A method and system for analyzing atmospheric environmental pollution data

By setting up gas sampling points during the ceramic production process and monitoring in real time, using scatter plots and mutual information calculations, the problem of traditional monitoring methods neglecting pollution in the production process is solved, and comprehensive monitoring of air pollution and influencing factors are achieved, ensuring data Accuracy and timely response.

CN118520421BActive Publication Date: 2024-11-19SHANDONG HONGSHI CERAMIC TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410579091.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-11
Publication Date
2024-11-19
Estimated Expiration
2044-05-11

AI Technical Summary

Technical Problem

Traditional pollutant monitoring methods only focus on the pollutant concentration at the final discharge port, ignore the possible pollution problems that may arise in each link in the production process, and it is difficult to quickly determine the specific pollution source, resulting in slow reaction.

Method used

Gas sampling points are set up in all aspects of ceramic production to obtain gas samples and environmental parameters in real time, and through scatter plots, interval divisions and mutual information calculations, pollutant concentrations and influencing factors are evaluated, and pollution exceeding standards are discovered in a timely manner.

Benefits of technology

A comprehensive monitoring of air pollution during ceramic production has been achieved, ensuring the integrity and accuracy of data, timely identifying pollution problems, deeply understanding the correlation between pollutant concentration and environmental parameters, and accurately assessing influencing factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118520421B_ABST
    Figure CN118520421B_ABST
Patent Text Reader

Abstract

The present invention provides an atmospheric environmental pollution data analysis method and system, which relates to the field of data processing technology. The method includes: taking the concentration of key pollutants and corresponding environmental parameters as two variables to form a scatter plot; determining the final interval division scheme, dividing the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determining the distribution of data points in each grid according to the data point groups, and calculating the final mutual information value according to the data point distribution; comparing the concentration of key pollutants with preset influencing factors to obtain a comparison result. The present invention can comprehensively monitor the atmospheric pollution in the production process and can promptly detect the pollution exceeding the standard.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an atmospheric environmental pollution data analysis method and system. Background Art

[0002] In the process of producing ceramic products, if the traditional pollutant monitoring method is adopted, that is, only monitoring equipment is installed at the discharge port of the factory to regularly measure the concentration of pollutants. This method is simple and easy to implement, and it also meets the basic requirements of environmental protection regulations at that time. However, with the expansion of production scale and the improvement of environmental protection standards, this traditional monitoring method began to expose its inherent defects:

[0003] For example, traditional monitoring methods may only focus on the final pollutant concentration at the discharge port, while ignoring the pollution that may be generated in various links during the production process. This means that even if the final emission meets the standard, there may still be pollution problems in some links of the production process, and these problems cannot be discovered under traditional monitoring methods.

[0004] In addition, since monitoring is only carried out at the emission outlet, it is difficult to quickly identify the specific source of pollution when the pollutant concentration exceeds the standard. This leads to a slow response when dealing with pollution problems and may not be able to take effective control measures in a timely manner. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide an atmospheric environmental pollution data analysis method and system, which can comprehensively monitor the atmospheric pollution situation in the production process and timely discover the pollution exceeding the standard.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a method for analyzing atmospheric environmental pollution data comprises:

[0008] Set up gas sampling points at various stages of ceramic production;

[0009] Obtain the gas samples collected at each sampling point and the sampling environment parameters corresponding to the gas samples in real time;

[0010] Conduct composition analysis on gas samples to obtain key pollutant concentrations;

[0011] The concentration of key pollutants and the corresponding environmental parameters are used as two variables to construct a scatter plot;

[0012] Determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid based on the data point groups, and calculate the final mutual information value based on the data point distribution;

[0013] Compare the concentration of key pollutants with the preset influencing factors to obtain comparative results;

[0014] According to the comparison results and the final mutual information value, the status and influencing factors of air pollution in the ceramic production process are evaluated to obtain the evaluation results.

[0015] Furthermore, the final interval division plan is determined, including:

[0016] Initialize a group of particles, each particle represents an interval partitioning scheme, which includes the number, position and size of intervals;

[0017] A fitness function is used to determine the quality of the interval division scheme; according to the fitness function, the fitness value of each particle is calculated, and the position and speed of the particle are updated according to the fitness value to obtain the final interval division scheme.

[0018] Furthermore, the intervals are divided in the X-axis and Y-axis directions of the scatter plot to obtain data point groups, including:

[0019] According to the determined interval division scheme, the boundary values ​​of the intervals are determined on the X-axis and Y-axis of the scatter plot respectively, so as to form intervals to divide the scatter plot into a plurality of grids, wherein the X-axis corresponds to the concentration of the key pollutant and the Y-axis corresponds to the environmental parameter;

[0020] Traverse each data point and classify the data point into the corresponding grid according to the coordinate value corresponding to the data point;

[0021] For each grid containing data points, the center point of the grid is used as the initial cluster center;

[0022] Through continuous iteration, the data points are assigned to the nearest cluster center, and the position of the cluster center is recalculated until the preset number of iterations is reached, so as to achieve the distribution of data points to each cluster to obtain data point grouping.

[0023] Furthermore, according to the data point grouping, the distribution of data points in each grid is determined, including:

[0024] Traverse the data points in each data point group, and for each traversed data point, determine the grid to which the data point belongs according to the coordinate value corresponding to the data point;

[0025] After all data point groups are traversed, the distribution of data points in each grid is determined.

[0026] Furthermore, according to the distribution of data points, the final mutual information value is calculated, including:

[0027] For key pollutant concentrations and environmental parameters, the frequency of occurrence of data points in each interval is calculated to obtain the interval probability corresponding to each interval, and the joint probability of the data points appearing in a specific grid on the scatter plot is calculated;

[0028] The marginal entropy of key pollutant concentrations and environmental parameters are calculated based on interval probabilities;

[0029] Calculate the joint entropy of key pollutant concentrations and environmental parameters based on joint probabilities;

[0030] According to the marginal entropy and joint entropy Calculate the mutual information I(X;Y), where and w k is the weight factor, α, β and γ are smoothing parameters, ∑ k w k and∑ k ∑ l w kl is the sum of the weight factors, c(x i )、c(y j ) and c(x i ,y j ) represent the concentration of key pollutants in the interval x i , the interval y of environmental parameters j And the grid (x i ,y j ), i is the interval of indexing key pollutant concentrations, j is the interval of indexing environmental parameters, k and l are index variables; j' and i' are the index variables for summation; c(x i' ) represents the number of data points appearing in the i'th interval among all possible intervals of the key pollutant concentration; c(y j' ) represents the number of data points that appear in the j'th interval among all possible intervals of the environmental parameters; c(x i' ,y j' ) represents the number of data points appearing in the intersection area between the i'th interval of the key pollutant concentration and the j'th interval of the environmental parameter.

[0031] Furthermore, the mutual information I(X; Y) represents the correlation between the concentrations of key pollutants and environmental parameters.

[0032] Furthermore, the concentration of key pollutants is compared with the preset influencing factors to obtain comparative results, including:

[0033] pass Calculate the impact factor, where D represents the impact factor of key pollutants; x mis the measured value of the mth environmental condition, M is the total number of environmental conditions, ∈ is a positive number, m and n are indices, and a m represents the average impact of the linear change of the mth environmental condition on the key pollutant influencing factor D, b mn represents the combined impact of the mth environmental condition and the nth environmental condition on the key pollutant influencing factor D when they change simultaneously, c m represents the impact of the logarithmic transformation of the mth environmental condition on the key pollutant impact factor D, and d is the intercept of the regression line;

[0034] The key pollutant impact factor D is compared with the key pollutant concentration to obtain a comparative result.

[0035] In a second aspect, an atmospheric environment pollution data analysis device comprises:

[0036] The acquisition module is used to set gas sampling points in various links of ceramic production; obtain the gas samples collected at each sampling point and the sampling environmental parameters corresponding to the gas samples in real time; analyze the components of the gas samples to obtain the concentration of key pollutants; and use the concentration of key pollutants and the corresponding environmental parameters as two variables to form a scatter plot;

[0037] The processing module is used to determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid according to the data point groups, and calculate the final mutual information value according to the data point distribution; compare the concentration of key pollutants with the preset influencing factors to obtain comparison results; evaluate the status and influencing factors of air pollution in the ceramic production process according to the comparison results and the final mutual information value to obtain evaluation results.

[0038] According to a third aspect, a computing device includes:

[0039] one or more processors;

[0040] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0041] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0042] The above solution of the present invention includes at least the following beneficial effects:

[0043] Setting up gas sampling points at various stages of ceramic production can fully monitor gas emissions during the production process, thereby ensuring the integrity and accuracy of pollution data. Real-time acquisition of gas samples and sampling environmental parameters makes the collection of pollution data more timely, which helps to quickly respond to and identify potential pollution problems. Using scatter plots to show the relationship between key pollutant concentrations and environmental parameters is a very intuitive method. By analyzing the composition of gas samples, the concentration of key pollutants can be accurately obtained.

[0044] By dividing the scatter plot into intervals, grouping the data points, and calculating the mutual information value, we can gain a deeper understanding of the correlation between pollutant concentrations and environmental parameters, thereby more accurately identifying the key factors affecting pollutant emissions. By comparing the concentrations of key pollutants with the preset influencing factors, we can promptly detect situations where pollutants exceed the standard. The comprehensive comparison results and mutual information values ​​can more comprehensively evaluate the status and influencing factors of air pollution in the ceramic production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of an atmospheric environmental pollution data analysis method provided by an embodiment of the present invention.

[0046] Figure 2 It is a schematic diagram of an atmospheric environment pollution data analysis device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0048] like Figure 1 As shown, an embodiment of the present invention provides an atmospheric environment pollution data analysis method, the method comprising the following steps:

[0049] Step 11, setting up gas sampling points at various stages of ceramic production;

[0050] Step 12, obtaining the gas samples collected at each sampling point and the sampling environment parameters corresponding to the gas samples in real time;

[0051] Step 13, performing component analysis on the gas sample to obtain the concentration of key pollutants;

[0052] Step 14, using the concentration of key pollutants and the corresponding environmental parameters as two variables to form a scatter plot;

[0053] Step 15, determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid according to the data point groups, and calculate the final mutual information value according to the data point distribution;

[0054] Step 16, comparing the concentration of key pollutants with preset influencing factors to obtain a comparison result;

[0055] Step 17, based on the comparison results and the final mutual information value, evaluate the status and influencing factors of air pollution in the ceramic production process to obtain an evaluation result.

[0056] In an embodiment of the present invention, by setting gas sampling points in various links of ceramic production, the method can collect gas emission data in the production process in an all-round way to ensure the comprehensiveness and accuracy of the data. Real-time acquisition of gas samples and sampling environmental parameters enables pollution data to be captured and analyzed in a timely manner, thereby achieving real-time monitoring and rapid response to atmospheric pollution conditions. By performing component analysis on gas samples, the concentrations of key pollutants can be accurately identified and quantified. The concentrations of key pollutants and corresponding environmental parameters are formed into a scatter plot, so that complex data relationships can be intuitively displayed. By dividing intervals and grouping data points, as well as calculating mutual information values, the intrinsic connections between data can be deeply explored, revealing the main influencing factors of atmospheric pollution in the ceramic production process. By comparing the concentrations of key pollutants with preset influencing factors, the pollution status can be accurately assessed and potential pollution risks can be discovered in a timely manner.

[0057] In another preferred embodiment of the present invention, the above step 11 may include:

[0058] Step 111, conduct a detailed investigation of the ceramic production site to understand the production process, equipment layout, raw material usage, etc.; based on the results of the on-site investigation, select representative links as sampling points, for example, set sampling points at key links such as raw material crushing, mixing, molding, and sintering. The setting of sampling points should follow relevant technical specifications to ensure the stable operation of the sampler and the accuracy of the sampling data. The sampler should be installed at the determined sampling point location, and necessary debugging and calibration should be carried out to ensure the normal operation of the sampler and the accuracy of the data.

[0059] For example, taking a ceramic production plant as an example, the production process of the plant includes raw material crushing, mixing, molding, sintering and waste gas treatment. In order to comprehensively evaluate the atmospheric pollution in the production process, it is decided to set up gas sampling points in the following links: set up a sampling point near the crusher to monitor the dust and other pollutants generated in the raw material crushing process, set up a sampling point near the mixing equipment to monitor the harmful gases that may be generated in the mixing process, set up a sampling point near the molding machine to monitor the dust and other pollutants that may be generated in the molding process, set up a sampling point at the inlet and outlet of the sintering kiln to monitor the composition and concentration changes of the waste gas generated during the sintering process, and set up a sampling point before and after the waste gas treatment facility to evaluate the treatment effect and monitor whether the discharged waste gas meets the standard. Through the above settings, gas samples from each link in the ceramic production process can be collected comprehensively and accurately.

[0060] In another preferred embodiment of the present invention, the above step 12 may include:

[0061] Step 121, install automated gas samplers at each sampling point. These samplers can extract gas samples regularly or continuously. The samplers have real-time data transmission capabilities so that the sampling data can be sent to the central data processing system in a timely manner.

[0062] Step 122, the sampler collects gas samples in real time and transmits the data to a data center via wired or wireless means. The data center is equipped with a data storage and processing server for receiving, storing and analyzing the sampled data. In addition to the gas sample data, it is also necessary to simultaneously record the environmental parameters during sampling, such as temperature, humidity, air pressure, etc. These environmental parameters can be obtained through a weather station or sensor installed near the sampling point.

[0063] Step 123, the data center should establish a data synchronization mechanism to ensure that the data of all sampling points can be updated in real time, and regularly verify the data to ensure the accuracy and integrity of the data. The data center should establish strict security measures to prevent data leakage or tampering, and regularly back up the data to prevent data loss.

[0064] For example, taking the real-time gas sampling system of a ceramic production plant as an example, the system achieves real-time acquisition of gas samples and environmental parameters through the following steps: Automated gas samplers are set up in key links such as raw material crushing, mixing, molding, sintering and waste gas treatment in the ceramic production plant. Each sampler is equipped with a data transmission module to ensure that data is sent to the central data processing system in real time. The sampler automatically extracts gas samples at regular intervals (such as every minute) and transmits the data to the data center wirelessly. The server in the data center receives and processes this data in real time and stores it in the database. A small weather station is installed near each sampling point to monitor and record environmental parameters such as temperature, humidity, and air pressure in real time. These environmental parameters are stored in the database together with the gas sample data for subsequent analysis. The analysis software in the data center processes and analyzes the gas samples and environmental parameters collected in real time.

[0065] In another preferred embodiment of the present invention, the above step 13 may include:

[0066] Step 131, receiving and registering gas samples, ensuring the integrity and identification accuracy of the samples, and performing appropriate pretreatment on the gas samples, such as filtering, concentrating or diluting, to meet the requirements of the analytical instrument; selecting appropriate analytical methods, such as chromatography, mass spectrometry, spectroscopy, etc., according to the properties of the pollutants and the detection requirements; setting the parameters of the analytical instrument, such as temperature, pressure, flow rate, etc., to ensure the accuracy and precision of the analysis.

[0067] Step 132, injecting the pretreated gas sample into the analytical instrument, running the analytical instrument, separating and detecting the chemical components in the gas sample, and recording the response signal of the analytical instrument, such as peak height, peak area, etc., for subsequent quantitative calculation.

[0068] Step 133, using the standard curve to convert the response signal of the analytical instrument into the concentration value of the pollutant, statistically analyzing the data, and calculating the average concentration, maximum concentration and other parameters of the key pollutants.

[0069] For example, in a gas pollution monitoring project at a ceramic production plant, the gas samples collected from various sampling points were analyzed for composition. The following is a detailed description of the analysis steps:

[0070] Gas samples were collected from the raw material crushing, mixing, molding, sintering and waste gas treatment links. After filtering and concentration, the samples were sent to the analysis laboratory for further processing. In view of the pollutants that may be generated in the ceramic production process, such as sulfur dioxide, nitrogen oxides, particulate matter, etc., gas chromatography was selected as the main analysis method. The gas chromatograph was set to specific temperature and pressure conditions to ensure the best separation effect. The pretreated gas samples were injected into the gas chromatograph; after the instrument was run, the gases of different components were separated in the chromatographic column and detected by the detector. The detection signal was recorded and converted into the concentration value of the pollutant. The detection signal was converted into a specific concentration value through the standard curve, and the results of multiple measurements were averaged to obtain the average concentration of each pollutant. The results showed that the average concentration of sulfur dioxide was 0.5ppm, the average concentration of nitrogen oxides was 1.2ppm, and the average concentration of particulate matter was 3.5μg / m3. The analysis results were organized into a report form, which listed in detail the pollutants detected in each link and their concentration values.

[0071] In another preferred embodiment of the present invention, the above step 14 may include:

[0072] Step 141, the key pollutant concentration data and environmental parameter data (such as temperature, humidity, etc.) obtained from the previous step need to be organized into data sets to ensure that each set of data contains the key pollutant concentration and environmental parameter values ​​at the same time. Use Excel, Python's matplotlib library, R language ggplot2 package and other drawing tools to create a scatter plot, with the key pollutant concentration as the Y axis and the environmental parameter as the X axis, and each set of data is represented as a point on the graph. According to the range and distribution of the data, the scale and label of the coordinate axis are appropriately adjusted to more clearly show the distribution of the data.

[0073] Step 142, add chart titles, axis labels, and legends to enhance the readability of the chart. Different colors, shapes, or sizes can be used as needed to represent different attributes or classifications of points. Observe the distribution of points in the scatter plot and analyze whether there is a trend or correlation between the concentrations of key pollutants and environmental parameters. If obvious linear relationships, nonlinear relationships, or clustering phenomena are found, the reasons and mechanisms behind them can be further explored.

[0074] For example, suppose that a week-long continuous monitoring was conducted in the sintering process of a ceramic production plant, and the sulfur dioxide (SO2) concentration and the corresponding ambient temperature data were obtained. Now, this data will be used to draw a scatter plot. There are 7 days of data, and the SO2 concentration and temperature are recorded every hour every day, totaling 168 sets of data. The data is organized into a table with two columns, one for temperature (℃) and the other for SO2 concentration (ppm); Python's matplotlib library is chosen to draw the scatter plot; in matplotlib, the scatter function is used to draw the scatter plot, with the X-axis being the temperature and the Y-axis being the SO2 concentration. The scales and labels of the coordinate axes are also set to display the data more clearly. The chart title "Scatter plot of the relationship between SO2 concentration and temperature in the sintering process" is added, and different colors are used to represent different dates to better observe the distribution of the data. By observing the scatter plot, it is found that when the temperature is higher, the SO2 concentration is also relatively higher, which may indicate that more sulfur dioxide is produced during the sintering process under high temperature conditions. This finding can help ceramic factories optimize the sintering process, such as taking emission reduction measures during high temperature periods to reduce sulfur dioxide emissions.

[0075] In a preferred embodiment of the present invention, determining the final interval division scheme includes:

[0076] Initialize a group of particles, each particle represents an interval partitioning scheme, which includes the number, position and size of intervals;

[0077] A fitness function is used to determine the quality of the interval division scheme; according to the fitness function, the fitness value of each particle is calculated, and the position and speed of the particle are updated according to the fitness value to obtain the final interval division scheme.

[0078] In the embodiment of the present invention, the size of the particle group (i.e., the number of particles) is set, and an interval partitioning scheme is randomly generated for each particle, including the number, position, and size of intervals, which can be expressed as the position and velocity vectors of the particles. A fitness function is defined, and the fitness function is used to evaluate the quality of the interval partitioning scheme. For example, the specific calculation formula of the fitness function is:

[0079] Among them, n represents the number of divided intervals, N i represents the number of data points in the ith interval, μ represents the average number of data points in all intervals, represents the interval partitioning scheme, i is the index used to traverse the interval, and ∈ is a small constant to prevent division by zero errors; for each particle (i.e., each interval partitioning scheme), the fitness function is used to calculate its fitness value; according to the current position and speed of each particle, as well as its own best position and the best position in the group, the position and speed of the particle are updated, where the position and speed of the particle are updated using the following formula:

[0080]

[0081]

[0082] Among them, w is the inertia weight, which is used to control the influence of the current speed on the next speed, c1 and c2 are learning factors, r1 and r2 are random numbers in the range of [0, 1], is the best historical position of particle i, is the historical best position of the entire particle swarm, i is the index variable, t represents the current number of iterations, Represents the velocity vector of particle i at the next iteration (i.e., time t+1); represents the position vector of particle i at the current iteration (i.e. time t), Represents the velocity vector of particle i at the current iteration (i.e., time t). Repeat the steps until the termination condition is met (such as reaching the maximum number of iterations); select the particle with the highest fitness value as the final interval partitioning scheme.

[0083] For example, suppose there is a set of data points distributed in the range of 0 to 100, and you want to divide these data points into several intervals so that the number of data points in each interval is as equal as possible. Initialize a particle swarm containing 10 particles, each particle represents an interval division scheme. For example, a particle may represent dividing the data into three intervals: [0,20), [20,50), and [50,100]. Define the fitness function so that the number of data points in each interval is as equal as possible, so the fitness function can be designed as the inverse of the standard deviation of the number of data points in each interval (the smaller the standard deviation, the more uniform the distribution of data points and the higher the fitness). For each particle (interval division scheme), calculate its fitness value. For example, for the three intervals mentioned above, calculate the number of data points in each interval respectively, calculate its standard deviation, and then take the inverse as the fitness value. According to the update rule of PSO, update the position and velocity of each particle. This may cause the boundaries of the interval to change, such as from [0,20), [20,50), [50,100] to [0,25), [25,60), [60,100]. Repeat the above process multiple times until the termination condition is met. In each iteration, the particle swarm will gradually move towards a better interval partitioning scheme. After the iteration, the particle with the highest fitness value is selected as the final interval partitioning scheme. For example, it may be a partitioning scheme of [0,30), [30,65), [65,100].

[0084] In the embodiment of the present invention, the optimization algorithm can find the global optimal solution in a complex search space, thereby improving the search efficiency and accuracy. The method does not require too many mathematical assumptions about the problem, nor does it rely on the gradient information of the problem, so it has strong adaptability and flexibility. Since the particles in the optimization algorithm continuously learn and adjust their own speed and position during the search process, it can effectively avoid falling into the local optimal solution and find a more globally optimal interval partitioning scheme.

[0085] In a preferred embodiment of the present invention, dividing intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups includes:

[0086] According to the determined interval division scheme, the boundary values ​​of the intervals are determined on the X-axis and Y-axis of the scatter plot respectively, so as to form intervals to divide the scatter plot into a plurality of grids, wherein the X-axis corresponds to the concentration of the key pollutant and the Y-axis corresponds to the environmental parameter;

[0087] Traverse each data point and classify the data point into the corresponding grid according to the coordinate value corresponding to the data point;

[0088] For each grid containing data points, the center point of the grid is used as the initial cluster center;

[0089] Through continuous iteration, the data points are assigned to the nearest cluster center, and the position of the cluster center is recalculated until the preset number of iterations is reached, so as to achieve the distribution of data points to each cluster to obtain data point grouping.

[0090] In the embodiment of the present invention, by dividing the intervals, a large number of scattered data points can be effectively classified and organized into different grids. After the data points are grouped, a more in-depth analysis can be performed on each group without the need to examine the entire data set one by one, thereby improving the efficiency of data analysis. The interval division and clustering results can be intuitively displayed on the scatter plot, making the relationship and pattern between the data more clearly visible.

[0091] When used specifically, collect historical data on key pollutant concentrations (such as dust, sulfur dioxide, etc.) and environmental parameters (such as temperature, humidity, etc.), ensure the accuracy and completeness of the data, and preprocess the data, such as removing outliers and filling missing values. Analyze the data distribution of the X-axis (key pollutant concentration) and the Y-axis (environmental parameters), set the number and range of intervals, and ensure that there are enough data points in each interval for subsequent analysis. According to the determined interval division scheme, set boundary values ​​on the X-axis and Y-axis respectively to form multiple grids, each of which represents a specific pollutant concentration range and environmental parameter range. Traverse each data point and classify the data point into the corresponding grid according to its pollutant concentration and environmental parameter coordinate values. For data points that fall on the grid boundary, you can choose to classify them into one of the adjacent grids according to the actual situation. For each grid containing data points, calculate the average coordinates of all data points in it to obtain the center point of the grid, use these center points as the initial cluster centers, use distance measurement methods (such as Euclidean distance) to calculate the distance between each data point and each cluster center, assign the data point to the nearest cluster center to form an initial cluster, and recalculate the center point of each cluster, that is, the average coordinates of all data points in the cluster. Repeat the above steps until the preset number of iterations is reached or the change in the cluster center is less than a certain threshold, and the clustering results are considered to be stable. Output the final clustering results, including information such as the data points, cluster centers, and cluster sizes of each cluster. Analyze the clustering results and explore the differences in pollutant concentrations and environmental parameters between different clusters and their possible causes.

[0092] For example, suppose that the relationship between pollutants (such as dust) and environmental parameters (such as workshop temperature) generated during the production of ceramics is analyzed in order to optimize production conditions and reduce pollution emissions. Production data for the past year, including daily dust concentration and workshop temperature, were collected. According to the distribution of historical data, the dust concentration was divided into three intervals: low, medium, and high, and the workshop temperature was divided into three intervals: cold, warm, and hot. In this way, the scatter plot was divided into 9 grids. According to the daily dust concentration and workshop temperature data, the data points were classified into the corresponding grids. Initial cluster center setting and cluster iteration: Cluster analysis was performed according to steps 5 and 6 in the above specific implementation process. Through cluster analysis, it was found that: in an environment with low temperature and low dust concentration, product quality was the best and pollution emissions were the lowest; in an environment with high temperature and high dust concentration, product quality decreased and pollution emissions increased; in an environment with medium temperature and medium dust concentration, product quality and pollution emissions were at an intermediate level. Based on these findings, it was decided to adjust the production conditions and try to keep production in an environment with low temperature and low dust concentration to optimize product quality and reduce pollution emissions.

[0093] In a preferred embodiment of the present invention, determining the distribution of data points in each grid according to the data point grouping includes:

[0094] Traverse the data points in each data point group, and for each traversed data point, determine the grid to which the data point belongs according to the coordinate value corresponding to the data point;

[0095] After all data point groups are traversed, the distribution of data points in each grid is determined.

[0096] In an embodiment of the present invention, by determining the distribution of data points in each grid, the distribution of data in different intervals can be more intuitively understood, which helps to discover patterns and trends in the data. Gridded data point distribution can provide refined operation and decision support. For example, in terms of pollution control, production condition optimization, etc., more targeted strategies can be formulated based on the density and distribution of data points in different grids. By gridding the data points, subsequent data analysis and processing can be carried out more efficiently, because similar data points have been classified into the same grid, which is convenient for batch processing and analysis.

[0097] The specific implementation process includes: setting a counter for each grid to record the number of data points in the grid, traversing the data points in each group for the data point grouping obtained by clustering, and determining the grid to which it belongs based on its coordinate value (key pollutant concentration on the X-axis and environmental parameters on the Y-axis) for each traversed data point. After classifying the data point into the corresponding grid, increase the value of the grid counter. When all data point groups have been traversed, the counter of each grid will reflect the number of data points in the grid, and output the distribution of data points in each grid, which can be the number of data points in the grid, the proportion or other statistical information.

[0098] For example, in the process of producing ceramics, we want to understand the dust pollution under different environmental conditions in the production workshop. The data of dust concentration (X-axis) and workshop temperature (Y-axis) at different locations in the workshop over a period of time are collected, and the data points are grouped. Next, the distribution of data points in each grid is determined using the above specific implementation process: First, several grids are divided according to the range of dust concentration and workshop temperature, and a counter is set for each grid. Then, the data point groups obtained by clustering are traversed, and for each data point, it is classified into the corresponding grid according to its coordinate values ​​of dust concentration and workshop temperature, and the counter of the grid is updated. When all data point groups are traversed, the number of data points in each grid is obtained. By analyzing the distribution of these data points, it is found that: in some grids with high temperature and high dust concentration, the data points are distributed more densely, which indicates that dust pollution may be more serious under these environmental conditions. In some grids with low temperature and low dust concentration, the data points are distributed more sparsely, which indicates that these environmental conditions may be more ideal and dust pollution is lighter. Based on these findings, it was decided to renovate the production workshop to improve the environmental conditions in the high temperature and high dust areas and reduce dust pollution. At the same time, it is also planned to add dust removal equipment and ventilation facilities in these key areas to improve the quality of the working environment.

[0099] In a preferred embodiment of the present invention, the final mutual information value is calculated according to the distribution of data points, including:

[0100] For key pollutant concentrations and environmental parameters, the frequency of occurrence of data points in each interval is calculated to obtain the interval probability corresponding to each interval, and the joint probability of the data points appearing in a specific grid on the scatter plot is calculated;

[0101] The marginal entropy of key pollutant concentrations and environmental parameters are calculated based on interval probabilities;

[0102] Calculate the joint entropy of key pollutant concentrations and environmental parameters based on joint probabilities;

[0103] According to the marginal entropy and joint entropy Calculate the mutual information I(X;Y), where and w k is the weight factor, α, β and γ are smoothing parameters, ∑ k w k and∑ k ∑ l w kl is the sum of the weight factors, c(x i )、c(y j ) and c(x i ,y j ) represent the concentration of key pollutants in the interval x i , the interval y of environmental parameters j And the grid (x i ,y j ), i is the interval of indexing key pollutant concentrations, j is the interval of indexing environmental parameters, k and l are index variables; j' and i' are the index variables for summation; c(x i' ) represents the number of data points appearing in the i'th interval among all possible intervals of the key pollutant concentration; c(y j' ) represents the number of data points that appear in the j'th interval among all possible intervals of the environmental parameters; c(x i' ,y j' ) represents the number of data points appearing in the intersection area of ​​the i'th interval of the key pollutant concentration and the j'th interval of the environmental parameter; the mutual information I(X;Y) represents the correlation between the key pollutant concentration and the environmental parameter.

[0104] In the embodiment of the present invention, by calculating the mutual information value, the correlation between the concentration of key pollutants and environmental parameters can be quantified, which helps to understand the strength of the connection between the two, so as to more accurately predict and control the emission of pollutants. Through the mutual information value, the production strategy can be adjusted according to environmental factors to reduce pollution and improve efficiency. By analyzing the mutual information value, it is possible to identify which environmental factors have the greatest impact on pollutant emissions, so as to conduct risk assessment and formulate prevention strategies.

[0105] When applied specifically, it specifically includes: collecting dust concentration data and workshop temperature data over a period of time (for example, one month) from the monitoring system for ceramic production, ensuring that the data appears in pairs, that is, each dust concentration data point has a corresponding workshop temperature data point. According to the range of dust concentration and workshop temperature, they are divided into several intervals respectively. For example, dust concentration can be divided into three intervals: low, medium, and high, and workshop temperature can be divided similarly. Create a grid on a two-dimensional plane, each grid represents a combination of a dust concentration interval and a workshop temperature interval, and classify each pair of dust concentration and workshop temperature data points into the corresponding grid.

[0106] For each dust concentration interval and workshop temperature interval, the frequency of occurrence of data points is calculated, which can be achieved by counting the number of data points in each interval and dividing it by the total number of data points; for each grid (i.e., the interval combination of dust concentration and workshop temperature), the joint probability of the occurrence of data points is calculated, which is achieved by dividing the number of data points in a specific grid by the total number of data points. Using the interval probabilities calculated above, the marginal entropy of dust concentration and workshop temperature is calculated respectively. The marginal entropy represents the uncertainty of a single variable (such as dust concentration or workshop temperature). Using the joint probability calculated above, the joint entropy of dust concentration and workshop temperature is calculated. The joint entropy represents the uncertainty of the simultaneous occurrence of two variables. Based on the marginal entropy and joint entropy, the mutual information value between dust concentration and workshop temperature is calculated using the formula of mutual information. Mutual information represents the degree of correlation between two variables. The size of the mutual information value is analyzed. A larger mutual information value indicates that there is a stronger correlation between dust concentration and workshop temperature. According to the results of the mutual information value, corresponding strategies can be formulated to optimize the production environment and reduce dust emissions.

[0107] For example, when producing ceramics, it was found that the dust concentration in the production workshop was high, which may have a negative impact on the health and production efficiency of employees. In order to understand the relationship between dust concentration and workshop temperature, it was decided to use the above method to calculate the mutual information value between them. By collecting and analyzing the dust concentration and workshop temperature data within one month, it was found that when the workshop temperature was between 25-30 degrees Celsius, the dust concentration was often at a medium level, when the workshop temperature exceeded 30 degrees Celsius, the dust concentration increased significantly, and when the workshop temperature was below 20 degrees Celsius, the dust concentration was relatively low. According to the calculation results of the mutual information value, it was found that there was a strong correlation between dust concentration and workshop temperature, which means that by controlling the workshop temperature, the dust concentration can be controlled to a certain extent. Based on these findings, it was decided to take the following measures:

[0108] A temperature control system was installed in the workshop to ensure that the workshop temperature was maintained between 20-25 degrees Celsius to reduce dust concentration, ventilation facilities in the workshop were strengthened to improve air quality and reduce dust accumulation, and employees were regularly examined to ensure that their health was not affected by dust. Through the implementation of these measures, the dust concentration in the production workshop was successfully reduced, and the working environment and production efficiency of employees were improved.

[0109] In a preferred embodiment of the present invention, the concentration of key pollutants is compared with a preset influencing factor to obtain a comparison result, including:

[0110] pass Calculate the impact factor, where D represents the impact factor of key pollutants; x m is the measured value of the mth environmental condition, M is the total number of environmental conditions, ∈ is a positive number, and m and n are indices, where:

[0111] Among them, a m It represents the average impact of the linear change of the mth environmental condition on the key pollutant impact factor D. If a m is positive, indicating that as x m As the value of x increases, the key pollutant impact factor D also tends to increase; if it is negative, the opposite is true; mi is the measured value of the mth environmental condition in the ith sample, is the average value of the mth environmental condition in all samples, D i is the impact factor measurement value of the i-th sample, is the average of all sample impact factors, N is the total number of samples, and i is the index;

[0112] When m=n, Among them, b mm Indicates the contribution of the interaction between different environmental conditions to the influencing factor. If b mm is positive, indicating that as x m As the square of x increases, the key pollutant impact factor D also tends to increase, which may indicate that there is an optimal x m value; if it is negative, there exists an x ​​that minimizes D m value;

[0113] When m≠n, Among them, D i is the observed value of the key pollutant influencing factor, x ni is the measured value of the nth environmental condition in the ith sample, is the average value of the nth environmental condition, b mn It represents the joint impact of the mth environmental condition and the nth environmental condition on the key pollutant influencing factor D when they change simultaneously. If bmn is positive, indicating that when x m and x n When they increase at the same time, the key pollutant impact factor D also tends to increase; if it is negative, the opposite is true;

[0114] Among them, c m It represents the impact of the logarithmic transformation of the mth environmental condition on the key pollutant impact factor D;

[0115] Where d is the intercept of the regression line, which means that when all environmental conditions x m When all are 0 (or their average value, depending on whether the data is centered), the predicted values ​​of the key pollutant impact factors are: and They are the key pollutant impact factors D and x m The average value of

[0116] The key pollutant impact factor D is compared with the key pollutant concentration to obtain a comparative result.

[0117] In the embodiment of the present invention, the relationship between environmental conditions and key pollutant influencing factors can be captured more accurately, thereby improving the accuracy of prediction and comparison. The above formula contains linear terms, quadratic terms, and logarithmic terms, which can adapt to different forms of relationships, making the model more flexible and universal. The calculated influencing factors are compared and analyzed with the actual measured concentrations of key pollutants to observe their consistency. If the influencing factors are found to be high or have a large deviation from the actual pollutant concentration, it indicates that the current environmental conditions may not be conducive to the control of pollutants. At this time, based on the analysis results of the model, the environmental conditions in the production process can be adjusted (such as adjusting the temperature, humidity or ventilation volume of the kiln, etc.) to reduce pollutant emissions.

[0118] For example, a ceramic production company has been facing environmental pressure in recent years and needs to reduce pollutant emissions in its production process. To achieve this goal, it decided to use a mathematical model to analyze and optimize its production process. Production data was collected for one month, and the main environmental conditions included: temperature and humidity in the production workshop, operating time of production equipment, type and amount of raw materials, etc. At the same time, the corresponding pollutant (such as particulate matter) emission concentration data was also collected.

[0119] To calculate the impact factor D, we first use an extended form of the multiple linear regression model that takes into account linear, quadratic, and logarithmic terms. The specific steps are as follows:

[0120] Qualitative variables (such as raw material types) were one-hot encoded and converted into dummy variables, and all quantitative variables (temperature, humidity, equipment operating time, raw material usage) were standardized, that is, the mean was subtracted and divided by its standard deviation, so as to consider the impact of each variable more fairly in the model.

[0121] Using the collected data, a regression model is constructed that contains linear terms, quadratic terms, and logarithmic terms. The model form is as follows:

[0122]

[0123] Estimate the parameters a in the model by using the least squares method or other optimization algorithms m , b mn , c m and d, these parameters represent the quantitative impact of environmental conditions on the pollutant impact factor D; the estimated parameters and daily environmental condition measurements are substituted into the model to calculate the daily impact factor D.

[0124] After obtaining the daily impact factor D, it was compared with the daily pollutant emission concentration. The correlation between the impact factor D and the pollutant emission concentration was analyzed by drawing scatter plots and calculating correlation coefficients. It was found that when the impact factor D was high, the pollutant emission concentration was also often high, indicating that environmental conditions had a significant impact on pollutant emissions. Further analysis of the impact of individual environmental conditions determined the optimal control range of key factors such as temperature and humidity.

[0125] Based on the above analysis, it is decided to take the following optimization measures:

[0126] Install advanced temperature control systems to ensure that the temperature of the production workshop is always maintained within the optimal range, increase humidity control equipment in the workshop to maintain a constant humidity level, and upgrade production equipment to reduce pollutants generated during equipment operation. Through the above methods, the key factors affecting pollutant emissions were successfully identified and corresponding optimization measures were formulated. These measures not only help reduce pollutant emissions, but also improve production efficiency, achieving both economic and environmental benefits.

[0127] In another preferred embodiment of the present invention, the above step 17 may include:

[0128] First, it is necessary to integrate the comparison results obtained in step 16, that is, the comparison data of the key pollutant concentration and the preset influencing factors, and at the same time, consider the mutual information value calculated in step 15, which reflects the correlation between environmental parameters and pollutant concentrations. According to the integrated data, analyze which environmental parameters have the greatest impact on pollutant concentrations, that is, find out the main pollution influencing factors, evaluate the overall situation of air pollution in the ceramic production process, including the types of pollutants, concentration levels and possible pollution sources, and according to the analysis results, obtain the specific situation and main influencing factors of air pollution in the ceramic production process.

[0129] For example, a ceramic production plant is located in an industrial area. In recent years, as the scale of production has expanded, the surrounding residents have expressed concerns about the air pollution that may be generated during its production process. In order to solve this problem, the above analysis method is used, including:

[0130] The concentration data of key pollutants (such as sulfur dioxide, nitrogen oxides, etc.) were collected for one consecutive month and compared with the preset influencing factors (such as temperature, humidity, operating time of production equipment, etc.). At the same time, according to step 15, the mutual information value between each environmental parameter and the pollutant concentration was calculated. By comparing the results, it was found that when the temperature of the production workshop exceeded 28°C, the concentrations of sulfur dioxide and nitrogen oxides increased significantly. The mutual information value also showed that there was a high correlation between temperature and the concentrations of these two pollutants. In the ceramic production process, high temperature is the main factor leading to increased emissions of sulfur dioxide and nitrogen oxides. In order to reduce pollution, it was decided to install a temperature control system in the production workshop to ensure that the temperature is always maintained below 25°C. By implementing temperature control measures, the temperature of the production workshop was successfully controlled below 25°C, thereby effectively reducing the emission concentrations of sulfur dioxide and nitrogen oxides.

[0131] like Figure 2 As shown, an embodiment of the present invention further provides an atmospheric environment pollution data analysis device 20, comprising:

[0132] The acquisition module 21 is used to set gas sampling points at various links of ceramic production; obtain gas samples collected at various sampling points and sampling environmental parameters corresponding to the gas samples in real time; perform component analysis on the gas samples to obtain the concentration of key pollutants; and use the concentration of key pollutants and the corresponding environmental parameters as two variables to form a scatter plot;

[0133] The processing module 22 is used to determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid according to the data point groups, and calculate the final mutual information value according to the data point distribution; compare the concentration of key pollutants with the preset influencing factors to obtain comparison results; based on the comparison results and the final mutual information value, evaluate the status and influencing factors of air pollution in the ceramic production process to obtain evaluation results.

[0134] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0135] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0136] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0137] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0139] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0142] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0143] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using basic programming skills after reading the description of the present invention.

[0144] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0145] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for analyzing atmospheric environmental pollution data, characterized in that: The method comprises: Set up gas sampling points at various stages of ceramic production; Obtain the gas samples collected at each sampling point and the sampling environment parameters corresponding to the gas samples in real time; Conduct composition analysis on gas samples to obtain key pollutant concentrations; The concentration of key pollutants and the corresponding environmental parameters are used as two variables to construct a scatter plot; Determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid based on the data point groups, and calculate the final mutual information value based on the data point distribution; Compare the concentration of key pollutants with the preset influencing factors to obtain comparative results; According to the comparison results and the final mutual information value, the status and influencing factors of air pollution in the ceramic production process are evaluated to obtain the evaluation results; Determine the final interval division plan, including: Initialize a group of particles, each particle represents an interval partitioning scheme, which includes the number, position and size of intervals; A fitness function is used to determine the quality of the interval division scheme; according to the fitness function, the fitness value of each particle is calculated, and the position and speed of the particle are updated according to the fitness value to obtain the final interval division scheme; Divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups, including: According to the determined interval division scheme, the boundary values ​​of the intervals are determined on the X-axis and Y-axis of the scatter plot respectively, so as to form intervals to divide the scatter plot into a plurality of grids, wherein the X-axis corresponds to the concentration of the key pollutant and the Y-axis corresponds to the environmental parameter; Traverse each data point and classify the data point into the corresponding grid according to the coordinate value corresponding to the data point; For each grid containing data points, the center point of the grid is used as the initial cluster center; Through continuous iteration, the data points are assigned to the nearest cluster center, and the position of the cluster center is recalculated until the preset number of iterations is reached, so as to achieve the distribution of data points to each cluster to obtain data point grouping; According to the data point grouping, determine the distribution of data points in each grid, including: Traverse the data points in each data point group, and for each traversed data point, determine the grid to which the data point belongs according to the coordinate value corresponding to the data point; When all data point groups are traversed, the distribution of data points in each grid is determined; According to the distribution of data points, the final mutual information value is calculated, including: For key pollutant concentrations and environmental parameters, the frequency of occurrence of data points in each interval is calculated to obtain the interval probability corresponding to each interval, and the joint probability of the data points appearing in the grid on the scatter plot is calculated; The marginal entropy of key pollutant concentrations and environmental parameters are calculated based on interval probabilities; Calculate the joint entropy of key pollutant concentrations and environmental parameters based on joint probabilities; According to the marginal entropy and joint entropy Calculating mutual information ,in, , , and is the weight factor, , and is the smoothing parameter, and is the sum of the weight factors, , and Respectively represent the range of key pollutant concentrations , the range of environmental parameters and the grid The number of data points in i is the interval of index key pollutant concentration, j are the intervals of index environment parameters, k and l is the index variable; j' and i' is the index variable to be summed; Indicates that among all possible ranges of key pollutant concentrations, i' The number of data points that appear in an interval; Indicates that among all possible intervals of environmental parameters, j' The number of data points that appear in an interval; Indicates the concentration of key pollutants i' interval and environmental parameters j' The number of data points that appear in the intersection of the intervals; Mutual Information Express the correlation between key pollutant concentrations and environmental parameters; Compare the concentration of key pollutants with the preset impact factors to obtain comparative results, including: pass Calculate the impact factor, where Indicates the key pollutant impact factor; is the measured value of the mth environmental condition, M is the total number of environmental conditions, is a positive number, m and n are indices, represents the average impact of the linear change of the mth environmental condition on the key pollutant influencing factor D, It represents the joint impact of the mth environmental condition and the nth environmental condition on the key pollutant influencing factor D when they change simultaneously. represents the impact of the logarithmic transformation of the mth environmental condition on the key pollutant impact factor D, and d is the intercept of the regression line; The key pollutant influencing factors Compare with key pollutant concentrations to get comparative results.

2. An atmospheric environmental pollution data analysis system, characterized in that: Applied in the method as claimed in claim 1, comprising: The acquisition module is used to set gas sampling points in various links of ceramic production; obtain the gas samples collected at each sampling point and the sampling environmental parameters corresponding to the gas samples in real time; analyze the components of the gas samples to obtain the concentration of key pollutants; and use the concentration of key pollutants and the corresponding environmental parameters as two variables to form a scatter plot; The processing module is used to determine the final interval division scheme, divide the intervals in the X-axis and Y-axis directions of the scatter plot to obtain data point groups; determine the distribution of data points in each grid according to the data point groups, and calculate the final mutual information value according to the data point distribution; compare the concentration of key pollutants with the preset influencing factors to obtain comparison results; evaluate the status and influencing factors of air pollution in the ceramic production process according to the comparison results and the final mutual information value to obtain evaluation results.

3. A computing device, characterized in that: include: one or more processors; A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in claim 1.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to claim 1 when executed by a processor.

Citation Information

Patent Citations

  • Regional spatial quality analysis method

    CN103336093A

  • Evolutionary ensemble learning-based atmospheric pollutant concentration space-time prediction method

    CN114578457A

  • Sewage treatment intelligent control method and system based on data fusion

    CN116589078A

  • Evaluation method for impact of emission control on air quality, device and storage medium thereof

    US20200393434A1