Atmospheric pollution monitoring method, device, equipment, storage medium and product

By adaptively adjusting the working parameters of the acquisition equipment and using multi-scale feature extraction and neural network models, the problem of real-time and low efficiency of air pollution monitoring in the existing technology is solved, and rapid response and efficient monitoring of air pollution situations are achieved. .

CN119086818AActive Publication Date: 2024-12-06CHINA MOBILE GROUP ANHUI +1

Patent Information

Application Number
CN202411180845.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-12-06
Estimated Expiration
2044-08-26

AI Technical Summary

Technical Problem

Existing air pollution monitoring technologies are difficult to respond quickly to environmental changes, and their real-time and data capture efficiency are low, so they cannot quickly determine air pollution.

Method used

Through adaptive adjustment of working parameters by the acquisition equipment, the gradient descent method is used to optimize the adjustment coefficient, and combined with wavelet decomposition and neural network model, multi-scale feature extraction and prediction of atmospheric pollutant concentration data is achieved, improving data acquisition efficiency and accuracy.

Benefits of technology

It realizes rapid response and efficient monitoring of air pollution, improves data collection efficiency and accuracy, and can allocate system resources more reasonably and adapt to environmental changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086818A_ABST
    Figure CN119086818A_ABST
Patent Text Reader

Abstract

The invention provides an atmospheric pollution monitoring method, device and equipment, a storage medium and a product. The method comprises the following steps: carrying out atmospheric data acquisition based on working parameters through acquisition equipment to obtain atmospheric pollutant concentration data within a preset time range; according to statistical characteristics of the atmospheric pollutant concentration data in the set time range, the working parameters are subjected to self-adaptive adjustment according to adjustment coefficients, and the working parameters after self-adaptive adjustment correspond to the statistical characteristics; under the condition that the working parameters of the acquisition equipment are adjusted, calculating a first performance index value corresponding to an atmospheric data acquisition process; and according to the first performance index value, optimizing the adjustment coefficient through a gradient descent method, so that a second performance index value of the corresponding data acquisition process is greater than the first performance index value under the condition that the working parameters are adjusted based on the optimized adjustment coefficient.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring technology, and in particular to an air pollution monitoring method, device, equipment, storage medium and product. Background Art

[0002] With the rapid development of industry, transportation and other industries, especially the large-scale use of coal and oil, air pollution has become a major concern of people. Therefore, air pollution monitoring technology has also begun to develop gradually. Air pollution monitoring refers to the process of determining the types and concentrations of pollutants in the atmosphere and observing their temporal and spatial distribution and change patterns. The purpose of air pollution monitoring is to identify pollutants in the atmosphere, understand their distribution and diffusion patterns, and monitor the emission and control of air pollution sources.

[0003] In the existing technology, air pollution monitoring mainly relies on monitoring equipment at fixed sites, but air pollutants may contain a variety of different components and change with time and environmental conditions. Traditional monitoring methods may not be able to effectively capture these complex data characteristics when using fixed monitoring equipment and monitoring according to preset working parameters. The real-time performance of air pollution monitoring is not high, and it is impossible to quickly determine the air pollution situation. Summary of the invention

[0004] The embodiments of the present application provide an air pollution monitoring method, device, equipment, storage medium and product, which can quickly respond to environmental changes and determine the air pollution situation.

[0005] In a first aspect, the present application provides an air pollution monitoring method, comprising:

[0006] The atmospheric data is collected by the collection equipment based on the working parameters to obtain the atmospheric pollutant concentration data within the preset time range;

[0007] According to the statistical characteristics of the atmospheric pollutant concentration data within the set time range, the operating parameters are adaptively adjusted according to the adjustment coefficient, and the adaptively adjusted operating parameters correspond to the statistical characteristics;

[0008] When the working parameters of the acquisition device are adjusted, calculating a first performance indicator value corresponding to the atmospheric data acquisition process;

[0009] According to the first performance indicator value, the adjustment coefficient is optimized by gradient descent method, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

[0010] In some possible implementations, the air data collection is performed based on working parameters by a collection device to obtain air pollutant concentration data within a preset time range, including:

[0011] Collect the pollutant concentration values ​​corresponding to each time point within the preset time range through the collection equipment according to the working parameters;

[0012] Calculate the average value of the pollutant concentration values ​​corresponding to each time point to obtain the mean pollutant concentration;

[0013] Calculate the square value of the difference between the pollutant concentration value corresponding to each time point and the mean pollutant concentration;

[0014] Calculate the average of each of the squares, take the square root of the average of the squares, and obtain the standard deviation of the pollutant concentration;

[0015] Determining a pollutant concentration change trend according to the rate at which each pollutant concentration value changes over time;

[0016] The pollutant concentration values ​​corresponding to the various time points, the pollutant concentration mean, the pollutant concentration standard deviation and the pollutant concentration change trend are used as atmospheric pollutant concentration data within a preset time range.

[0017] In some possible implementations, the operating parameters include sampling frequency, quantization accuracy, and data compression rate, and the adaptively adjusting the operating parameters according to the adjustment coefficient based on the statistical characteristics of the atmospheric pollutant concentration data within the set time range includes:

[0018] Determine the sampling frequency increase value according to the adjustment coefficient, the standard deviation of the pollutant concentration and the pollutant concentration change trend;

[0019] Determine a target sampling frequency according to a preset basic sampling frequency and the sampling frequency boost value, and adjust the sampling frequency to the target sampling frequency;

[0020] Adjust the quantification accuracy according to the current pollutant concentration value and the extreme pollutant concentration value within the preset time range;

[0021] The data compression rate is adjusted according to the ratio of the pollutant concentration to the preset standard deviation.

[0022] In some possible implementations, after the atmospheric data is collected by the collection device based on the working parameters to obtain atmospheric pollutant concentration data within a preset time range, the method further includes:

[0023] Performing wavelet decomposition on the atmospheric pollutant concentration data by using a preset wavelet basis function to obtain wavelet coefficients, wherein the wavelet coefficients represent local characteristics of the atmospheric pollutant concentration data at multiple different scales;

[0024] Extracting features from the wavelet coefficients to obtain pollutant concentration features at multiple different scales;

[0025] Combining the pollutant concentration features at multiple different scales to obtain multi-scale fusion features;

[0026] The multi-scale fusion features are input into a preset prediction model to obtain atmospheric pollutant concentration prediction data corresponding to a preset time, where the preset time is later than the preset time range.

[0027] In some possible implementations, performing wavelet decomposition on the atmospheric pollutant concentration data by using a preset wavelet basis function to obtain wavelet coefficients includes:

[0028] Obtain the decomposition scale corresponding to the preset wavelet basis function;

[0029] According to the decomposition scale corresponding to the preset wavelet basis function, the atmospheric pollutant concentration data is subjected to wavelet decomposition to obtain initial wavelet coefficients;

[0030] Performing statistical analysis on the initial wavelet coefficients to determine statistical characteristics of the initial wavelet coefficients;

[0031] The initial wavelet coefficients are denoised based on a threshold value corresponding to the statistical feature to obtain wavelet coefficients.

[0032] In some possible implementations, after optimizing the adjustment coefficient by a gradient descent method according to the first performance indicator value, the method further includes:

[0033] Adjusting working parameters based on the optimized adjustment coefficients;

[0034] collecting pollutant concentration data according to the working parameters;

[0035] Combining the pollutant concentration data, geographic data and meteorological data to obtain environmental fusion data;

[0036] The environmental fusion data is processed by a preset neural network model to obtain an atmospheric pollution analysis result.

[0037] In some possible implementations, the preset neural network model includes a convolutional neural network, a graph neural network, a long short-term memory network, and a fully connected network. The environmental fusion data is processed by the preset neural network model to obtain an atmospheric pollution analysis result, including:

[0038] Extracting features from the environment fusion data by using the convolutional neural network to obtain spatiotemporal features of the environment fusion data;

[0039] Extracting features from the environmental fusion data through the graph neural network to obtain pollution diffusion features of the environmental fusion data;

[0040] Inputting the spatiotemporal characteristics and the pollution diffusion characteristics into the long short-term memory network to obtain the temporal dependence characteristics of air pollution;

[0041] The time-dependent features are input into the fully connected network to obtain air pollution analysis results.

[0042] In some possible implementations, calculating a first performance indicator value corresponding to an atmospheric data collection process when the working parameter of the collection device is adjusted includes:

[0043] When the working parameters are adjusted, obtaining data quality index values, energy consumption and data transmission volume during data collection;

[0044] A weighted sum is taken for the data quality index value, the energy consumption amount and the data transmission amount to obtain a first performance index value corresponding to the data collection process.

[0045] In a second aspect, the present application provides an air pollution monitoring device, the device comprising:

[0046] The acquisition module is used to acquire atmospheric data based on working parameters through acquisition equipment to obtain atmospheric pollutant concentration data within a preset time range;

[0047] An adjustment module, configured to adaptively adjust the operating parameters according to the statistical characteristics of the atmospheric pollutant concentration data within the set time range according to the adjustment coefficient, wherein the adaptively adjusted operating parameters correspond to the statistical characteristics;

[0048] A calculation module, used for calculating a first performance indicator value corresponding to an atmospheric data collection process when the working parameters of the collection device are adjusted;

[0049] The optimization module is used to optimize the adjustment coefficient by gradient descent method according to the first performance indicator value, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

[0050] In a third aspect, the present application provides an air pollution monitoring device, comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the air pollution monitoring method described above.

[0051] In a fourth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions, when executed by a processor, implement the air pollution monitoring method as described above.

[0052] In a fifth aspect, the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device performs the air pollution monitoring method described above.

[0053] The air pollution monitoring method, device, equipment, storage medium and product provided in the embodiments of the present application adjust the working parameters of the collection equipment according to the real-time air pollutant concentration data and the adjustment coefficient, so that the system resources in the collection process can be more reasonably allocated and the collection efficiency can be improved. Further, the corresponding first performance index value is calculated, and the adjustment coefficient is optimized according to the first performance index value, and the adjustment coefficient is continuously optimized in continuous iterations. Since the working parameters will be adjusted according to the actual atmospheric conditions to adapt to the current actual situation, the adjusted collection working parameters can be used to more efficiently collect changes in the concentration of air pollutants based on the actual environment, and can quickly respond to environmental changes, and then quickly determine the air pollution situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present application can be better understood from the following description of the specific embodiments of the present application in conjunction with the accompanying drawings, in which:

[0055] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features.

[0056] Figure 1 is a flow chart of an air pollution monitoring method provided by an embodiment of the present application;

[0057] Figure 2 is a flow chart of an environmental data extraction process provided by an embodiment of the present application;

[0058] Figure 3 is a flowchart of a multi-source data fusion mining process provided by an embodiment of the present application;

[0059] Figure 4is a structural schematic diagram of an air pollution monitoring device provided by an embodiment of the present application;

[0060] Figure 5 It is a schematic diagram of the hardware structure of the air pollution monitoring device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0061] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0062] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0063] Integrated Sensing and Communication (ISAC): A technology that uses the same frequency band and hardware for perception and communication. It can fully share the multi-dimensional resources of time, space, etc. of wireless communication and radar perception, and realize the coexistence and mutual assistance of the two technologies.

[0064] In this embodiment, the ISAC device performs environmental monitoring. Specifically, in the ISAC device, the environmental monitoring sensor uses a high-sensitivity, low-power, miniaturized laser radar, electrochemical and other sensors to monitor the concentration of air pollutants such as PM2.5, CO, SO2, and NO2 in real time.

[0065] Design a joint processing circuit for RF signals and environmental perception signals to efficiently separate and extract the two types of signals. After filtering, amplification, down-conversion and other processing, the RF communication signal is sent to the baseband processing unit for communication demodulation; the environmental perception signal is filtered, amplified, and AD converted through a dedicated signal conditioning circuit, and then sent to the environmental signal processing unit for feature extraction and concentration calculation.

[0066] According to the communication business volume and environmental monitoring needs, the allocation ratio of radio frequency resources and computing resources between communication and perception tasks is dynamically configured. During peak communication periods, priority is given to ensuring communication quality; during idle communication periods, more resources are used for the collection and processing of environmental monitoring data to improve the monitoring time resolution.

[0067] In order to solve the problems of the prior art, the embodiments of the present application provide an air pollution monitoring method, device, equipment, storage medium and product. The air pollution monitoring method provided by the embodiments of the present application is first introduced below, and this method can be performed by the above-mentioned air pollution monitoring device.

[0068] Figure 1 FIG. 1 is a flow chart of an air pollution monitoring method provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps S101 to S105.

[0069] Step S101: collecting atmospheric data based on working parameters through a collection device to obtain atmospheric pollutant concentration data within a preset time range.

[0070] In a specific implementation, the collection device is preset with working parameters, which may specifically include sampling frequency, sensor sensitivity, etc. Data collection is performed according to a preset time range, and the collection device continuously measures and records the concentration of air pollutants to obtain air pollutant concentration data within the preset time range.

[0071] Step S102: According to the statistical characteristics of the above-mentioned atmospheric pollutant concentration data within the above-mentioned set time range, the above-mentioned working parameters are adaptively adjusted according to the adjustment coefficient, and the above-mentioned working parameters after adaptive adjustment correspond to the above-mentioned statistical characteristics.

[0072] In a specific implementation, the data collected in S101 is statistically analyzed to calculate the statistical characteristics of the data, such as the mean, variance, etc. An adjustment coefficient is set based on the statistical characteristics of the data to adjust the working parameters. The working parameters are adaptively adjusted according to the calculated adjustment coefficient.

[0073] As another example, if the data variance is large, the sensitivity or sampling frequency of the sensor can be adjusted to improve the data quality.

[0074] Step S103: Calculate a first performance indicator value corresponding to the atmospheric data collection process after adjusting the working parameters of the collection device.

[0075] In a specific implementation, in order to evaluate the adjusted collection effect so as to optimize the adjustment coefficient, data collection is performed again under the adjusted working parameters, and the first performance indicator value is calculated based on the newly collected data.

[0076] As another example, when calculating the first performance indicator value, indicators such as accuracy and stability of the data may be calculated.

[0077] Step S104: According to the first performance indicator value, the adjustment coefficient is optimized by the gradient descent method, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

[0078] In a specific implementation, an objective function is set, the first performance indicator value is used as part of the objective function, and an optimization target is set, for example, the second performance indicator value should be greater than the first performance indicator value. Based on the objective function, the gradient of the adjustment coefficient is calculated, and the gradient descent step is repeated according to the gradient adjustment coefficient until the objective function value meets the optimization requirements, thereby completing the optimization of the adjustment coefficient.

[0079] The air pollution monitoring method provided in the embodiment of the present application adjusts the working parameters of the collection equipment according to the real-time air pollutant concentration data and the adjustment coefficient, so that the system resources in the collection process can be more reasonably allocated and the collection efficiency can be improved. Further, the corresponding first performance index value is calculated, and the adjustment coefficient is optimized according to the first performance index value, and the adjustment coefficient is continuously optimized in continuous iteration. Since the working parameters will be adjusted according to the actual atmospheric conditions to adapt to the current actual situation, the adjusted collection working parameters can be used to more efficiently collect changes in the concentration of air pollutants based on the actual environment, and can quickly respond to environmental changes, and then quickly determine the air pollution situation.

[0080] In order to allow the atmospheric pollutant concentration data to fully reflect the actual situation of atmospheric pollution, in some embodiments, the above S101 includes steps A1 to F1:

[0081] Step A1: Collect the pollutant concentration values ​​corresponding to each time point within a preset time range through the collection device according to the working parameters.

[0082] In the specific implementation, first, configure the collection equipment and set the working parameters, such as sampling frequency, sampling time interval, sensor sensitivity, etc. Start the equipment to start collecting data, ensure continuous sampling at the set frequency within the preset time range, and record the pollutant concentration value at each time point.

[0083] Step B1: Calculate the average value of the pollutant concentration corresponding to each of the above time points to obtain the mean pollutant concentration.

[0084] In a specific implementation, the concentration values ​​of the pollutant concentration values ​​corresponding to the above-mentioned various time points are added together to obtain the total concentration, and the total concentration is divided by the number of time points to obtain the mean pollutant concentration.

[0085] Step C1: Calculate the square value of the difference between the above pollutant concentration value corresponding to each time point and the above pollutant concentration mean value.

[0086] In a specific implementation, for each pollutant concentration value at each time point, the difference between it and the mean is calculated, and each deviation value is squared to obtain the square value of the difference between the above pollutant concentration value corresponding to each time point and the above pollutant concentration mean.

[0087] Step D1: Calculate the average of each of the above squares, take the square root of the average of the above squares, and obtain the standard deviation of the pollutant concentration.

[0088] In a specific implementation, the square values ​​of the deviations at all time points are summed up, and their average value is calculated. The square root of the square average value is taken to obtain the standard deviation of the pollutant concentration.

[0089] Step E1: Determine the pollutant concentration change trend according to the rate at which the above-mentioned pollutant concentration values ​​change over time.

[0090] In the specific implementation, linear regression or other trend analysis methods are used to fit the time series data, calculate the slope of the regression line, and determine the trend of pollutant concentration changes according to the slope of the regression line.

[0091] Step F1: The pollutant concentration values ​​corresponding to the above-mentioned various time points, the above-mentioned pollutant concentration mean value, the above-mentioned pollutant concentration standard deviation and the above-mentioned pollutant concentration change trend are used as the atmospheric pollutant concentration data within a preset time range.

[0092] The above-mentioned implementation method of the embodiment of the present application collects the pollutant concentration values ​​corresponding to each time point within a preset time range through the collection equipment according to the working parameters, and then calculates the concentration mean and standard deviation of each pollutant concentration value, and then uses the pollutant concentration values ​​corresponding to the above-mentioned each time point, the above-mentioned pollutant concentration mean, the above-mentioned pollutant concentration standard deviation and the above-mentioned pollutant concentration change trend as the atmospheric pollutant concentration data within the preset time range, and comprehensively utilizes multiple data as the atmospheric pollutant concentration data within the preset time range, so that the atmospheric pollutant concentration data can comprehensively reflect the actual situation of air pollution.

[0093] In order to accurately adjust various working parameters, in some implementations, the working parameters include sampling frequency, quantization accuracy and data compression rate. The step S102 includes steps A2 to D2:

[0094] Step A2: Determine the sampling frequency increase value according to the adjustment coefficient, the standard deviation of the above pollutant concentration and the change trend of the above pollutant concentration.

[0095] In the specific implementation, the adjustment coefficient and the standard deviation of the pollutant concentration calculated from step D1 are first obtained, which reflects the discrete degree of the data, and the trend of the pollutant concentration obtained from step E1. The sampling frequency increase value is determined based on the above information. For example, if the pollutant concentration has increased significantly, the sampling frequency is appropriately increased; if it decreases or stabilizes, the sampling frequency can be maintained or appropriately reduced.

[0096] Step B2: determining a target sampling frequency according to a preset basic sampling frequency and the sampling frequency boost value, and adjusting the sampling frequency to the target sampling frequency.

[0097] In a specific implementation, the current basic sampling frequency is obtained, the basic sampling frequency is added with the sampling frequency boost value to obtain the target sampling frequency, and the calculated target sampling frequency is applied to adjust the sampling frequency to the above target sampling frequency.

[0098] As another example, after the target sampling frequency is calculated, it can be checked whether the new target sampling frequency is within the range allowed by the device. If it is exceeded, corresponding measures are taken, such as returning to the default maximum or minimum frequency.

[0099] Step C2: adjusting the quantification accuracy according to the current pollutant concentration value and the extreme value of the pollutant concentration within a preset time range.

[0100] In the specific implementation, the extreme values ​​of pollutant concentration within the preset time range are calculated, including the maximum and minimum values. The new quantization accuracy is determined based on the relationship between the current concentration value and the extreme value. For example, the closer the current concentration value is to the extreme value, the higher the quantization accuracy is. Based on the new quantization accuracy, the quantization accuracy is adjusted.

[0101] Step D2: adjusting the data compression rate according to the ratio of the above pollutant concentration to the preset standard deviation.

[0102] In the specific implementation, the ratio of the current pollutant concentration value to the standard deviation is calculated. If the ratio is greater than the preset threshold, the compression rate can be increased to reduce storage requirements. If the ratio is close to 1 or lower than 1, the compression rate is reduced to retain more data details, thereby adjusting the data compression rate.

[0103] The above implementation method of the embodiment of the present application adjusts the sampling frequency according to the adjustment coefficient, the above pollutant concentration standard deviation and the above pollutant concentration change trend, adjusts the quantization accuracy based on the current pollutant concentration value and the extreme pollutant concentration within a preset time range, and adjusts the data compression rate according to the ratio of the above pollutant concentration to the preset standard deviation, so as to accurately adjust various working parameters.

[0104] In order to obtain accurate atmospheric pollutant concentration prediction data, in some embodiments, the above S101 includes steps A3 to D3:

[0105] Step A3: performing wavelet decomposition on the above-mentioned atmospheric pollutant concentration data by using a preset wavelet basis function to obtain wavelet coefficients, wherein the wavelet coefficients represent the local characteristics of the above-mentioned atmospheric pollutant concentration data at multiple different scales.

[0106] In the specific implementation, the time series data of atmospheric pollutant concentration is obtained. These data usually exist in the form of time series, such as hourly or daily pollutant concentration values. Based on the characteristics of the scene and data, the preset wavelet basis function is determined, and the selected wavelet basis function is used to perform wavelet transform on the pollutant concentration data to obtain the wavelet coefficients.

[0107] As another example, the wavelet transform process involves decomposing the original time series data into coefficients of different frequency components. Specifically, the wavelet transform decomposes the data into approximate coefficients (low frequency) and detail coefficients (high frequency), layer by layer to obtain information at different scales. Each decomposition layer generates a set of wavelet coefficients that represent the characteristics of the data at different scales.

[0108] Step B3: Extract features from the above wavelet coefficients to obtain pollutant concentration features at multiple different scales.

[0109] In the specific implementation, the appropriate feature type is selected according to the analysis purpose, and the selected features are calculated for the wavelet coefficients at each scale to obtain the pollutant concentration characteristics at multiple different scales.

[0110] As another example, the features that may be extracted include: statistical features, such as mean, variance, kurtosis, skewness, etc. Spectral characteristics of wavelet coefficients, such as frequency domain amplitude, etc. Local features, such as local extreme points, change points, etc.

[0111] Step C3: Combine the above pollutant concentration features at multiple different scales to obtain multi-scale fusion features.

[0112] In the specific implementation, the features of each scale are combined into a comprehensive feature set according to a preset method to obtain multi-scale fusion features.

[0113] Step D3: Input the multi-scale fusion features into a preset prediction model to obtain atmospheric pollutant concentration prediction data corresponding to a preset time, where the preset time is later than the preset time range.

[0114] In the specific implementation, the multi-scale fusion feature data is input into the prediction model, the prediction operation is performed, and the model is used to infer the given feature data to predict the atmospheric pollutant concentration at the future time, and the atmospheric pollutant concentration prediction data corresponding to the preset time is obtained. For example, if the model is a regression model, a continuous concentration prediction value is generated; if it is a classification model, a prediction of the pollution level may be output.

[0115] The above-mentioned implementation method of the embodiment of the present application performs wavelet decomposition on the above-mentioned atmospheric pollutant concentration data through a preset wavelet basis function to obtain wavelet coefficients, and then performs feature extraction on the above-mentioned wavelet coefficients to obtain multi-scale fusion features, and uses a preset prediction model to process based on this multi-scale fusion feature to obtain the atmospheric pollutant concentration prediction data corresponding to the preset time. Using wavelet decomposition and multi-scale feature fusion as concentration prediction data can obtain accurate atmospheric pollutant concentration prediction data.

[0116] In order to obtain more accurate wavelet coefficients, in some implementations, the above A3 includes steps A31 to A32:

[0117] Step A31 obtains the decomposition scale corresponding to the preset wavelet basis function.

[0118] In a specific implementation, the decomposition scale is set according to the properties of the preset wavelet basis function. For example, for the Daubechies wavelet, 8 levels of decomposition may be selected. Each scale represents a different frequency component of the data.

[0119] Step A32 performs wavelet decomposition on the above-mentioned atmospheric pollutant concentration data according to the decomposition scale corresponding to the above-mentioned preset wavelet basis function to obtain initial wavelet coefficients.

[0120] In the specific implementation, the data is decomposed according to the preset decomposition scale. Each level generates wavelet coefficients of different frequency ranges, the data is applied with wavelet basis functions, and the wavelet coefficients of each level are calculated through convolution operations to obtain approximate coefficients and detail coefficients, and obtain the initial wavelet coefficients.

[0121] Step A33 performs statistical analysis on the initial wavelet coefficients to determine the statistical characteristics of the initial wavelet coefficients.

[0122] In the specific implementation, the statistical characteristics of the wavelet coefficients at each scale are calculated, such as mean, variance, kurtosis, skewness, etc., to determine the statistical characteristics of the initial wavelet coefficients. These characteristics describe the distribution and variation characteristics of the data.

[0123] Step A34 performs denoising on the initial wavelet coefficients based on the threshold corresponding to the above statistical features to obtain wavelet coefficients.

[0124] In a specific implementation, according to the statistical features in step A33, a suitable threshold is selected, including a soft threshold and a hard threshold. In the soft threshold denoising process, the coefficients whose absolute values ​​of the wavelet coefficients are lower than the threshold are set to zero, and the threshold is subtracted from the remaining coefficients. In the hard threshold denoising process, the coefficients whose absolute values ​​of the wavelet coefficients are lower than the threshold are set to zero, and the remaining coefficients remain unchanged. After the denoising process is completed, the wavelet coefficients are obtained.

[0125] The above implementation of the embodiment of the present application obtains the decomposition scale corresponding to the preset wavelet basis function, and then performs wavelet decomposition on the above atmospheric pollutant concentration data according to the decomposition scale, and then denoises the initial wavelet coefficients to remove useless information therein, so as to obtain more accurate wavelet coefficients.

[0126] In order to obtain accurate atmospheric pollution analysis results, in some embodiments, after the above S104, the above method further includes steps A4 to D4:

[0127] Step A4: Adjust the operating parameters based on the optimized adjustment coefficients.

[0128] In a specific implementation, the relevant working parameters are updated according to the optimized adjustment coefficients, thereby adjusting the working parameters.

[0129] As another example, for example, the sensitivity setting of the sensor can be adjusted to improve the measurement accuracy of the pollutant concentration. Alternatively, the frequency of data collection can be adjusted according to the optimization coefficient to ensure the timeliness and accuracy of the data.

[0130] Step B4: Collect pollutant concentration data according to the above working parameters.

[0131] In the specific implementation, the device is equipped to collect pollutant concentration data in the atmosphere according to adjustment parameters.

[0132] Step C4: Combine the above pollutant concentration data, geographic data and meteorological data to obtain environmental fusion data.

[0133] Geographic data may include information such as geographic location and topography, which may be obtained through map services or geographic information systems (GIS).

[0134] Meteorological data may include data on meteorological conditions such as temperature, humidity, and wind speed.

[0135] In a specific implementation, these data are matched in time and space, and the matched data are merged to generate environmental fusion data.

[0136] Step D4: Process the above environmental fusion data through a preset neural network model to obtain air pollution analysis results.

[0137] In the specific implementation, the environmental fusion data is converted into a format suitable for the neural network model input, the preset neural network model is loaded, and the prepared environmental fusion data is input into the neural network model. The input data is processed by the neural network model to calculate the predicted value or analysis result of air pollution. Finally, the analysis results are extracted from the model output, such as pollutant concentration prediction, pollution trend, etc.

[0138] The above implementation method of the embodiment of the present application adjusts the working parameters through the adjustment coefficient after optimizing the adjustment coefficient, uses the above working parameters to collect pollutant concentration data, and combines the collected pollutant concentration data with geographical data and meteorological data to obtain environmental fusion data that comprehensively reflects the environmental conditions. Thereafter, the above environmental fusion data is processed using a preset neural network model to obtain accurate atmospheric pollution analysis results.

[0139] In order to obtain accurate air pollution analysis results, in some embodiments, the preset neural network model includes a convolutional neural network, a graph neural network, a long short-term memory network and a fully connected network, and the above D4 includes steps D41 to D44:

[0140] Step D41: extracting features from the above-mentioned environment fusion data through the above-mentioned convolutional neural network to obtain the spatiotemporal features of the above-mentioned environment fusion data.

[0141] In the specific implementation, environmental fusion data has been combined with pollutant concentration, geographic information and meteorological data. The data is usually represented in the form of a matrix, which contains time series, spatial location information and corresponding environmental variables. The convolution operation is applied to extract the spatial features in the data, and the convolution kernel scans the spatial dimension of the environmental fusion data to extract local features. The convolution operation extracts the spatial features of the data and generates spatiotemporal features in combination with the time series information. These features can represent the pollutant concentration pattern and its changing trend at different time points and spatial locations.

[0142] As another example, input data can be standardized or normalized so that a convolutional neural network can better process it.

[0143] Step D42: extract features from the environmental fusion data through the graph neural network to obtain pollution diffusion features of the environmental fusion data.

[0144] In the specific implementation, the environmental fusion data is converted into a graph structure, and feature vectors are assigned to each node in the graph. These vectors usually include pollutant concentrations, meteorological data, etc. The graph data is processed by applying a graph convolution operation, and the feature representation of the node is updated through the graph convolution layer, so that the feature of each node contains the information of its neighboring nodes, thereby better capturing the spatial characteristics of pollution diffusion and obtaining the pollution diffusion characteristics of the above environmental fusion data.

[0145] Step D43: Input the above-mentioned spatiotemporal characteristics and the above-mentioned pollution diffusion characteristics into the above-mentioned long short-term memory network to obtain the time-dependent characteristics of air pollution.

[0146] In the specific implementation, the spatiotemporal features extracted by the convolutional neural network are fused with the pollution diffusion features extracted by the graph neural network, for example, the two feature sets are merged into a larger feature vector or matrix. The fused feature vector is input to the Long Short-Term Memory (LSTM) layer. The LSTM network processes the fused features and extracts the time-dependent features to obtain the time-dependent features of air pollution. These features represent the change pattern of air pollution over time and its long-term trend.

[0147] Step D44: Input the above-mentioned time-dependent features into the above-mentioned fully connected network to obtain the atmospheric pollution analysis results.

[0148] In the specific implementation, the time-dependent features obtained from the LSTM network are used as the input of the fully connected network. The fully connected network includes one or more fully connected layers. Each neuron in each layer is connected to all neurons in the previous layer. According to the output of the fully connected network, interpretable analysis results are generated, such as predicted values, trend graphs or classification results of air pollution, to obtain air pollution analysis results.

[0149] The above implementation method of the embodiment of the present application performs feature extraction on the above environmental fusion data through a convolutional neural network to obtain the spatiotemporal characteristics of the environmental fusion data, and then performs feature extraction on the above environmental fusion data through a graph neural network to obtain the pollution diffusion characteristics of the environmental fusion data. The pollution diffusion characteristics and spatiotemporal characteristics are integrated using a long short-term memory network to obtain time series dependency characteristics. Finally, based on a fully connected network, the atmospheric pollution analysis results are obtained. Based on different angles, the characteristics are analyzed in many aspects, so that accurate atmospheric pollution analysis results can be obtained.

[0150] In order to accurately obtain the first performance indicator value corresponding to the data collection process, in some embodiments, the above S103 includes steps A5 to B5:

[0151] Step A5: After adjusting the above working parameters, obtain the data quality index value, energy consumption and data transmission volume during the data collection process.

[0152] In the specific implementation, after adjusting the above working parameters, the data collection process is started to record the relevant quality index values ​​and data transmission volume. By monitoring the energy usage, the energy consumption data is recorded.

[0153] Step B5: performing weighted summation on the data quality index value, the energy consumption and the data transmission volume to obtain a first performance index value corresponding to the data collection process.

[0154] In the specific implementation, in order to comprehensively consider the impact of data quality, energy consumption and data transmission volume, appropriate weights are assigned to each indicator in advance. These weights represent the importance of each indicator in the overall performance evaluation. The above different indicators are standardized, each indicator is converted into a unified range, and the weighted values ​​of all indicators are summed to obtain the first performance indicator value corresponding to the data collection process.

[0155] The above-mentioned implementation method of the embodiment of the present application obtains the data quality index value, energy consumption and data transmission volume in the data collection process respectively while adjusting the working parameters, and performs weighted summation on them, so as to accurately obtain the first performance index value corresponding to the data collection process.

[0156] In some embodiments, in the process of obtaining the pollutant concentration, a fixed-size sliding window W is defined for real-time evaluation of the environmental state. For the pollutant concentration c(t) at time t, we calculate the following indicators:

[0157] Mean μ(t):μ(t)=(1 / W)*Σ(c(i)), i from t-W+1to t;

[0158] Standard deviation σ(t):σ(t)=sqrt((1 / W)*Σ((c(i)-μ(t))^2)), i from t-W+1to t;

[0159] Change trend (linear regression slope): k(t): k(t) = (W*Σ(i*c(i))-Σ(i)*Σ(c(i))) / (W*Σ(i^2)-(Σ(i))^2), i from t-W+1to t.

[0160] Based on the environmental status assessment results, dynamically adjust the ISAC device operating parameters, such as:

[0161] The sampling frequency is adjusted to: f(t): f(t) = f_base + α*|σ(t)| + β*|k(t)|, where f_base is the base sampling frequency, and α and β are adjustment coefficients.

[0162] The quantization accuracy is adjusted to: b(t): b(t) = b_min + floor((c(t) - c_min) / (c_max - c_min) * (b_max - b_min)), where b_min and b_max are the minimum and maximum quantization bits respectively, and c_min and c_max are the historical minimum and maximum values ​​of pollutant concentration.

[0163] The data compression rate is adjusted to: r(t): r(t) = r_max-γ*(|σ(t)| / σ_max), where r_max is the maximum compression rate, γ is the adjustment coefficient, and σ_max is the preset maximum standard deviation.

[0164] Then we can define a comprehensive performance index J(t):

[0165] J(t)=w1*Q(t)+w2*(1 / E(t))+w3*(1 / T(t)).

[0166] Among them, Q(t) is the data quality indicator, which can be expressed by the signal-to-noise ratio (SNR); E(t) is the energy consumption; T(t) is the data transmission volume; w1, w2, w3 are weight coefficients.

[0167] In order to maximize J(t), the gradient descent method can be used to continuously optimize the parameter adjustment strategy. The specific adjustment formula is:

[0168]

[0169] Where θ represents the parameters to be optimized (such as α, β, γ), and η is the learning rate.

[0170] The 3-sigma rule is used for anomaly detection, that is, if |c(t)-μ(t)|>3σ(t), the exception handling mechanism is triggered to temporarily increase the sampling frequency to the maximum value; temporarily increase the quantization accuracy to the maximum value; reduce the data compression rate to ensure data integrity. In addition, data exchange and collaborative optimization can be performed between adjacent ISAC devices. Specifically, a collaborative index is defined: C(t)=ρ*J_local(t)+(1-ρ)*avg(J_neighbor(t)), and this index is optimized, where ρ is the trade-off coefficient between local and neighbor performance.

[0171] In addition, the process of environmental signal feature extraction can refer to Figure 2 ,like Figure 2 As shown, the specific algorithm flow includes the following steps:

[0172] Step S201: performing preprocessing such as normalization and detrending on the collected original environmental signals to eliminate the influence of sensor bias and long-term drift.

[0173] Step S202: Adaptively select the optimal wavelet basis function according to the statistical characteristics of the signal.

[0174] Step S203: Perform multi-scale time-frequency decomposition on the signal according to the optimal wavelet basis function and decomposition scale. The wavelet coefficients reflect the energy distribution of the signal at different scales.

[0175] Specifically, let the environmental signal be f(t) and the wavelet basis function be ψ(t), then the wavelet decomposition formula is:

[0176]

[0177] Where a is the scale parameter, b is the translation parameter, and * represents the complex conjugate. f (a,b) is the wavelet coefficient, which reflects the projection coefficient of the signal at scale a and time b.

[0178] Step S204: determining a denoising threshold, where the denoising threshold includes at least one of a soft threshold and a hard threshold.

[0179] Step S205: De-noise the wavelet decomposition result according to the denoising threshold. At each scale, the threshold is adaptively set according to the statistical distribution of the wavelet coefficients, and the wavelet coefficients are processed by soft threshold or hard threshold to filter out high-frequency noise while retaining useful signal components that reflect changes in pollutant concentrations.

[0180] Specifically, let the wavelet coefficient at the jth scale be W j , the adaptive threshold is λ j , then the soft threshold denoising formula is:

[0181]

[0182] in, is the wavelet coefficient after denoising. Threshold λ j It can be set adaptively according to the statistical characteristics of the wavelet coefficients, such as: Among them, σ j is the standard deviation of the j-th scale wavelet coefficient, N j is the number of coefficients at this scale.

[0183] Step S206: extracting features from the denoised wavelet decomposition results, calculating energy distribution at different scales in the denoised wavelet coefficients, and extracting key frequency band energy features that reflect changes in pollutant concentrations.

[0184] Specifically, let the wavelet coefficient after de-noising at the jth scale be Then the energy characteristics of this scale are:

[0185]

[0186] Step S207: using weighted fusion or nonlinear mapping methods to combine energy features extracted at different scales to form a multi-scale fusion feature vector, which achieves data compression while maintaining key signal information.

[0187] Specifically, let the extracted M scale energy features be E1, E2, ..., E M , then the multi-scale fusion feature is: F = [w1E1,w2E2,…,w M E M ] T Among them, w1, w2, etc. are weight coefficients of each scale, which can be adaptively adjusted according to environmental conditions.

[0188] Step S208: According to the changes in environmental conditions, the weight coefficients of the features of each scale are dynamically adjusted to give higher weights to scales with stronger discrimination of pollutant concentrations, thereby improving the adaptability and robustness of the features.

[0189] Step S209: Perform feature selection based on the fused features and weights.

[0190] Step S210: training the inversion model to obtain a concentration inversion model that can accurately perform predictions.

[0191] Step S211: Process the selected features based on the inversion model to obtain pollutant concentration estimates, and input the extracted multi-scale fusion features into the pre-trained concentration inversion model to achieve real-time estimation of pollutant concentrations. The inversion model can be a regression model based on machine learning, such as support vector regression, random forest, etc.

[0192] Specifically, let the multi-scale fusion feature be F and the concentration inversion model be g(·), then the pollutant concentration estimate is The inversion model g(·) can be trained using machine learning methods such as support vector regression.

[0193] For further reference, Figure 3 In view of the characteristics of heterogeneous data, a multi-view autoencoder network can be designed to map data from different sources and different modes into a shared latent space and explore the intrinsic connections between them. On this basis, a graph convolutional neural network is used to model the complex relationship between "site-pollutant-influencing factors" in the pollution process. A causal inference mechanism is introduced to explore the causes of pollution and clarify the causal chain of various factors. Through the fusion of multi-dimensional information, the temporal and spatial distribution of pollution is comprehensively described, which specifically includes the following steps.

[0194] Step S301: input multi-source heterogeneous data, including environmental monitoring data, meteorological data, geographic information data, emission source data and satellite remote sensing data.

[0195] Step S302: Clean and standardize heterogeneous data through data preprocessing.

[0196] Specifically, step S302 includes operations such as step S3021 of missing value filling, step S3022 of outlier detection, and step S3023 of data standardization.

[0197] Step S303: perform data association on the preprocessed data. During the data association process, the association and mapping of data from different sources and in different formats are achieved through techniques such as step S3031 spatiotemporal alignment, step S3032 feature matching, and step S3033 semantic mapping.

[0198] Specifically, in the S3031 spatiotemporal alignment process, we first use spatial interpolation algorithms such as Kriging to unify monitoring data of different spatial resolutions onto a regular grid; then, we use Kalman filter data assimilation technology to align data of different time granularities to a unified time base. Through this spatiotemporal alignment, we achieve consistent representation of multi-source data such as pollutant concentrations, meteorological parameters, and emission source lists in the spatiotemporal dimension.

[0199] In the process of S3032 feature matching, in view of the differences in physical quantities and measurement units of monitoring data from different sources, first, the physical mechanism model of atmospheric pollution process, such as the convection-diffusion equation, is used to establish the conversion relationship between different physical quantities; then, statistical learning methods such as canonical correlation analysis are used to identify homogeneous features in different data sources from a data-driven perspective. On this basis, a unified feature representation space for multi-source monitoring data is constructed, realizing the normalization and standardized representation of features in different measurement units such as mass concentration, volume concentration, and emission flux.

[0200] In the process of S3033 semantic mapping, in view of the differences in concepts and semantics in the fields of environmental monitoring, meteorology, emission inventory, etc., firstly, a general ontology covering all fields of air pollution monitoring was constructed, defining core concepts and relationships such as pollutants, meteorological parameters, and emission source types; then, ontology matching algorithms, such as semantic similarity calculation, were used to map ontologies in different fields to this general ontology to achieve a unified representation of semantics. At the same time, knowledge graph technology was also used to link concepts, entities, and relationships in the ontology with multi-source monitoring data to form a semantically rich air pollution monitoring knowledge base.

[0201] Step S304: Perform data fusion, using algorithms such as multi-view representation learning, graph neural network, and causal inference to mine the intrinsic connections and rules of data from multiple perspectives and multiple associations.

[0202] Step S305: Perform environmental process modeling, input the fused data into the environmental process modeling, and establish a machine learning model that can reflect the temporal and spatial evolution of pollution.

[0203] Specifically, on the basis of data-driven, the classic atmospheric diffusion mechanism model is integrated to build a machine learning model of the pollution process. Adopting the paradigm of spatiotemporal series prediction, an end-to-end prediction model is established with pollution monitoring data, meteorological conditions, emission source information, etc. as input and the spatiotemporal distribution of pollution concentration as output. The attention mechanism and physical constraints are introduced to enhance the interpretability and generalization of the model. The model can be used for tasks such as pollution source tracing and pollution concentration forecasting.

[0204] For example, after inputting the correlated and fused multi-source air pollution monitoring data, an end-to-end spatiotemporal sequence prediction modeling paradigm is adopted to design a deep neural network model that integrates spatiotemporal feature extraction, long short-term memory, and attention mechanism. Then, convolutional neural networks are used to extract local spatiotemporal features, and graph neural networks are used to extract inter-regional propagation correlation features.

[0205] Specifically:

[0206] Convolutional neural network feature extraction: Assume that the input spatiotemporal pollution data is Where T is the time step, H and W are the spatial dimensions, and C is the pollutant type. The calculation formula of the convolutional layer is: Among them, * represents the convolution operation, W (l) and b (l) are the weight and bias of the lth convolutional layer, X (l-1) is the output of the l-1th layer.

[0207] Graph neural network feature extraction: Assume that the graph of pollution monitoring stations is G = (V, E), where V is the node set and E is the edge set. The calculation formula of the graph convolution layer is:

[0208]

[0209] in, To add a self-connected adjacency matrix, for The degree matrix, H (l) is the feature matrix of the l-th layer node, W (l) is the weight matrix of the lth layer, and σ is the activation function.

[0210] The extracted spatiotemporal features are then input into the long short-term memory network (LSTM) to characterize the temporal dependence and trend of the pollution process.

[0211] Attention mechanism can be introduced on the basis of LSTM to focus on the most important historical moments and spatial regions for prediction. The learned spatiotemporal features are mapped to the predicted concentration distribution values ​​at future moments through the fully connected network layer. The supervised learning paradigm integrating physical constraints is adopted to train the model, and physical constraint regularization terms such as mass conservation equation and convection diffusion equation are introduced into the loss function. Data enhancement, adversarial learning and other technologies are used to enhance the generalization and robustness of the model.

[0212] Step S306: Based on the environmental process model, further carry out pollution source analysis and pollution concentration forecast, and output the results of intelligent analysis of air pollution.

[0213] In the above implementation of the present application, the correlation fusion analysis of multi-source data expands the application depth and breadth of environmental monitoring data. Traditional environmental monitoring data analysis is mostly limited to a single data source, and it is difficult to fully characterize the complex pollution process. The multi-source data correlation fusion method proposed in the proposal of this application can integrate environmental monitoring data with meteorological, geographical, emission and other data in multiple dimensions, and construct a high-dimensional feature space that comprehensively reflects the pollution process, which provides a data basis for in-depth understanding of the cause mechanism of pollution and the development of multi-scenario analysis applications. The modeling method that integrates physical mechanism and machine learning realizes the accurate characterization and prediction of the pollution process. Most of the existing pollution process models are based on simplified physical mechanisms or statistical relationships, which are difficult to accurately reflect the complexity of the real world. The fusion modeling method proposed in the proposal of this application, by combining the classical physical model with the deep learning model, while ensuring the accuracy of the physical mechanism, makes full use of the data-driven machine learning algorithm to characterize the complex nonlinear relationship of the pollution process, and realizes the accurate, efficient and universal modeling of the pollution process, which provides strong support for intelligent analysis and decision-making applications.

[0214] Based on the air pollution monitoring method provided in the above embodiment, the present application also provides a specific implementation of an air pollution monitoring device. Please refer to the following embodiment.

[0215] See first Figure 4 The air pollution monitoring device 400 provided in the embodiment of the present application includes the following modules:

[0216] The collection module 401 is used to collect atmospheric data based on working parameters through a collection device to obtain atmospheric pollutant concentration data within a preset time range.

[0217] The adjustment module 402 is used to adaptively adjust the above working parameters according to the statistical characteristics of the above atmospheric pollutant concentration data within the above set time range according to the adjustment coefficient, and the above working parameters after adaptive adjustment correspond to the above statistical characteristics.

[0218] The calculation module 403 is used to calculate the first performance indicator value corresponding to the atmospheric data collection process when the working parameters of the collection device are adjusted.

[0219] The optimization module 404 is used to optimize the adjustment coefficient by gradient descent method according to the first performance indicator value, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

[0220] The air pollution monitoring device provided in the embodiment of the present application continuously adjusts the working parameters of the collection device according to the real-time air pollutant concentration data and the adjustment coefficient, so that the system resources in the collection process can be more reasonably allocated and the collection efficiency can be improved. Further, the corresponding first performance index value is calculated, and the adjustment coefficient is optimized according to the above first performance index value, and the adjustment coefficient is continuously optimized in continuous iteration. Since the working parameters will be adjusted according to the actual atmospheric conditions to adapt to the current actual situation, the adjusted collection working parameters can be used to more efficiently collect changes in the concentration of air pollutants based on the actual environment, and can quickly respond to environmental changes, and then quickly determine the air pollution situation.

[0221] As an implementation of the present application, the acquisition module 401 may include:

[0222] The collection unit is used to collect the pollutant concentration values ​​corresponding to each time point within a preset time range through the collection equipment according to the working parameters.

[0223] The calculation unit is used to calculate the average value of the pollutant concentration values ​​corresponding to the above-mentioned various time points to obtain the mean pollutant concentration.

[0224] The calculation unit is further used to calculate the square value of the difference between the above-mentioned pollutant concentration value corresponding to each time point and the above-mentioned pollutant concentration mean value.

[0225] The calculation unit is also used to calculate the average value of each of the above squares, take the square root of the average value of the above squares, and obtain the standard deviation of the pollutant concentration.

[0226] The determination unit is used to determine the pollutant concentration change trend according to the rate at which the above-mentioned various pollutant concentration values ​​change over time.

[0227] The determination unit is also used to use the pollutant concentration values ​​corresponding to the above-mentioned each time point, the above-mentioned pollutant concentration mean, the above-mentioned pollutant concentration standard deviation and the above-mentioned pollutant concentration change trend as the atmospheric pollutant concentration data within a preset time range.

[0228] The above-mentioned implementation method of the embodiment of the present application collects the pollutant concentration values ​​corresponding to each time point within a preset time range through the collection equipment according to the working parameters, and then calculates the concentration mean and standard deviation of each pollutant concentration value, and then uses the pollutant concentration values ​​corresponding to the above-mentioned each time point, the above-mentioned pollutant concentration mean, the above-mentioned pollutant concentration standard deviation and the above-mentioned pollutant concentration change trend as the atmospheric pollutant concentration data within the preset time range, and comprehensively utilizes multiple data as the atmospheric pollutant concentration data within the preset time range, so that the atmospheric pollutant concentration data can comprehensively reflect the actual situation of air pollution.

[0229] As an implementation of the present application, the adjustment module 402 may include:

[0230] The determination unit is used to determine the sampling frequency increase value according to the adjustment coefficient, the standard deviation of the pollutant concentration and the change trend of the pollutant concentration.

[0231] The adjustment unit is used to determine the target sampling frequency according to the preset basic sampling frequency and the sampling frequency increase value, and adjust the sampling frequency to the target sampling frequency.

[0232] The adjustment unit is further used to adjust the quantization accuracy according to the current pollutant concentration value and the extreme value of the pollutant concentration within a preset time range.

[0233] The adjustment unit is further used to adjust the data compression rate according to the ratio of the above pollutant concentration to the preset standard deviation.

[0234] The above implementation method of the embodiment of the present application adjusts the sampling frequency according to the adjustment coefficient, the above pollutant concentration standard deviation and the above pollutant concentration change trend, adjusts the quantization accuracy based on the current pollutant concentration value and the extreme pollutant concentration within a preset time range, and adjusts the data compression rate according to the ratio of the above pollutant concentration to the preset standard deviation, so as to accurately adjust various working parameters.

[0235] As an implementation of the present application, the air pollution monitoring device 400 may further include:

[0236] The decomposition module is used to perform wavelet decomposition on the above-mentioned atmospheric pollutant concentration data through a preset wavelet basis function to obtain wavelet coefficients, wherein the above-mentioned wavelet coefficients represent the local characteristics of the above-mentioned atmospheric pollutant concentration data at multiple different scales.

[0237] The extraction module is used to extract features from the wavelet coefficients to obtain pollutant concentration features at multiple different scales.

[0238] The combination module is used to combine the above pollutant concentration features at multiple different scales to obtain multi-scale fusion features.

[0239] The determination module is used to input the above-mentioned multi-scale fusion features into a preset prediction model to obtain the atmospheric pollutant concentration prediction data corresponding to a preset time, and the above-mentioned preset time is later than the above-mentioned preset time range.

[0240] The above-mentioned implementation method of the embodiment of the present application performs wavelet decomposition on the above-mentioned atmospheric pollutant concentration data through a preset wavelet basis function to obtain wavelet coefficients, and then performs feature extraction on the above-mentioned wavelet coefficients to obtain multi-scale fusion features, and uses a preset prediction model to process based on this multi-scale fusion feature to obtain the atmospheric pollutant concentration prediction data corresponding to the preset time. Using wavelet decomposition and multi-scale feature fusion as concentration prediction data can obtain accurate atmospheric pollutant concentration prediction data.

[0241] As an implementation of the present application, the decomposition module may include:

[0242] The acquisition unit is used to acquire the decomposition scale corresponding to the preset wavelet basis function.

[0243] The decomposition unit is used to perform wavelet decomposition on the above-mentioned atmospheric pollutant concentration data according to the decomposition scale corresponding to the above-mentioned preset wavelet basis function to obtain initial wavelet coefficients.

[0244] The analysis unit is used to perform statistical analysis on the initial wavelet coefficients to determine the statistical characteristics of the initial wavelet coefficients.

[0245] The denoising unit is used to perform denoising processing on the initial wavelet coefficients based on the threshold value corresponding to the above statistical characteristics to obtain the wavelet coefficients.

[0246] The above implementation of the embodiment of the present application obtains the decomposition scale corresponding to the preset wavelet basis function, and then performs wavelet decomposition on the above atmospheric pollutant concentration data according to the decomposition scale, and then denoises the initial wavelet coefficients to remove useless information therein, so as to obtain more accurate wavelet coefficients.

[0247] As an implementation of the present application, the air pollution monitoring device 400 may further include:

[0248] The adjustment module is used to adjust the working parameters based on the optimized adjustment coefficient.

[0249] The collection module is used to collect pollutant concentration data according to the above working parameters.

[0250] The combination module is used to combine the above pollutant concentration data, geographic data and meteorological data to obtain environmental fusion data.

[0251] The processing module is used to process the above environmental fusion data through a preset neural network model to obtain air pollution analysis results.

[0252] The above implementation method of the embodiment of the present application adjusts the working parameters through the adjustment coefficient after optimizing the adjustment coefficient, uses the above working parameters to collect pollutant concentration data, and combines the collected pollutant concentration data with geographical data and meteorological data to obtain environmental fusion data that comprehensively reflects the environmental conditions. Thereafter, the above environmental fusion data is processed using a preset neural network model to obtain accurate atmospheric pollution analysis results.

[0253] As an implementation of the present application, the processing module may include:

[0254] The extraction unit is used to extract features from the above-mentioned environmental fusion data through the above-mentioned convolutional neural network to obtain the spatiotemporal features of the above-mentioned environmental fusion data.

[0255] The extraction unit is also used to perform feature extraction on the above-mentioned environmental fusion data through the above-mentioned graph neural network to obtain the pollution diffusion characteristics of the above-mentioned environmental fusion data.

[0256] The determination unit is used to input the above-mentioned spatiotemporal characteristics and the above-mentioned pollution diffusion characteristics into the above-mentioned long short-term memory network to obtain the time-series dependence characteristics of air pollution.

[0257] The determination unit is also used to input the above-mentioned time-series dependent features into the above-mentioned fully connected network to obtain the atmospheric pollution analysis results.

[0258] The above implementation method of the embodiment of the present application performs feature extraction on the above environmental fusion data through a convolutional neural network to obtain the spatiotemporal characteristics of the environmental fusion data, and then performs feature extraction on the above environmental fusion data through a graph neural network to obtain the pollution diffusion characteristics of the environmental fusion data. The pollution diffusion characteristics and spatiotemporal characteristics are integrated using a long short-term memory network to obtain time series dependency characteristics. Finally, based on a fully connected network, the atmospheric pollution analysis results are obtained. Based on different angles, the characteristics are analyzed in many aspects, so that accurate atmospheric pollution analysis results can be obtained.

[0259] As an implementation of the present application, the calculation module 403 may include:

[0260] The acquisition unit is used to acquire the data quality index value, energy consumption and data transmission volume in the data acquisition process when the above working parameters are adjusted.

[0261] The summing unit is used to perform weighted summation on the data quality index value, the energy consumption and the data transmission volume to obtain a first performance index value corresponding to the data collection process.

[0262] The above-mentioned implementation method of the embodiment of the present application obtains the data quality index value, energy consumption and data transmission volume in the data collection process respectively while adjusting the working parameters, and performs weighted summation on them, so as to accurately obtain the first performance index value corresponding to the data collection process.

[0263] Each module in the air pollution monitoring device provided in the embodiment of the present application can implement each step in the above-mentioned air pollution monitoring method and achieve the corresponding effect. For the sake of concise description, it will not be repeated here.

[0264] Figure 5 A schematic diagram of the structure of the air pollution monitoring hardware provided in an embodiment of the present application is shown.

[0265] The air pollution monitoring device may include a processor 501 and a memory 502 storing computer program instructions.

[0266] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0267] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0268] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the atmospheric pollution monitoring method according to any one embodiment of the present disclosure.

[0269] The processor 501 implements any one of the air pollution monitoring methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0270] In one example, the air pollution monitoring device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0271] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0272] Bus 510 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0273] In addition, in combination with the method for air pollution monitoring in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the air pollution monitoring methods in the above embodiments is implemented.

[0274] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the air pollution monitoring methods in the above embodiments.

[0275] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0276] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0277] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0278] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0279] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for monitoring air pollution, characterized in that: include: The atmospheric data is collected by the collection equipment based on the working parameters to obtain the atmospheric pollutant concentration data within the preset time range; According to the statistical characteristics of the atmospheric pollutant concentration data within the set time range, the operating parameters are adaptively adjusted according to the adjustment coefficient, and the adaptively adjusted operating parameters correspond to the statistical characteristics; When the working parameters of the acquisition device are adjusted, calculating a first performance indicator value corresponding to the atmospheric data acquisition process; According to the first performance indicator value, the adjustment coefficient is optimized by gradient descent method, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

2. The air pollution monitoring method according to claim 1, characterized in that: The air data is collected by the collection device based on the working parameters to obtain the air pollutant concentration data within a preset time range, including: Collect the pollutant concentration values ​​corresponding to each time point within the preset time range through the collection equipment according to the working parameters; Calculate the average value of the pollutant concentration values ​​corresponding to each time point to obtain the mean pollutant concentration; Calculate the square value of the difference between the pollutant concentration value corresponding to each time point and the mean pollutant concentration; Calculate the average of each of the squares, take the square root of the average of the squares, and obtain the standard deviation of the pollutant concentration; Determining a pollutant concentration change trend according to the rate at which each of the pollutant concentration values ​​changes over time; The pollutant concentration values ​​corresponding to the various time points, the pollutant concentration mean, the pollutant concentration standard deviation and the pollutant concentration change trend are used as atmospheric pollutant concentration data within a preset time range.

3. The air pollution monitoring method according to claim 2, characterized in that: The working parameters include sampling frequency, quantization accuracy and data compression rate, and the working parameters are adaptively adjusted according to the adjustment coefficient based on the statistical characteristics of the atmospheric pollutant concentration data within the set time range, including: Determine the sampling frequency increase value according to the adjustment coefficient, the standard deviation of the pollutant concentration and the pollutant concentration change trend; Determine a target sampling frequency according to a preset basic sampling frequency and the sampling frequency boost value, and adjust the sampling frequency to the target sampling frequency; Adjust the quantification accuracy according to the current pollutant concentration value and the extreme pollutant concentration value within the preset time range; The data compression rate is adjusted according to the ratio of the pollutant concentration to the preset standard deviation.

4. The air pollution monitoring method according to claim 1, characterized in that: After the atmospheric data is collected by the collection device based on the working parameters to obtain atmospheric pollutant concentration data within a preset time range, the method further includes: Performing wavelet decomposition on the atmospheric pollutant concentration data by using a preset wavelet basis function to obtain wavelet coefficients, wherein the wavelet coefficients represent local characteristics of the atmospheric pollutant concentration data at multiple different scales; Extracting features from the wavelet coefficients to obtain pollutant concentration features at multiple different scales; Combining the pollutant concentration features at multiple different scales to obtain multi-scale fusion features; The multi-scale fusion features are input into a preset prediction model to obtain atmospheric pollutant concentration prediction data corresponding to a preset time, where the preset time is later than the preset time range.

5. The air pollution monitoring method according to claim 4, characterized in that: The wavelet decomposition of the atmospheric pollutant concentration data by a preset wavelet basis function to obtain wavelet coefficients includes: Obtain the decomposition scale corresponding to the preset wavelet basis function; According to the decomposition scale corresponding to the preset wavelet basis function, the atmospheric pollutant concentration data is subjected to wavelet decomposition to obtain initial wavelet coefficients; Performing statistical analysis on the initial wavelet coefficients to determine statistical characteristics of the initial wavelet coefficients; The initial wavelet coefficients are denoised based on a threshold value corresponding to the statistical feature to obtain wavelet coefficients.

6. The air pollution monitoring method according to claim 1, characterized in that: After optimizing the adjustment coefficient by a gradient descent method according to the first performance indicator value, the method further includes: Adjusting working parameters based on the optimized adjustment coefficients; collecting pollutant concentration data according to the working parameters; Combining the pollutant concentration data, corresponding geographic data and meteorological data to obtain environmental fusion data; The environmental fusion data is processed by a preset neural network model to obtain an atmospheric pollution analysis result.

7. The air pollution monitoring method according to claim 6, characterized in that: The preset neural network model includes a convolutional neural network, a graph neural network, a long short-term memory network and a fully connected network. The environmental fusion data is processed by the preset neural network model to obtain an atmospheric pollution analysis result, including: Extracting features from the environment fusion data by using the convolutional neural network to obtain spatiotemporal features of the environment fusion data; Extracting features from the environmental fusion data through the graph neural network to obtain pollution diffusion features of the environmental fusion data; Inputting the spatiotemporal characteristics and the pollution diffusion characteristics into the long short-term memory network to obtain the temporal dependence characteristics of air pollution; The time-dependent features are input into the fully connected network to obtain air pollution analysis results.

8. The air pollution monitoring method according to any one of claims 1 to 7, characterized in that: The step of calculating a first performance indicator value corresponding to the atmospheric data collection process when the working parameters of the collection device are adjusted includes: When the working parameters are adjusted, obtaining data quality index values, energy consumption and data transmission volume during data collection; A weighted sum is taken for the data quality index value, the energy consumption amount and the data transmission amount to obtain a first performance index value corresponding to the data collection process.

9. An air pollution monitoring device, characterized in that: The device comprises: The acquisition module is used to acquire atmospheric data based on working parameters through acquisition equipment to obtain atmospheric pollutant concentration data within a preset time range; An adjustment module, configured to adaptively adjust the operating parameters according to the statistical characteristics of the atmospheric pollutant concentration data within the set time range according to the adjustment coefficient, wherein the adaptively adjusted operating parameters correspond to the statistical characteristics; A calculation module, used for calculating a first performance indicator value corresponding to an atmospheric data collection process when the working parameters of the collection device are adjusted; The optimization module is used to optimize the adjustment coefficient by gradient descent method according to the first performance indicator value, so that when the working parameters are adjusted based on the optimized adjustment coefficient, the second performance indicator value of the corresponding data acquisition process is greater than the first performance indicator value.

10. An air pollution monitoring device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the air pollution monitoring method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the air pollution monitoring method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the air pollution monitoring method as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Atmospheric pollutant concentration monitoring system

    CN117310101A

  • Air quality prediction method based on traffic jam index and multi-source data fusion

    CN117494034A

  • Underground water multi-parameter real-time monitoring and pollution early warning system

    CN118311221A

  • Atmospheric pollution monitoring system based on wireless sensor network

    CN118354474A

  • Pollution source online monitoring data quality monitoring method

    CN118503667A

Cited By

  • Surface water multi-point source pollution source tracing method and system

    CN120217089A

  • A method and system for tracing the source of multi-point source pollution of surface water

    CN120217089B