A method and system for monitoring vocs

Abstract

The present disclosure provides a VOCs monitoring method and system, which belongs to the technical field of environmental monitoring. The method comprises the following steps: determining the data feature type of historical first VOCs data, wherein the historical first VOCs data is obtained by monitoring a target area by a historical target monitoring point; the data feature type comprises a seasonal type and a non-seasonal type; determining a prediction model based on the data feature type of the historical first VOCs data; predicting the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is obtained by monitoring VOCs in the target area based on the target monitoring point; and determining the VOCs warning level of the target area based on the target prediction result. The VOCs monitoring method and system provided by the present disclosure can improve the accuracy and reliability of VOCs monitoring.

Description

Technical Field

[0001] This disclosure belongs to the field of environmental monitoring technology, and more specifically, relates to a VOCs monitoring method and system. Background Technology

[0002] With the acceleration of industrialization and urbanization, the emission of volatile organic compounds (VOCs) has become an increasingly serious problem. VOCs are a class of organic compounds that are easily volatile at room temperature, and their sources are wide-ranging, covering many fields such as chemical production, painting operations, printing industry, and automobile exhaust emissions.

[0003] VOCs not only significantly impact air quality but also pose a serious threat to human health. In the atmosphere, VOCs are important precursors to secondary pollutants such as ozone and fine particulate matter (PM2.5). When they undergo photochemical reactions with nitrogen oxides under sunlight, they promote an increase in near-surface ozone concentration, forming photochemical smog. This not only reduces atmospheric visibility and affects transportation but also damages plant growth and ecosystem balance. Furthermore, long-term exposure to environments containing high concentrations of VOCs can cause respiratory irritation, dizziness, nausea, and fatigue. Some toxic and carcinogenic VOCs, such as benzene and formaldehyde, further increase the risk of cancer and other serious diseases.

[0004] Traditional environmental monitoring methods can only obtain limited real-time data and cannot comprehensively and accurately predict future VOCs concentration trends, making it difficult to provide sufficient time and decision-making basis for effective pollution prevention and control.

[0005] Therefore, there is an urgent need for an accurate and reliable method for monitoring VOCs. Summary of the Invention

[0006] The purpose of this disclosure is to provide a VOCs monitoring method and system to improve the accuracy and reliability of VOCs monitoring.

[0007] A first aspect of this disclosure provides a VOCs monitoring method, comprising:

[0008] The data characteristic types of the historical first VOCs data are determined. The historical first VOCs data are data obtained from monitoring the target area by historical target monitoring points. The data characteristic types include seasonal and non-seasonal types.

[0009] The prediction model is determined based on the data feature type of the first historical VOCs data. The prediction model is used to predict the first VOCs data to obtain the target prediction result. The first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring points.

[0010] The VOCs warning level for the target area is determined based on the target prediction results.

[0011] A second aspect of this disclosure provides a VOCs monitoring system, comprising:

[0012] The data feature determination module is used to determine the data feature type of the historical first VOCs data. The historical first VOCs data is the data obtained by monitoring the target area by the historical target monitoring points. The data feature types include seasonal and non-seasonal types.

[0013] The prediction module is used to determine the prediction model based on the data feature type of the first historical VOCs data, and to predict the first VOCs data based on the prediction model to obtain the target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring points;

[0014] The early warning module is used to determine the VOCs early warning level of the target area based on the target prediction results.

[0015] A third aspect of this disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the VOCs monitoring method described above.

[0016] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the VOCs monitoring method described above.

[0017] The beneficial effects of the VOCs monitoring method and system provided in this disclosure are as follows:

[0018] This disclosure improves the timeliness of monitoring by acquiring first-order VOCs data through real-time monitoring of target areas based on target monitoring points, thereby rapidly capturing dynamic changes in VOCs emissions. Furthermore, by utilizing the data characteristics of historical first-order VOCs data to construct a predictive model, this disclosure fully leverages the patterns and trends in historical data to improve the accuracy of predicting future VOCs emissions. Finally, by using a predictive model to predict first-order VOCs data and obtaining target prediction results, this disclosure achieves the analysis and prediction of VOCs emissions, improving the accuracy and reliability of VOCs monitoring. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of a VOCs monitoring method provided in an embodiment of the present disclosure;

[0021] Figure 2 This is a structural block diagram of a VOCs monitoring system provided in one embodiment of the present disclosure;

[0022] Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present disclosure. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0024] To make the objectives, technical solutions, and advantages of this disclosure clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0025] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a VOCs monitoring method according to an embodiment of the present disclosure. The method includes:

[0026] S101: Determine the data feature type of the first historical VOCs data. The first historical VOCs data is the data obtained by monitoring the target area by the historical target monitoring points; the data feature type includes seasonal type and non-seasonal type.

[0027] In this embodiment, VOCs refers to volatile organic compounds. The first historical VOCs data refers to the VOCs data obtained when the target monitoring point monitored the target area in the past. The data type of the first historical VOCs data includes VOCs concentration value and sampling time.

[0028] A target monitoring point is a specific location set up to monitor a specific target area. Target monitoring points are equipped with relevant monitoring equipment, such as sensors and monitoring instruments.

[0029] The target area is the geographical area that needs to be monitored for VOCs, which can be an industrial park, a certain area of ​​a city, etc.

[0030] Data feature type refers to whether it is seasonal, that is, whether the data features meet seasonal characteristics. This is considered because VOCs data in some regions may show seasonal variations. For example, in agricultural planting areas, agricultural production activities have obvious seasonality. During the crop growing season, such as spring sowing and summer growth stages, plants release a large amount of VOCs, and pesticides and fertilizers used in agricultural production also volatilize and produce VOCs. After the harvest season, the relevant emission sources decrease, and the VOCs concentration decreases.

[0031] In some regions, VOCs data do not show significant seasonal changes. For example, in tropical rainforests, the climate is relatively stable due to high temperatures and abundant rainfall throughout the year. Plant growth and metabolic activities do not show significant seasonal differences, and emissions from biological sources are relatively stable.

[0032] Therefore, this embodiment can more accurately select a suitable prediction model in subsequent processing by determining the data feature type of VOCs. Specifically, the data feature type of the first historical VOCs data can be determined in the following ways:

[0033] Historical time series plots were determined based on the first historical VOCs data.

[0034] The historical time series graph is input into the first neural network model to obtain the data feature types of the first historical VOCs data; the first neural network model is obtained by training with a certain amount of VOCs data and its corresponding data feature types.

[0035] In this embodiment, a historical time series graph is a graph plotted with time as the horizontal axis and the value (concentration) of the first historical VOCs data as the vertical axis. It can intuitively show the changes in VOCs data over time. If the data has significant seasonality, it will usually show obvious periodic fluctuations.

[0036] The obtained historical time series graph can be input into the first neural network model to obtain the data feature types of the historical first VOCs data. These data feature types can include seasonal and non-seasonal types. It's important to note that the first neural network is trained with a certain amount of VOCs data and its corresponding data feature types, and also includes corresponding seasonal periodic values. This process is not limited to the first VOCs data; even if the VOCs data is from other monitoring points or obtained through other methods, it can still be used as training data. "A certain amount" refers to the quantity sufficient for the neural network to train and output; this can be set based on experience or the data set to solve similar problems.

[0037] S102: Determine the prediction model based on the data feature type of the first historical VOCs data, and predict the first VOCs data based on the prediction model to obtain the target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point.

[0038] In this embodiment, the first VOCs data refers to the relevant VOCs data obtained at the current stage by monitoring the target area through the target monitoring point, such as concentration value, sampling time and other information.

[0039] In this embodiment, the prediction model is determined based on the data feature type of the first historical VOCs data, including:

[0040] In response to the fact that the data type of the first historical VOCs data is non-seasonal, the autoregressive integral moving average model was determined as the prediction model.

[0041] Since the data characteristics of the first historical VOCs data are seasonal, the seasonal autoregressive integral moving average model is selected as the prediction model.

[0042] In this embodiment, as shown in S101, the data feature types can include seasonal and non-seasonal types. Different prediction models should be used to predict the VOCs data of the target area for different data feature types. The prediction models include the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0043] Specifically, the autoregressive integral moving average model consists of three parts: autoregression, integration, and moving average. The autoregressive part represents the linear relationship between the current value and past values ​​of the time series, i.e. ,in, It is the current moment. VOCs concentration, It's the past VOCs concentration at each time point It is the autoregressive coefficient. It is the order of autoregression. It is a white noise error sequence.

[0044] The integral part is used to handle the non-stationarity of the time series. By performing a differencing operation on the time series, it is transformed into a stationary series. A differencing operation is performed on a non-stationary VOCs time series to make it stationary. If the original series... go through After order differencing, it becomes a stationary sequence, i.e. ,in, It is a lag operator, it is Difference operator.

[0045] The moving average portion describes the linear relationship between the current error and past errors of a time series, expressed as: ,in, It is the moving average coefficient. It is the order of the moving average.

[0046] The comprehensive model, the autoregressive integral moving average model, can be expressed as follows: Combining the above three parts, the complete model expression is as follows: ,in, , , The polynomial representing the seasonal autoregressive component. It is a polynomial of the seasonal moving average component.

[0047] The seasonal autoregressive integral moving average model adds a seasonally relevant parameter to the autoregressive integral moving average model, denoted as . ,in, This is the seasonal autoregressive order, representing the difference between the current seasonal value and past values. A linear relationship between seasonal values The seasonal differencing order is used to bring seasonally non-stationary time series to stationarity, and to perform seasonal differencing on the time series. Subseasonal differences. The order of the seasonal moving average describes the error between the current season and the past. The relationship between seasonal errors. This represents the length of the seasonal cycle.

[0048] In this embodiment, the target prediction result includes information such as the VOCs concentration value at a future time and the concentration change trend.

[0049] Based on the established prediction model, the first newly acquired VOCs data—that is, the latest VOCs data obtained from the target monitoring point in the target area—is input into this prediction model. The prediction model analyzes and calculates the input VOCs data according to its own algorithm and parameters, thereby predicting the VOCs situation in the target area over a future period. The final output of this prediction result is called the target prediction result.

[0050] S103: Determine the VOCs warning level for the target area based on the target prediction results.

[0051] In this embodiment, the target prediction result contains VOCs concentration information for the target area over a future period of time. The VOCs warning level of the target area should be determined based on the relevant environmental protection standards, policies and regulations of the target area, and the VOCs concentration thresholds corresponding to different warning levels should be determined.

[0052] In this embodiment, the warning level can be determined based on a single evaluation indicator. For example, when the predicted VOCs concentration exceeds the first-level threshold but is lower than the second-level threshold, it is determined to be a first-level warning; when the concentration exceeds the second-level threshold, it is determined to be a second-level warning, and so on.

[0053] Multiple indicators can also be considered to determine the warning level. For example, in one embodiment of this disclosure, determining the VOCs warning level of a target area based on the target prediction result includes:

[0054] Based on the target prediction results, determine the VOCs concentration index, VOCs concentration change trend index, and duration index in the target area;

[0055] The early warning index is obtained by weighting the VOCs concentration index, the VOCs concentration change trend index, and the duration index.

[0056] The VOCs warning level for the target area is determined based on the warning indicators.

[0057] In this embodiment, the VOCs concentration index can be directly obtained from the target prediction result. The VOCs concentration change trend index can be calculated by comparing the VOCs concentration at different time points in the target prediction result, or by using the concentration data at multiple time points in the target prediction result and fitting a trend line using mathematical methods (such as the least squares method). The slope of the trend line can then be used as the VOCs concentration change trend index. A positive slope indicates an upward trend in concentration, while a negative slope indicates a downward trend in concentration. The absolute value of the slope indicates the rate of change. If the target prediction result shows that the VOCs concentration is within a specific range or exhibits a specific change trend over a certain period of time, this period of time is the duration index. Alternatively, a threshold for VOCs concentration or change trend can be set based on relevant standards or experience. When the predicted VOCs concentration exceeds this threshold or the change trend reaches a certain level, the duration is calculated until it falls below the threshold.

[0058] The weights of VOCs concentration indicators, VOCs concentration change trend indicators, and duration indicators can be set based on expert experience.

[0059] Considering that the weights should be different for different temperatures or regions, for example, in one embodiment of this disclosure, a VOCs monitoring method further includes:

[0060] In response to the population density of the target area being greater than the first population density, the weight of VOCs concentration is increased by the first density step, the weight of VOCs change is decreased by the second density step, and the weight of duration is decreased by the third density step.

[0061] In response to the target area being an industrial concentration area and / or the ambient temperature in the target area being greater than a first temperature, the weight of VOCs change is increased with a first industrial step, the weight of VOCs concentration is decreased with a second industrial step, and the weight of duration is decreased with a third industrial step.

[0062] In response to the target area being an ecological protection zone, the weight of duration is increased with the first ecological step, the weight of VOCs concentration is decreased with the second density step, and the weight of VOCs change is decreased with the third density step.

[0063] Among them, the VOCs concentration weight is the weight corresponding to the VOCs concentration index, the VOCs change weight is the weight corresponding to the VOCs concentration change trend index, and the duration weight is the weight corresponding to the duration index.

[0064] In this embodiment, in densely populated urban centers, high concentrations have a more direct and significant impact on residents' health. Therefore, the weight of concentration indicators should be increased to ensure timely issuance of high-concentration pollution warnings. The first population density, first density step size, second density step size, and third density step size can be set based on experience, but it should be noted that the first density step size is equal to the sum of the second and third density step sizes.

[0065] Secondly, industrial production is the main source of VOCs emissions, so the focus should be on the emissions and concentration changes of enterprises. The weight of VOCs concentration and trend indicators can be appropriately increased to facilitate the timely detection of abnormal emissions from enterprises. The target area should be an industrial cluster, which can be predetermined. The first industrial step size equals the sum of the second and third industrial steps, and can be set based on experience.

[0066] Secondly, ecosystems are highly sensitive to long-term exposure to VOCs, and the weight of duration indicators should be increased to assess the impact on the ecological environment. Whether the target area belongs to an ecological protection zone should be predetermined, and the first ecological step length is equal to the sum of the second and third ecological steps, which can be set based on experience.

[0067] As can be seen from the above, this disclosure, by conducting real-time monitoring of the target area based on target monitoring points and acquiring the first VOCs data, can quickly capture the dynamic changes in VOCs emissions, thereby improving the timeliness of monitoring. This disclosure, by utilizing the data characteristics of historical first VOCs data to construct a predictive model, can fully leverage the patterns and trends in historical data to improve the accuracy of predicting future VOCs emissions. This disclosure, through predictive models to predict the first VOCs data and obtain target prediction results, realizes the analysis and prediction of VOCs emissions, improving the accuracy and reliability of VOCs monitoring.

[0068] In one embodiment of this disclosure, a VOCs monitoring method further includes:

[0069] The partial autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the partial autocorrelation function.

[0070] The autoregressive order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the partial autocorrelation function sequence.

[0071] In response to the prediction model being a seasonal autoregressive integral moving average model, seasonal difference is performed on the first VOCs data to obtain seasonally differenced VOCs data, and seasonal difference is performed on the historical first VOCs data to obtain historical seasonally differenced VOCs data.

[0072] The partial autocorrelation function sequence of the differential VOCs data and the historical differential VOCs data is determined based on the partial autocorrelation function.

[0073] The seasonal autoregressive order of the seasonal autoregressive integral moving average model is determined based on the differential partial autocorrelation function sequence.

[0074] In this embodiment, the partial autocorrelation function sequence is a numerical sequence obtained by calculating the first VOCs data and the historical first VOCs data using the partial autocorrelation function.

[0075] Partial autocorrelation function (PAC) measures the correlation between two observations in time series data after controlling for the influence of intermediate observations. For the first VOCs data and historical first VOCs data, the PAC sequence can be obtained by calculating their PAC coefficients at different time intervals.

[0076] For example, in a time series, if you want to know the direct correlation between the VOCs data at the current moment and the VOCs data three time units (time steps) ago, you can calculate it using the partial autocorrelation function. The series of correlation coefficients obtained constitutes the partial autocorrelation function sequence.

[0077] In autoregressive integral moving average (ARM) and seasonal autoregressive integral moving average (SRM) models, the autoregressive component represents the linear relationship between current and past values. By observing the partial autocorrelation function sequence, when the partial autocorrelation coefficient rapidly approaches zero after a certain lag order, this lag order can be used as the autoregressive order. .

[0078] For example, if the partial autocorrelation function sequence fluctuates around zero after a lag of 3, then we can consider setting the autoregression order to 3, which means that the current VOCs data is mainly directly related to the VOCs data of the past 3 time points, so as to construct the autoregressive part of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0079] In this embodiment, the rate of change of the partial autocorrelation function sequence can be calculated as a criterion for judging whether it rapidly approaches zero. For example, if the rate of change of the partial autocorrelation function at a consecutive first number of points is less than the first rate of change, then the smallest lag order among the lag orders corresponding to the first number of points is taken as the autoregressive order. The first number and the first rate of change can be preset based on experiments or experience.

[0080] The above calculations yield the autoregressive order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model. The seasonal autoregressive integral moving average model also has a seasonal autoregressive order, so it is necessary to determine the seasonal autoregressive order.

[0081] Considering the use of a seasonal autoregressive integral moving average model, it is evident that the data exhibits seasonality. To eliminate this seasonality and make the data more stable, facilitating modeling and analysis, seasonal differencing is necessary. The resulting difference is the seasonally differencing data. Performing this operation on both the first VOCs data and historical first VOCs data yields seasonally differencing VOCs data and historical seasonally differencing VOCs data, respectively. This processed data better reflects the trend after removing seasonality, which is beneficial for subsequent parameter estimation and prediction of the model.

[0082] Similar to determining the partial autocorrelation function sequence, the first VOCs data after seasonal differencing is the seasonally differencing VOCs data, and the historical first VOCs data after seasonal differencing is the historical seasonally differencing VOCs data. Calculating their partial autocorrelation functions yields the difference partial autocorrelation function sequence.

[0083] In a seasonal autoregressive integral moving average model, the seasonal autoregressive order determines the degree and manner in which seasonal factors influence the current value. By observing the differenced partial autocorrelation function sequence, similar to the method used to determine the autoregressive order, we find the lag order at which the partial autocorrelation coefficient rapidly approaches zero, and use this lag order as the seasonal autoregressive order. .

[0084] As can be seen from the above, this disclosure, by introducing a partial autocorrelation function to determine the autoregressive order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model, can more accurately capture the time dependence in VOCs data, thereby improving the model's fit and prediction accuracy. Through seasonal differencing, the influence of seasonal fluctuations on the model is eliminated, enabling this embodiment to more accurately reflect the long-term trend and seasonal changes in VOCs concentration, thus improving the accuracy and reliability of VOCs monitoring.

[0085] In one embodiment of this disclosure, a VOCs monitoring method further includes:

[0086] Time series data were obtained based on the first VOCs data and historical first VOCs data.

[0087] An augmented Dickey-Fuller test is performed on the time series. If the test result is non-stationary, the time series is differencing until the test result is stationary. The difference order corresponding to the stationary test result is used as the difference order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0088] Since the prediction model is a seasonal autoregressive integral moving average model, the time series is subjected to the HEGY test. If the test result is seasonally non-stationary, the time series is subjected to seasonal differencing until the test result is seasonally stationary. The seasonal differencing order corresponding to the test result being seasonally stationary is taken as the differencing order of the seasonal autoregressive integral moving average model.

[0089] In this embodiment, the first VOCs data and historical first VOCs data can be arranged in chronological order to form a time series. This time series reflects the changes in VOCs data over time and serves as the basis for subsequent analysis and modeling. For example, VOCs concentration data can be recorded for each hour of the day, and these data arranged in chronological order constitute a time series.

[0090] The Augmented Dickey-Fuller (ADF) test is a statistical method used to test whether a time series is stationary. If the ADF test result indicates that the time series is not stationary, it needs to be differencing. The purpose of differencing is to eliminate non-stationary factors such as trends or seasonality in the time series by subtracting the data from adjacent time points, thus making it stationary. First-order differencing calculates the difference between two adjacent time points, i.e. If the series is still not stationary after the first difference, a second difference can be performed, that is, the series after the first difference is differencing again, and so on. Continue the differencing process until the ADF test result shows that the time series has become stationary. The difference order performed at this point is the difference order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0091] When the prediction model is a seasonal autoregressive integral moving average model, in addition to considering the overall stationarity of the time series, it is also necessary to test its seasonal stationarity. The HEGY test is specifically used to test whether a time series has a seasonal unit root. If the HEGY test result indicates that the time series is seasonally non-stationary, seasonal differencing is required. Seasonal differencing is a differencing operation performed on the seasonal characteristics of the time series. For example, for monthly data, if there is a seasonal cycle of 12 months, then seasonal differencing calculates... By continuously performing seasonal differencing until the HEGY test results show that the time series becomes seasonally stationary, the order of seasonal differencing performed at this point is the seasonal differencing order of the seasonal autoregressive integral moving average model. .

[0092] As can be seen from the above, this disclosure effectively identifies the non-stationarity of time series through the augmented Dickey-Fuller test, and then gradually eliminates the trend term and / or seasonal factors through differencing, ensuring that the time series reaches a stationary state, which helps to improve the prediction accuracy and stability of this disclosure. This disclosure introduces the HEGY test, which is specifically used to detect the seasonal non-stationarity of time series, and can eliminate seasonal fluctuations in time series, thereby improving the seasonal prediction ability of this disclosure.

[0093] In one embodiment of this disclosure, a VOCs monitoring method further includes:

[0094] The autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the autocorrelation function.

[0095] The moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the autocorrelation function sequence.

[0096] Since the prediction model is a seasonal autoregressive integral moving average model, the seasonal autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the seasonal autocorrelation function.

[0097] The seasonal moving average order of the seasonal autoregressive integral moving average model is determined based on the seasonal autocorrelation function sequence.

[0098] In this embodiment, the autocorrelation function is used to measure the correlation between observations at different time points in a time series. For the first VOCs data and historical first VOCs data, calculating their autocorrelation coefficients at different lag orders yields the autocorrelation function sequence.

[0099] For example, suppose there is a set of VOC data sequences Autocorrelation coefficient .

[0100] .in It is the number of data samples. It is the mean of the data. By calculating different... Value This yields the autocorrelation function sequence. .

[0101] Autocorrelation function sequence, when the autocorrelation coefficient is of a certain order This order then decays rapidly to zero or fluctuates around zero. It can be used as the order of the moving average.

[0102] In this embodiment, the obtained autocorrelation sequence and autocorrelation coefficient can be combined to form a first sequence graph, and the first sequence graph can be input into a second neural network to obtain the moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0103] It should be noted that the second neural network was trained on a large dataset consisting of autocorrelation sequences, autocorrelation coefficients, and their corresponding moving average orders.

[0104] The above calculations yield the moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model. The seasonal autoregressive integral moving average model also includes the seasonal moving average order. .

[0105] Therefore, the seasonal autocorrelation function (SAC) can be used to measure the correlation between observations across different seasonal cycles. The SAC is a function that analyzes time series exhibiting seasonal characteristics, based on the autocorrelation function. For example, ,in, The seasonal cycle can be obtained through the first neural network model.

[0106] In this disclosure, the partial autocorrelation function is used to calculate the order of the autoregression, while the autocorrelation function is used to calculate the order of the moving average. This is because the partial autocorrelation function measures the direct correlation between observations in a time series separated by a specific lag order, after controlling for the influence of intermediate observations. For an autoregressive process, the partial autocorrelation function directly reflects the true dependency between the current value and past values, unaffected by other intermediate lag terms. The autoregressive model describes the linear relationship between the current observation and observations from several past periods; its core is to determine which specific past lag values ​​the current value has a direct dependency on. The partial autocorrelation function clearly shows the order of this direct dependency; that is, a lag order where the partial autocorrelation function is significantly non-zero often corresponds to the order of the autoregressive model.

[0107] The autocorrelation function measures the overall correlation between observations at different lag orders in a time series, encompassing all possible dependencies and the combined effect of random disturbances. The moving average model primarily describes the current observation as a linear combination of random error terms from several past periods; its impact on the observation is cumulative, unlike the autoregressive model which shows a direct lag dependency. The autocorrelation function captures the correlation change pattern caused by this cumulative effect, exhibiting a clear tailing characteristic after the moving average order, gradually decaying to zero.

[0108] As can be seen from the above, this disclosure utilizes the autocorrelation function to analyze the time-series characteristics of VOCs data. By identifying the lag order of the autocorrelation coefficient decaying to or near zero, it determines the moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model, as well as the seasonal moving average order. This ensures that the model can accurately capture the random fluctuation component in the data, improving the accuracy of VOCs monitoring and prediction. This disclosure, for time-series data with seasonal characteristics, introduces a seasonal autocorrelation function for analysis. This can measure the correlation between observations under different seasonal cycles, thereby accurately determining the seasonal moving average order of the seasonal autoregressive integral moving average model, enhancing the predictive ability of this disclosure for seasonal changes.

[0109] Corresponding to the VOCs monitoring method in the above embodiment, Figure 2 This is a structural block diagram of a VOCs monitoring system according to an embodiment of this disclosure. For ease of explanation, only the parts relevant to the embodiment of this disclosure are shown. References Figure 2 The VOCs monitoring system 20 includes: a data feature determination module 21, a prediction module 22, and an early warning module 23.

[0110] The data feature determination module 21 is used to determine the data feature type of the historical first VOCs data, which is the data obtained by the historical target monitoring point monitoring the target area; the data feature type includes seasonal type and non-seasonal type.

[0111] Prediction module 22 is used to determine the prediction model based on the data feature type of the historical first VOCs data, and to predict the first VOCs data based on the prediction model to obtain the target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point;

[0112] The early warning module 23 is used to determine the VOCs early warning level of the target area based on the target prediction results.

[0113] In one embodiment of this disclosure, the data feature determination module 21 is specifically used to determine a historical time series graph based on historical first VOCs data;

[0114] The historical time series graph is input into the first neural network model to obtain the data feature types of the first historical VOCs data; the first neural network model is obtained by training with a certain amount of VOCs data and its corresponding data feature types.

[0115] In one embodiment of this disclosure, the prediction module 22 is specifically used to determine the autoregressive integral moving average model as the prediction model in response to the fact that the data type of the first historical VOCs data is non-seasonal.

[0116] Since the data characteristics of the first historical VOCs data are seasonal, the seasonal autoregressive integral moving average model is selected as the prediction model.

[0117] In one embodiment of this disclosure, a VOCs monitoring system 20 further includes: an autoregression order determination module, used to determine the partial autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the partial autocorrelation function;

[0118] The autoregressive order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the partial autocorrelation function sequence.

[0119] In response to the prediction model being a seasonal autoregressive integral moving average model, seasonal difference is performed on the first VOCs data to obtain seasonally differenced VOCs data, and seasonal difference is performed on the historical first VOCs data to obtain historical seasonally differenced VOCs data.

[0120] The partial autocorrelation function sequence of the differential VOCs data and the historical differential VOCs data is determined based on the partial autocorrelation function.

[0121] The seasonal autoregressive order of the seasonal autoregressive integral moving average model is determined based on the differential partial autocorrelation function sequence.

[0122] In one embodiment of this disclosure, a VOCs monitoring system 20 further includes: a differential order determination module, used to obtain a time series based on first VOCs data and historical first VOCs data;

[0123] An augmented Dickey-Fuller test is performed on the time series. If the test result is non-stationary, the time series is differencing until the test result is stationary. The difference order corresponding to the stationary test result is used as the difference order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model.

[0124] Since the prediction model is a seasonal autoregressive integral moving average model, the time series is subjected to the HEGY test. If the test result is seasonally non-stationary, the time series is subjected to seasonal differencing until the test result is seasonally stationary. The seasonal differencing order corresponding to the test result being seasonally stationary is taken as the differencing order of the seasonal autoregressive integral moving average model.

[0125] In one embodiment of this disclosure, a VOCs monitoring system 20 further includes: a moving average order determination module, used to determine the autocorrelation function sequence of first VOCs data and historical first VOCs data based on the autocorrelation function;

[0126] The moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the autocorrelation function sequence.

[0127] Since the prediction model is a seasonal autoregressive integral moving average model, the seasonal autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the seasonal autocorrelation function.

[0128] The seasonal moving average order of the seasonal autoregressive integral moving average model is determined based on the seasonal autocorrelation function sequence.

[0129] In one embodiment of this disclosure, the early warning module 23 is specifically used to determine the VOCs concentration index, VOCs concentration change trend index, and duration index in the target area based on the target prediction results.

[0130] The early warning index is obtained by weighting the VOCs concentration index, the VOCs concentration change trend index, and the duration index.

[0131] The VOCs warning level for the target area is determined based on the warning indicators.

[0132] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present disclosure. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above system embodiments, for example... Figure 2 The functions of modules 21 to 23 are shown.

[0133] It should be understood that, in the embodiments of this disclosure, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0134] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0135] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0136] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this disclosure can execute the implementation methods described in the first and second embodiments of the VOCs monitoring method provided in the embodiments of this disclosure, or they can execute the implementation methods of the electronic devices described in the embodiments of this disclosure, which will not be repeated here.

[0137] In another embodiment of this disclosure, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0138] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0139] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0140] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0142] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this disclosure, depending on actual needs.

[0143] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this disclosure, and these modifications or substitutions should all be covered within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for monitoring VOCs, characterized in that, include: The data feature type of the first historical VOCs data is determined. The first historical VOCs data is the data obtained by monitoring the target area from historical target monitoring points. The data feature type includes seasonal and non-seasonal types. The prediction model is determined based on the data feature type of the first historical VOCs data. Specifically, in response to the data type of the first historical VOCs data being non-seasonal, the autoregressive integral moving average model is determined as the prediction model; in response to the data feature type of the first historical VOCs data being seasonal, the seasonal autoregressive integral moving average model is determined as the prediction model. The first VOCs data is predicted based on the prediction model to obtain the target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point; Based on the target prediction results, VOCs concentration indicators, VOCs concentration change trend indicators, and duration indicators are determined in the target area; the VOCs concentration indicators, VOCs concentration change trend indicators, and duration indicators are weighted and calculated to obtain early warning indicators; The method of obtaining the early warning indicator by weighting the VOCs concentration index, the VOCs concentration change trend index, and the duration index further includes: In response to the population density of the target area being greater than the first population density, the weight of VOCs concentration is increased by the first density step, the weight of VOCs change is decreased by the second density step, and the weight of duration is decreased by the third density step. In response to the target area being an industrial concentration area and / or the ambient temperature of the target area being greater than a first temperature, the weight of VOCs change is increased with a first industrial step, the weight of VOCs concentration is decreased with a second industrial step, and the weight of duration is decreased with a third industrial step. In response to the target area being an ecological protection zone, the duration weight is increased with the first ecological step, the VOCs concentration weight is decreased with the second density step, and the VOCs change weight is decreased with the third density step. Among them, the VOCs concentration weight is the weight corresponding to the VOCs concentration index, the VOCs change weight is the weight corresponding to the VOCs concentration change trend index, and the duration weight is the weight corresponding to the duration index. The VOCs warning level for the target area is determined based on the aforementioned warning indicators.

2. The VOCs monitoring method as described in claim 1, characterized in that, The data feature types for determining the first historical VOCs data include: A historical time series graph was determined based on the aforementioned first historical VOCs data; The historical time series graph is input into the first neural network model to obtain the data feature types of the historical first VOCs data; the first neural network model is obtained by training with a certain amount of VOCs data and its corresponding data feature types.

3. The VOCs monitoring method as described in claim 1, characterized in that, Also includes: The partial autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the partial autocorrelation function. The autoregressive order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the partial autocorrelation function sequence. In response to the prediction model being a seasonal autoregressive integral moving average model, seasonal difference is performed on the first VOCs data to obtain seasonally differenced VOCs data, and seasonal difference is performed on the historical first VOCs data to obtain historical seasonally differenced VOCs data. The differential partial autocorrelation function sequence of the differential VOCs data and the historical differential VOCs data is determined based on the partial autocorrelation function; The seasonal autoregressive order of the seasonal autoregressive integral moving average model is determined based on the differential partial autocorrelation function sequence.

4. The VOCs monitoring method as described in claim 1, characterized in that, Also includes: A time series is obtained based on the first VOCs data and the historical first VOCs data; An augmented Dickey-Fuller test is performed on the time series. If the test result is non-stationary, the time series is differencing until the test result is stationary. The difference order corresponding to the stationary test result is used as the difference order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model. In response to the prediction model being a seasonal autoregressive integral moving average model, a HEGY test is performed on the time series. If the test result is seasonally non-stationary, the time series is seasonally differencing until the test result is seasonally stationary. The seasonal differencing order corresponding to the seasonally stationary test result is then used as the differencing order of the seasonal autoregressive integral moving average model.

5. A VOCs monitoring method as described in claim 1, characterized in that, Also includes: The autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the autocorrelation function. The moving average order of the autoregressive integral moving average model and the seasonal autoregressive integral moving average model is determined based on the autocorrelation function sequence. In response to the prediction model being a seasonal autoregressive integral moving average model, the seasonal autocorrelation function sequence of the first VOCs data and the historical first VOCs data is determined based on the seasonal autocorrelation function. The seasonal moving average order of the seasonal autocorrelation integral moving average model is determined based on the seasonal autocorrelation function sequence.

6. A VOCs monitoring system, characterized in that, include: The data feature determination module is used to determine the data feature type of the historical first VOCs data, which is the data obtained by historical target monitoring points monitoring the target area; the data feature type includes seasonal type and non-seasonal type. The prediction module is used to determine the prediction model based on the data feature type of the first historical VOCs data. Specifically, in response to the data type of the first historical VOCs data being non-seasonal, the autoregressive integral moving average model is determined as the prediction model; in response to the data feature type of the first historical VOCs data being seasonal, the seasonal autoregressive integral moving average model is determined as the prediction model. The first VOCs data is predicted based on the prediction model to obtain the target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point; The early warning module is used to determine the VOCs concentration index, VOCs concentration change trend index, and duration index in the target area based on the target prediction results; and to obtain the early warning index by weighting the VOCs concentration index, VOCs concentration change trend index, and duration index. In response to the population density of the target area being greater than the first population density, the weight of VOCs concentration is increased by the first density step, the weight of VOCs change is decreased by the second density step, and the weight of duration is decreased by the third density step. In response to the target area being an industrial concentration area and / or the ambient temperature of the target area being greater than a first temperature, the weight of VOCs change is increased with a first industrial step, the weight of VOCs concentration is decreased with a second industrial step, and the weight of duration is decreased with a third industrial step. In response to the target area being an ecological protection zone, the duration weight is increased with the first ecological step, the VOCs concentration weight is decreased with the second density step, and the VOCs change weight is decreased with the third density step. Among them, the VOCs concentration weight is the weight corresponding to the VOCs concentration index, the VOCs change weight is the weight corresponding to the VOCs concentration change trend index, and the duration weight is the weight corresponding to the duration index. The VOCs warning level for the target area is determined based on the aforementioned warning indicators.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images