further solution of the present invention, the processing steps of the air warning model include:

[0019] Set model parameters;

[0020] Match each influencing factor column on the t-th day in the air component data subset with the (t + 1)-th warning column to form a warning on the t-th day for the (t + 1)-th day, and obtain the air component data set to be processed.

[0021] Substitute the air component data set to be processed into the SVM model to obtain the original parameter combination to form an optimization objective function, and the current accuracy rate, and initialize each parameter in GAFSA.

[0022] Substitute the optimized objective function into the GAFSA model, perform basic behaviors respectively, obtain the next moving points of the artificial fish in each behavior, compare the reference values of each point, and preferentially select the point with a larger value as the next moving point of the artificial fish, and update it to the bulletin board;

[0023] Loop until the iteration times are reached, output the parameter combination in the optimized objective function, and substitute it into the SVM model again for prediction, and output the air quality data.

[0024] As a further solution of the present invention, the second data processing module includes a classification model establishment sub-module and a prediction module;

[0025] The classification model establishment sub-module is used to establish a classification model based on the pre-acquired historical meteorological data;

[0026] The prediction module uses the classification model and the pre-acquired historical air pollution data to predict the change trend of air quality to obtain trend data.

[0027] As a further solution of the present invention, the classification model establishment sub-module includes a historical data acquisition unit and a model establishment unit;

[0028] The historical data acquisition unit is used to acquire historical meteorological data;

[0029] The model establishment unit is used to select classification factors from the acquired historical meteorological data as the data to be clustered, filter the data to be clustered; cluster the filtered data to be clustered, establish an initial classification model, and optimize the initial classification model to obtain a classification model.

[0030] As a further solution of the present invention, the prediction module includes an association unit and a prediction unit;

[0031] The association unit is used to determine the association relationship between the weather type and the air pollution status based on the historical air pollution data;

[0032] The prediction unit is used to predict the change trend of air quality based on the association relationship to obtain trend data within the next 7 days.

[0033] As a further solution of the present invention, the data display processing module includes a storage sub-module and a display sub-module.

[0034] The storage sub-module is used to connect to the monitoring micro-station, the data preprocessing module, the first data processing module and the second data processing module, and store the data generated by each module;

[0035] The display sub-module is used to display the data stored in the storage sub-module.

[0036] The technical solution provided by the present invention has the following beneficial effects:

[0037] The present invention collects various air component parameters at each position through a monitoring microsite to obtain various air component parameter datasets. Then, a data preprocessing module normalizes the various air component parameter datasets and cleans them to obtain a preprocessed dataset. A first data processing module calculates air quality data based on the preprocessed dataset and determines whether the air quality data exceeds a preset threshold. If it exceeds, an over-signal is sent to a second data processing module. The second data processing module predicts the air quality change trend based on the over-signal and previously obtained historical air pollution data to obtain trend data. Finally, the result is displayed through a data display processing module. The present invention can accurately give an early warning of air quality and accurately analyze the future air quality situation, improving the accuracy of air monitoring.

[0038] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a structural block diagram of an air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0041] Figure 2 It is a structural block diagram of a first data processing module in an air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0042] Figure 3 It is a structural block diagram of a second data processing module in an air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0043] Figure 4 It is a structural block diagram of a sub-module for establishing a classification model in an air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0044] Figure 5 It is a structural block diagram of a prediction module in an air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0045] Figure 6 Block diagram of the data display and processing module in the air quality early warning and forecasting visualization system based on AI technology according to an embodiment of the present invention.

[0046] In the figure: monitoring microsite - 100, data pre - processing module - 200, first data processing module - 300, second data processing module - 400, data display and processing module - 500, analysis and processing sub - module - 301, judgment and processing sub - module - 302, classification model establishment sub - module - 401, prediction module - 402, historical data acquisition unit - 4011, model establishment unit - 4012, association unit - 4021, prediction unit - 4022, storage sub - module - 501, display sub - module - 502. Specific implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] The flowcharts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0049] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0050] Specifically, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0051] In one embodiment, as shown in Figure 1 In the embodiment of the present invention, an air quality early warning and forecasting visualization system based on AI technology is also provided. The system includes a monitoring microsite 100, a data pre - processing module 200, a first data processing module 300, a second data processing module 400, and a data display and processing module 500.

[0052] The monitoring microsite 100 is used to collect various air component parameters at various locations to obtain various air component parameter data sets.

[0053] In an embodiment of the present invention, the air component parameters include PM10 particle concentration, PM2.5 particle concentration, SO2 gas concentration, NO2 gas concentration, CO gas concentration, and O3 gas concentration.

[0054] The data preprocessing module 200 is configured to perform normalization processing on various air component parameter data sets, clean them to obtain a preprocessed data set, and send the preprocessed data set to the first data processing module 300.

[0055] The first data processing module 300 is configured to calculate air quality data based on the preprocessed data set, and determine whether the air quality data exceeds a preset threshold. If it exceeds, an over-signal is sent to the second data processing module 400.

[0056] In an embodiment of the present invention, the first data processing module 300 calculates air quality data based on an air warning model and determines whether the control quality data exceeds a preset threshold.

[0057] In an embodiment of the present invention, see Figure 2 As shown, in an embodiment of the present invention, a structural block diagram of the first data processing module 300 is further provided. The first data processing module 300 includes an analysis and processing sub-module 301 and a judgment and processing sub-module 302;

[0058] The analysis and processing sub-module 301 is configured to obtain air quality data based on the air warning model.

[0059] The judgment and processing sub-module 302 is configured to determine whether the air quality data exceeds a preset threshold. If it exceeds, an over-signal is sent to the second data processing module 400.

[0060] In an embodiment of the present invention, the air warning model is a GAFSA-SVM model.

[0061] The processing steps of the air warning model include:

[0062] S1. Set model parameters; the model parameters include the initial position of the artificial fish, the visual field of the artificial fish, the maximum step length of the artificial fish movement, the maximum number of iterations, the total number of individual artificial fish, the number of attempts, the crowding factor, the penalty coefficient, and the kernel function bandwidth.

[0063] S2. Match each influencing factor column on the t-th day in the air component data subset with the warning column on the (t + 1)-th day to form a warning on the (t + 1)-th day for the t-th day, obtaining a to-be-processed air component data set. t is a natural number.

[0064] S3. Bring the air component dataset to be processed into the SVM model to obtain the original parameter combination to form the optimization objective function and the current accuracy rate, and initialize the parameters in GAFSA.

[0065] S4. Bring the optimization objective function into the GAFSA model, execute the basic behaviors respectively, obtain the next moving points of the artificial fish in each behavior, compare the reference values of each point, and preferentially select the point with a larger value as the next moving point of the artificial fish and update it to the billboard.

[0066] It should be noted that the Support Vector Machine (SVM) maps the features in the low-dimensional space to the high-dimensional space through mapping and constructs a hyperplane in the high-dimensional space, so that the samples on both sides of the hyperplane belong to different categories. SVM is suitable for dealing with classification problems with small data scale, non-linearity, and high dimension.

[0067] It should be noted that the Global Artificial Fish Swarm Algorithm (GAFSA) is an improvement based on the basic artificial fish swarm optimization algorithm. Although the basic artificial fish swarm algorithm can well jump out of the local extreme value and obtain the global optimal solution in the early stage of optimization. However, due to the local nature of the optimization behavior of a single artificial fish, it is easy to fall into the local extreme value in the later stage of optimization and the convergence speed is slow. The global artificial fish swarm optimization algorithm is improved on the basis of the basic algorithm to improve the accuracy and the later convergence speed by searching and expanding the search range, and at the same time introduces new behavior patterns, such as jumping behavior and swallowing behavior, to improve the search efficiency and accuracy.

[0068] In the embodiment of the present invention, the basic behaviors include foraging behavior, schooling behavior, following behavior, random behavior, jumping behavior, and swallowing behavior.

[0069] In the embodiment of the present invention, the foraging behavior is one of the basic behaviors of the artificial fish, and it selects the traveling direction by simulating the artificial fish's perception of the food concentration in the water.

[0070] In the embodiment of the present invention, the schooling behavior is that when fish swim in the water, they will instinctively gather in groups to migrate or avoid danger. The artificial fish swarm optimization algorithm simulates this instinctive behavior, making individual fish move towards the center of the fish swarm, and at the same time defining a crowding factor to avoid overcrowding.

[0071] In the embodiment of the present invention, the following behavior is that the artificial fish swarm optimization algorithm simulates the basic behaviors of fish swarms such as aggregation, dispersion, foraging, and following, where the following behavior is used for optimizing the objective function. When an artificial fish finds a better solution within its neighborhood, other individuals within its neighborhood will follow this individual to achieve a rapid convergence to a better solution.

[0072] In the embodiment of the present invention, the random behavior is a behavior in the artificial fish swarm optimization algorithm, that is, randomly selecting a state within the visual range as the target for movement, which is used to increase the search range of the algorithm and expand the solution space.

[0073] S5. Until the iteration count is reached, output the parameter combination in the optimized objective function, and substitute it into the SVM model again for prediction, and output the air quality data.

[0074] The GAFSA - SVM model in the present invention can accurately predict the air quality data.

[0075] The second data processing module 400 is used to predict the air quality change trend based on the excess signal and the pre - acquired historical air pollution data to obtain trend data. The trend data is used to predict the air quality in the future for a period of time, and the trend data is judged to determine whether the future weather quality exceeds the preset pollution threshold. If it exceeds, a warning signal is issued.

[0076] In the embodiment of the present invention, see Figure 3 As shown, in the embodiment of the present invention, a structural block diagram of the second data processing module 400 is also provided. The second data processing module 400 includes a classification model establishment sub - module 401 and a prediction module 402.

[0077] The classification model establishment sub - module 401 is used to establish a classification model based on the pre - acquired historical meteorological data.

[0078] In the embodiment of the present invention, see Figure 4 As shown, in the embodiment of the present invention, a structural block diagram of the classification model establishment sub - module 401 is also provided. The classification model establishment sub - module 401 includes a historical data acquisition unit 4011 and a model establishment unit 4012.

[0079] The historical data acquisition unit 4011 is used to acquire historical meteorological data.

[0080] The model establishment unit 4012 is used to select classification factors from the acquired historical meteorological data as the data to be clustered, filter the data to be clustered; cluster the filtered data to be clustered to establish an initial classification model, and optimize the initial classification model to obtain a classification model.

[0081] The prediction module 402 uses a classification model and pre-acquired historical air pollution data to predict the changing trend of air quality, so as to obtain trend data for the next 7 days, and judge the trend data to determine whether the future weather quality exceeds a preset pollution threshold. If it exceeds, a warning signal is issued.

[0082] In an embodiment of the present invention, refer to Figure 5 As shown, in the embodiment of the present invention, a structural block diagram of the prediction module 402 is further provided. The prediction module 402 includes an association unit 4021 and a prediction unit 4022.

[0083] The association unit 4021 is used to determine the association relationship between the weather type and the air pollution status based on the historical air pollution data.

[0084] The prediction unit 4022 is used to predict the changing trend of air quality based on the association relationship to obtain trend data.

[0085] The data display and processing module 500 is used to connect to the monitoring microsite 100, the data preprocessing module 200, the first data processing module 300, and the second data processing module 400, and store and display the data generated by each module.

[0086] In an embodiment of the present invention, refer to Figure 6 As shown, in the embodiment of the present invention, a structural block diagram of the data display and processing module 500 is further provided. The data display and processing module 500 includes a storage sub-module 501 and a display sub-module 502.

[0087] The storage sub-module 501 is used to connect to the monitoring microsite 100, the data preprocessing module 200, the first data processing module 300, and the second data processing module 400, and store the data generated by each module;

[0088] The display sub-module 502 is used to display the data stored by the storage sub-module 501.

[0089] The present invention collects various air component parameters at various positions through the monitoring microsite 100 to obtain various air component parameter datasets. Then, the data preprocessing module 200 performs normalization processing on the various air component parameter datasets and cleans them to obtain a preprocessed dataset. The first data processing module 300 calculates air quality data based on the preprocessed dataset and determines whether the air quality data exceeds a preset threshold. If it exceeds, it sends an over-signal to the second data processing module 400. The second data processing module 400 predicts the air quality change trend based on the over-signal and the previously obtained historical air pollution data to obtain trend data. Finally, the data display processing module 500 displays the results. The present invention can accurately give an early warning of air quality and accurately analyze the future air quality situation, improving the accuracy of air monitoring.

[0090] It should be understood that, as used herein, unless the context clearly supports the exception, the singular form "a" is also intended to include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the associated listed items. The serial numbers of the disclosed embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0091] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features between the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.

Claims

1. An air quality early warning and forecasting visualization system based on AI technology, characterized in that, The system includes: a monitoring microsite, a data preprocessing module, a first data processing module, a second data processing module, and a data display and processing module; The monitoring microsite is used to collect various air component parameters at each location to obtain various air component parameter datasets; The data preprocessing module is used to perform normalization processing on various air component parameter datasets, clean them to obtain a preprocessed dataset, and send the preprocessed dataset to the first data processing module; The first data processing module is used to calculate air quality data based on the preprocessed dataset, and determine whether the air quality data exceeds a preset threshold. If it exceeds, it sends an over-signal to the second data processing module; The second data processing module is used to predict the air quality change trend based on the over-signal and the previously obtained historical air pollution data to obtain trend data. The trend data is used to predict the air quality in a future period of time, judge the trend data, and determine whether the future weather quality exceeds a preset pollution threshold. If it exceeds, it sends a warning signal; The data display and processing module is used to connect to the monitoring microsite, the data preprocessing module, the first data processing module, and the second data processing module, and store and display the data generated by each module.

2. The visualization system for air quality early warning and forecasting based on AI technology according to claim 1, wherein The air component parameters include PM10 particle concentration, PM2.5 particle concentration, SO2 gas concentration, NO2 gas concentration, CO gas concentration, and O3 gas concentration.

3. The air quality early warning and forecasting visualization system based on AI technology according to claim 1, characterized in that The first data processing module calculates air quality data based on the air warning model and determines whether the control quality data exceeds a preset threshold.

4. The air quality early warning and forecasting visualization system based on AI technology according to claim 3, wherein The first data processing module includes an analysis and processing sub-module and a judgment and processing sub-module; The analysis and processing sub-module is used to obtain air quality data based on the air warning model. The judgment and processing sub-module is used to determine whether the air quality data exceeds a preset threshold. If it exceeds, it sends an over-signal to the second data processing module.

5. The visualization system for air quality early warning and forecasting based on AI technology according to claim 3, characterized in that, The air warning model is the GAFSA-SVM model.

6. The visualization system for air quality early warning and forecasting based on AI technology according to claim 5, wherein The processing steps of the air warning model include: Setting model parameters; Matching the influencing factor columns on the t-th day in the air component data subset with the warning column on the (t + 1)-th day to form a warning on the t-th day for the (t + 1)-th day, obtaining a to-be-processed air component dataset. Bringing the to-be-processed air component dataset into the SVM model to obtain the original parameter combination to form an optimization objective function, and the current accuracy rate, and initializing the parameters in GAFSA. Bringing the optimization objective function into the GAFSA model, respectively performing basic behaviors to obtain the next moving point of the artificial fish in each behavior, comparing the reference values of each point, preferentially taking the point with a larger value as the next moving point of the artificial fish, and updating it to the bulletin board; Until the iteration times are reached, output the parameter combination in the optimization objective function, and bring it into the SVM model again for prediction, and output the air quality data.

7. The air quality early warning and forecasting visualization system based on AI technology according to claim 2, characterized in that, The second data processing module includes a classification model establishment sub-module and a prediction module; The classification model establishment sub-module is used to establish a classification model based on the previously obtained historical meteorological data; The prediction module uses a classification model and pre-acquired historical air pollution data to predict the changing trend of air quality to obtain trend data.

8. The visualization system for air quality early warning and forecasting based on AI technology according to claim 7, characterized in that, The sub-module for establishing the classification model includes a historical data acquisition unit and a model establishment unit; The historical data acquisition unit is used to acquire historical meteorological data; The model establishment unit is used to select classification factors from the acquired historical meteorological data as data to be clustered, and filter the data to be clustered; Cluster the filtered data to be clustered, establish an initial classification model, and optimize the initial classification model to obtain a classification model.

9. The air quality early warning and forecasting visualization system based on AI technology according to claim 7, characterized in that, The prediction module includes a correlation unit and a prediction unit; The correlation unit is used to determine the correlation relationship between weather types and air pollution conditions based on historical air pollution data; The prediction unit is used to predict the changing trend of air quality based on the correlation relationship to obtain trend data.

10. The air quality early warning and forecasting visualization system based on AI technology according to claim 1, wherein The data display and processing module includes a storage sub-module and a display sub-module. The storage sub-module is used to connect to the monitoring microsite, the data preprocessing module, the first data processing module, and the second data processing module, and store the data generated by each module; The display sub-module is used to display the data stored by the storage sub-module.

Images