VOCs monitoring method and system

Abstract

The invention provides a VOCs monitoring method and system, and belongs to the technical field of environment monitoring, the method comprises the following steps: determining a data feature type of historical first VOCs data, the historical first VOCs data being data 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, and predicting the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is data obtained by monitoring VOCs in the target area based on the target monitoring point; and determining the VOCs early warning level of the target area based on the target prediction result. According to the VOCs monitoring method and system provided by the invention, the accuracy and reliability of VOCs monitoring can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of environmental monitoring, and more specifically, relates to a method and system for monitoring VOCs. Background Art

[0002] With the acceleration of industrialization and urbanization, the problem of emissions of volatile organic compounds (VOCs) has become increasingly severe. VOCs are a class of organic compounds that are volatile at normal temperatures, with a wide range of sources, covering many fields such as chemical production, painting operations, the printing industry, and vehicle exhaust emissions.

[0003] VOCs not only have a significant impact on the quality of the atmospheric environment but also pose a serious threat to human health. In the atmospheric environment, VOCs are important precursors for the formation of secondary pollutants such as ozone and fine particulate matter (PM2.5). When they undergo photochemical reactions with nitrogen oxides under sunlight irradiation, it will cause the concentration of ground-level ozone to increase, forming photochemical smog. This not only reduces atmospheric visibility and affects traffic travel but also damages the growth of plants and the balance of the ecosystem. At the same time, long-term exposure to an environment containing high concentrations of VOCs can cause symptoms such as respiratory irritation, dizziness, nausea, and fatigue in the human body. Some VOCs with toxicity and carcinogenicity, such as benzene and formaldehyde, will further increase the risk of cancer and other serious diseases.

[0004] Traditional environmental monitoring means often can only obtain limited real-time data, unable to comprehensively and accurately predict the changing trend of future VOCs concentrations, and it is 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 the present disclosure is to provide a method and system for monitoring VOCs to improve the accuracy and reliability of VOCs monitoring.

[0007] In the first aspect of the embodiments of the present disclosure, a method for monitoring VOCs is provided, including: Determine the data feature type of historical first VOCs data, where the historical first VOCs data is the data obtained by monitoring a target area at a historical target monitoring point; the data feature type includes seasonal type and non-seasonal type; Determine a prediction model based on the data feature type of the historical first VOCs data, and predict the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point; Determine the VOCs early warning level of the target area based on the target prediction result.

[0008] In a second aspect of the embodiments of the present disclosure, a VOCs monitoring system is provided, including: A data feature determination module, configured to determine the data feature type of historical first VOCs data, where the historical first VOCs data is data obtained by monitoring a target area at a historical target monitoring point; the data feature type includes a seasonal type and a non-seasonal type; A prediction module, configured to determine a prediction model based on the data feature type of the historical first VOCs data, and predict the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is data obtained by monitoring VOCs in the target area based on the target monitoring point; An early warning module, configured to determine the VOCs early warning level of the target area based on the target prediction result.

[0009] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned VOCs monitoring method are implemented.

[0010] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the above-mentioned VOCs monitoring method are implemented.

[0011] The beneficial effects of a VOCs monitoring method and system provided by the embodiments of the present disclosure are as follows: By performing real-time monitoring on the target area based on the target monitoring point and obtaining the first VOCs data, the present disclosure can quickly capture the dynamic changes in VOCs emissions, thereby improving the timeliness of monitoring. By using the data features of the historical first VOCs data to construct a prediction model, the present disclosure can make full use of the laws and trends in the historical data and improve the prediction accuracy of future VOCs emission situations. By predicting the first VOCs data through the prediction model to obtain the target prediction result, the present disclosure realizes the analysis and prediction of VOCs emission situations and improves the accuracy and reliability of VOCs monitoring. Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0013] Figure 1 A flowchart of a VOCs monitoring method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a VOCs monitoring system provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0014] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0015] To make the purpose, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments with reference to the accompanying drawings.

[0016] Please refer to Figure 1 , Figure 1 A flowchart of a VOCs monitoring method provided by an embodiment of the present disclosure, the method includes: S101: Determine the data feature type of historical first VOCs data, where the historical first VOCs data is data obtained by a historical target monitoring point for monitoring a target area; the data feature type includes seasonal type and non-seasonal type.

[0017] In this embodiment, VOCs refers to volatile organic compounds, and the historical first VOCs data refers to the VOCs data obtained when the historical target monitoring point monitored the target area in the past. The data type of the historical first VOCs data includes VOCs concentration values and sampling times.

[0018] The target monitoring point is a specific location point set to monitor a specific area, the target area. Relevant devices for monitoring, such as sensors, monitors, etc., are installed at the target monitoring point.

[0019] The target area is a geographical area that needs to be monitored for VOCs, which can be an industrial park, a certain area of a city, etc.

[0020] The data feature type refers to whether it is a seasonal type, that is, whether the data features meet the seasonal characteristics. This is considered because the VOCs data in some regions may show seasonal variations. For example, in agricultural planting areas, agricultural production activities have obvious seasonality. During the growing season of crops, such as the spring sowing and summer growth stages, on the one hand, plants will release a large amount of VOCs, and on the other hand, pesticides, fertilizers, etc. used in agricultural production will also volatilize to produce VOCs. After the harvest season, the relevant emission sources decrease and the VOCs concentration decreases.

[0021] However, the VOCs data in some regions do not show obvious seasonal variations. For example, in tropical rainforest areas, it is hot and rainy throughout the year, the climate conditions are relatively stable, there are no obvious seasonal differences in the growth and metabolic activities of plants, and the biogenic emissions are relatively stable.

[0022] Therefore, in this embodiment, by determining the data feature type of VOCs, a more accurate prediction model can be selected in subsequent processing. Specifically, the data feature type of the historical first VOCs data can be determined in the following way. Determining the data feature type of the historical first VOCs data includes: Determine the historical time series graph based on the historical first VOCs data; Input the historical time series graph into the first neural network model to obtain the data feature type of the historical first VOCs data; the first neural network model is trained with a certain number of VOCs data and their corresponding data feature type data.

[0023] In this embodiment, the historical time series graph refers to a graph plotted with time as the horizontal axis and the value (concentration) of the historical first VOCs data as the vertical axis, which can intuitively show the change of VOCs data over time. If the data has significant seasonality, it usually shows obvious periodic fluctuations.

[0024] The obtained historical time series graph can be input into the first neural network model to obtain the data feature type of the historical first VOCs data. The data feature type can include seasonal type and non-seasonal type. It should be noted that the first neural network is trained with a certain number of VOCs data and their corresponding data feature type data, and also contains the corresponding seasonal cycle value. In this process, it is not limited to the first VOCs data. Even if the VOCs data is from other monitoring points or obtained by other means, it can be used as the training data. A certain number refers to the numerical value that can satisfy the training and output of the neural network, which can be set according to experience or the data for solving similar problems.

[0025] S102: Determine a prediction model based on the data feature type of historical first VOCs data, and predict the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is data obtained by monitoring VOCs in a target area based on a target monitoring point.

[0026] In this embodiment, the first VOCs data refers to relevant data of VOCs obtained by monitoring a target area through a target monitoring point in the current stage, such as concentration values, sampling times, and other information.

[0027] In this embodiment, determining a prediction model based on the data feature type of historical first VOCs data includes: In response to the data type of historical first VOCs data being a non-seasonal type, determine the autoregressive integrated moving average model as the prediction model; In response to the data feature type of historical first VOCs data being a seasonal type, determine the seasonal autoregressive integrated moving average model as the prediction model.

[0028] In this embodiment, as can be seen from S101, the data feature type may include a seasonal type and a non-seasonal type. For different data feature types, different prediction models should be used to predict the VOCs data of the target area. The prediction models include the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model.

[0029] Specifically, the autoregressive integrated 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 a time series, that is , where is the VOCs concentration at the current time , are the VOCs concentrations at the past time points, are the autoregressive coefficients, is the order of autoregression, is the white noise error sequence.

[0030] The integration 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. Perform a differencing operation on the non-stationary VOCs time series to make it a stationary series. If the original series becomes a stationary series after orders of differencing, that is , where is the lag operator, and is the differencing operator.

[0031] The moving average part describes the linear relationship between the current error and the past errors of the time series, and the expression is , where are the moving average coefficients, is the order of the moving average.

[0032] For the combined model, the autoregressive integrated moving average model can be expressed as . Combining the above three parts, the complete model expression is , where , , represents the polynomial of the seasonal autoregressive part, is the polynomial of the seasonal moving average part.

[0033] The seasonal autoregressive integrated moving average model adds seasonality-related parameters on the basis of the autoregressive integrated moving average model, denoted as , where is the seasonal autoregressive order, representing the linear relationship between the current seasonal value and the past seasonal values, is the seasonal differencing order, used to make the seasonal non-stationary time series stationary, and perform times of seasonal differencing on the time series. is the seasonal moving average order, describing the relationship between the error of the current season and the past seasonal errors. is the seasonal cycle length.

[0034] In this embodiment, the target prediction result contains information such as the VOCs concentration value and the concentration change trend at a certain future moment.

[0035] On the basis of having determined the prediction model, the currently newly obtained first VOCs data, that is, the data on VOCs newly monitored by the target monitoring point for the target area, is input into this prediction model. The prediction model will analyze and calculate the input first VOCs data according to its own algorithm and parameters, so as to infer the relevant situation of VOCs in the target area in the future for a period of time, and the finally output inferred result is called the target prediction result.

[0036] S103: Determine the VOCs early warning level of the target area based on the target prediction result.

[0037] In this embodiment, the target prediction result contains the VOCs concentration information of the target area in the future for a period of time. To determine the VOCs early warning level of the target area through the target prediction result, the VOCs concentration thresholds corresponding to different levels of early warning should be determined according to the relevant environmental protection standards, policies and regulations of the target area.

[0038] In this embodiment, the early warning level can be determined according to a single evaluation index. For example, when the predicted VOCs concentration exceeds the first threshold but is lower than the second threshold, it is determined as a first-level early warning; when the concentration exceeds the second threshold, it is determined as a second-level early warning, and so on.

[0039] It is also possible to comprehensively consider multiple indicators to determine the early warning level. For example, in an embodiment of the present disclosure, determining the VOCs early warning level of the target area based on the target prediction result includes: Determining the VOCs concentration index, VOCs concentration change trend index, and duration index in the target area based on the target prediction result; Performing weighted calculation on the VOCs concentration index, VOCs concentration change trend index, and duration index to obtain an early warning index; Determining the VOCs early warning level of the target area based on the early warning index.

[0040] In this embodiment, the VOCs concentration index can be directly obtained according to the target prediction result. The VOCs concentration change trend index can calculate the change trend by comparing the VOCs concentrations at different time points in the target prediction result, or use the concentration data at multiple time points in the target prediction result to fit a trend line through a mathematical method (such as the least squares method), and the slope of the trend line can be used as the VOCs concentration change trend index. A positive slope indicates an increasing concentration trend, a negative slope indicates a decreasing concentration trend, and the absolute value of the slope indicates the speed of change. If the target prediction result shows that the VOCs concentration is within a certain specific range or the time span of a certain specific change trend, this time span is the duration index. Or according to relevant standards or experience, set a threshold for the VOCs concentration or change trend. When the predicted VOCs concentration exceeds the threshold or the change trend reaches a certain level, start calculating the duration until it is lower than the threshold.

[0041] The corresponding weights of the VOCs concentration index, VOCs concentration change trend index, and duration index can be set according to expert experience.

[0042] Considering that the weights should be different for different temperatures or regions, for example: in an embodiment of the present disclosure, a VOCs monitoring method further includes: In response to the population density of the target area being greater than the first personnel density, increasing the VOCs concentration weight by the first density step, decreasing the VOCs change weight by the second density step, and decreasing the duration weight by the third density step; In response to the target area being an industrial concentration area and / or the environmental temperature of the target area being greater than the first temperature, increase the VOCs change weight by the first industrial step, decrease the VOCs concentration weight by the second industrial step, and decrease the duration weight by the third industrial step; In response to the target area being an ecological protection area, increase the duration weight by the first ecological step, decrease the VOCs concentration weight by the second density step, and decrease the VOCs change weight by 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.

[0043] In this embodiment, in the densely populated urban center area, the impact of high concentration on residents' health is more direct and significant. Therefore, the weight of the concentration index should be increased to ensure that a high-concentration pollution warning can be issued in a timely manner. The first population density, the first density step, the second density step, and the third density step can be set according to experience, but it should be noted that the first density step is equal to the sum of the second density step and the third density step.

[0044] Secondly, industrial production is the main emission source of VOCs, and key attention should be paid to the emission situation and concentration changes of enterprises. The weights of the VOCs concentration index and the change trend index can be appropriately increased to promptly detect abnormal emission behaviors of enterprises. Whether the target area belongs to an industrial concentration area can be set in advance. The first industrial step is equal to the sum of the second industrial step and the third industrial step, and can be set according to experience.

[0045] Thirdly, the ecosystem is relatively sensitive to long-term exposure to VOCs, and the weight of the duration index should be increased to evaluate the impact on the ecological environment. Whether the target area belongs to an ecological protection area should be preset, and the first ecological step is equal to the sum of the second ecological step and the third ecological step, and can be set according to experience.

[0046] As can be seen from the above, the present disclosure can quickly capture the dynamic changes in VOCs emissions by performing real-time monitoring on the target area based on the target monitoring point and obtaining the first VOCs data, thereby improving the timeliness of monitoring. By using the data characteristics of historical first VOCs data to construct a prediction model, the present disclosure can make full use of the laws and trends in historical data to improve the prediction accuracy of future VOCs emission situations. By predicting the first VOCs data through the prediction model to obtain the target prediction result, the present disclosure realizes the analysis and prediction of VOCs emission situations, and improves the accuracy and reliability of VOCs monitoring.

[0047] In an embodiment of the present disclosure, a VOCs monitoring method further includes: Determine the partial autocorrelation function sequences of the first VOCs data and the historical first VOCs data based on the partial autocorrelation function; Determine the autoregressive orders of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the partial autocorrelation function sequences; In response to the prediction model being a seasonal autoregressive integrated moving average model, perform seasonal differencing on the first VOCs data to obtain seasonally differenced VOCs data, and perform seasonal differencing on the historical first VOCs data to obtain historical seasonally differenced VOCs data; Determine the differential partial autocorrelation function sequences of the differenced VOCs data and the historical differenced VOCs data based on the partial autocorrelation function; Determine the seasonal autoregressive order of the seasonal autoregressive integrated moving average model based on the differential partial autocorrelation function sequences.

[0048] In this embodiment, the partial autocorrelation function sequences are numerical sequences obtained by calculating the partial autocorrelation function for the first VOCs data and the historical first VOCs data.

[0049] The partial autocorrelation function is used to measure the correlation between two observations in time series data after controlling the influence of intermediate observations. For the first VOCs data and the historical first VOCs data, by calculating their partial autocorrelation coefficients at different time intervals, the partial autocorrelation function sequences can be obtained.

[0050] 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 3 time units (time steps) ago, you can calculate it through the partial autocorrelation function, and a series of obtained correlation coefficients constitute the partial autocorrelation function sequences.

[0051] The autoregressive order refers to the linear relationship between the current value and past values in the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model. By observing the partial autocorrelation function sequences, when the partial autocorrelation coefficients quickly approach zero after a certain lag order, then this lag order can be used as the autoregressive order, that is .

[0052] For example, if the partial autocorrelation function sequences basically fluctuate around zero after a lag of 3 orders, then the autoregressive order can be considered to be 3, meaning that the current VOCs data is mainly directly related to the VOCs data at the past 3 time points, and thus the autoregressive part in the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model can be constructed accordingly.

[0053] In this embodiment, the change rate of the partial autocorrelation function sequence can be calculated as the basis for judging whether it quickly approaches zero. For example, if the change rates of the partial autocorrelation functions of the first consecutive number of points are all less than the first change rate, 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 change rate can be preset according to experiments or experience.

[0054] Through the above calculations, the autoregressive orders of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model can be obtained. Moreover, the seasonal autoregressive integrated moving average model also has a seasonal autoregressive order. Therefore, it is also necessary to determine the seasonal autoregressive order.

[0055] Considering the use of the seasonal autoregressive integrated moving average model, it proves that its data has seasonal characteristics. In order to eliminate this seasonality, make the data more stable, and facilitate modeling analysis, seasonal differencing operations need to be performed. The obtained difference is the data after seasonal differencing. Such operations are performed on the first VOCs data and the historical first VOCs data respectively to obtain the seasonally differenced VOCs data and the historical seasonally differenced VOCs data. The data processed in this way can better reflect the change trend after removing seasonality, which is beneficial to subsequent parameter estimation and prediction of the model.

[0056] Similar to determining the partial autocorrelation function sequence before, for the first VOCs data after seasonal differencing, which is the seasonally differenced VOCs data, and the historical first VOCs data after seasonal differencing, which is the historical seasonally differenced VOCs data, calculate their partial autocorrelation functions, and the obtained is the differenced partial autocorrelation function sequence.

[0057] In the seasonal autoregressive integrated moving average model, the seasonal autoregressive order determines the degree and manner of the influence of seasonal factors on the current value. By observing the differenced partial autocorrelation function sequence, in the same way as determining the autoregressive order, find the lag order at which the partial autocorrelation coefficient quickly approaches zero, and take it as the seasonal autoregressive order, that is .

[0058] It can be concluded from the above that the present disclosure determines the autoregressive orders of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model by introducing the partial autocorrelation function, which can more accurately capture the time dependence in the VOCs data, thereby improving the fitting degree and prediction accuracy of the model. Through seasonal differencing processing, the influence of seasonal fluctuations on the model is eliminated, enabling this embodiment to more accurately reflect the long-term trend and seasonal changes of the VOCs concentration, and improving the accuracy and reliability of VOCs monitoring.

[0059] In an embodiment of the present disclosure, a VOCs monitoring method further includes: A time series is obtained based on the first VOCs data and the historical first VOCs data; Perform an augmented Dickey-Fuller test on the time series. If the test result is not stable, perform difference processing on the time series until the test result is stable. The difference order corresponding to the stable test result is used as the difference order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model. In response to the prediction model being the seasonal autoregressive integrated moving average model, a HEGY test is performed on the time series. If the test result is seasonal non-stationary, seasonal difference processing is performed on the time series until the test result is seasonally stable. The seasonal difference order corresponding to the test result being seasonally stable is used as the difference order of the seasonal autoregressive integrated moving average model.

[0060] In this embodiment, the first VOCs data and the historical first VOCs data can be arranged in chronological order to form a time series. This time series reflects the change of VOCs data over time and is the basis for subsequent analysis and modeling. For example, the VOCs concentration data of each hour of each day is recorded at time intervals of hours. These data are arranged in chronological order to form a time series.

[0061] The Augmented Dickey-Fuller (ADF) test is a statistical method used to test whether a time series is stationary. If the ADF test result shows that the time series is not stationary, it needs to be differentiated. The purpose of differentiation is to eliminate non-stationary factors such as trend or seasonality in the time series by differentiating the data at adjacent time points, making it stationary. The first-order difference is to calculate the difference between the data at two adjacent time points, that is, If the first-order difference is still not stable, the second-order difference can be performed, that is, the first-order difference sequence is differentiated again, and so on. The difference processing is continuously performed until the ADF test result shows that the time series becomes stable. At this time, the difference order performed is the difference order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model.

[0062] When the forecasting model is a seasonal autoregressive integrated moving average model, in addition to considering the overall stationarity of the time series, its seasonal stationarity also needs to be tested. The HEGY test is a method specifically used to test whether a time series has a seasonal unit root. If the HEGY test result shows that the time series is seasonally non-stationary, seasonal differencing is required. Seasonal differencing is a differential 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 is to calculate By continuously performing seasonal differencing until the HEGY test result shows that the time series becomes seasonally stationary, the order of seasonal differencing at this time is the order of seasonal differencing of the seasonal autoregressive integrated moving average model, that is .

[0063] It can be concluded from the above that the present disclosure effectively identifies the non-stationarity of the time series through the augmented Dickey-Fuller test, and then gradually eliminates the trend term and / or seasonal factors through differencing processing to ensure that the time series reaches a stationary state, which helps to improve the prediction accuracy and stability of the present disclosure. The present disclosure introduces the HEGY test, which is specifically used to detect the seasonal non-stationarity of the time series, can eliminate the seasonal fluctuations in the time series, and improve the seasonal prediction ability of the present disclosure.

[0064] In an embodiment of the present disclosure, a VOCs monitoring method further includes: Determining an autocorrelation function sequence of the first VOCs data and historical first VOCs data based on the autocorrelation function; Determining the moving average order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the autocorrelation function sequence; In response to the prediction model being a seasonal autoregressive integrated moving average model, determining a seasonal autocorrelation function sequence of the first VOCs data and historical first VOCs data based on the seasonal autocorrelation function; Determining the seasonal moving average order of the seasonal autoregressive integrated moving average model based on the seasonal autocorrelation function sequence.

[0065] In this embodiment, the autocorrelation function is used to measure the correlation between the observed values at different time points in a time series. For the first VOCs data and historical first VOCs data, by calculating their autocorrelation coefficients at different lag orders, the autocorrelation function sequence can be obtained.

[0066] For example, assume there is a set of VOC data sequences , the autocorrelation coefficient .

[0067] . Where is the number of samples of the data, is the mean of the data. By calculating at different values, the autocorrelation function sequence is obtained.

[0068] For the autocorrelation function sequence, when the autocorrelation coefficient rapidly decays to zero or fluctuates around zero after a certain order , this order can be used as the moving average order.

[0069] In this embodiment, the obtained autocorrelation sequence and autocorrelation coefficient can be combined to form a first sequence diagram, and the first sequence diagram is input into a second neural network to obtain the moving average orders of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model.

[0070] It should be noted that the second neural network is trained with a large number of datasets composed of autocorrelation sequences, autocorrelation coefficients, and their corresponding moving average orders.

[0071] Through the above calculations, the moving average orders of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model can be obtained, and the seasonal autoregressive integrated moving average model also contains the seasonal moving average order. 。

[0072] Therefore, the seasonal autocorrelation function can be used to measure the correlation between observations under different seasonal cycles. The seasonal autocorrelation function is a function for analyzing time series with seasonal characteristics based on the autocorrelation function. For example, , where is the seasonal period and can be obtained through the first neural network model.

[0073] In this disclosure, the partial autocorrelation function is used to calculate the autoregressive order, while the autocorrelation function is used to calculate the moving average order. This is because the partial autocorrelation function measures the direct correlation between observations separated by a specific lag order in a time series after controlling the influence of intermediate observations. For an autoregressive process, the partial autocorrelation function can directly reflect the true dependence relationship between the current value and past values without being interfered by other intermediate lag terms. The autoregressive model describes the linear relationship between the current observation and past observations over several periods, and its core is to determine which specific past lag values the current value directly depends on. The partial autocorrelation function can clearly show the order of this direct dependence relationship, that is, the lag order for which the partial autocorrelation function is significantly non-zero often corresponds to the order of the autoregressive model.

[0074] The autocorrelation function measures the overall correlation between observations at different lag orders in a time series, which includes the combined influence of all possible dependence relationships and random disturbances. The moving average model mainly describes that the current observation is a linear combination of past random error terms over several periods, and its influence on the observation is reflected in an accumulative manner, unlike the autoregressive model which has a direct lag dependence relationship. The autocorrelation function can capture the correlation change pattern caused by this accumulative effect, and the autocorrelation function will show an obvious trailing characteristic after the moving average order, that is, it gradually decays to zero.

[0075] As can be seen from the above, the present disclosure analyzes the time series characteristics of VOCs data using the autocorrelation function. By identifying the lag order at which the autocorrelation coefficient decays to zero or fluctuates near zero, the moving average order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model and the seasonal moving average order are determined, ensuring that the model can accurately capture the random fluctuation components in the data and improving the accuracy of VOCs monitoring and prediction. For the time series data with seasonal characteristics, the present disclosure introduces the seasonal autocorrelation function for analysis, which can measure the correlation between observed values under different seasonal cycles, thereby accurately determining the seasonal moving average order of the seasonal autoregressive integrated moving average model and enhancing the prediction ability of the present disclosure for seasonal changes.

[0076] A VOCs monitoring method corresponding to the above embodiment Figure 2 is a structural block diagram of a VOCs monitoring system provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 The VOCs monitoring system 20 includes: a data feature determination module 21, a prediction module 22, and an early warning module 23.

[0077] Among them, the data feature determination module 21 is used to determine the data feature type of historical first VOCs data, and the historical first VOCs data is the data obtained by monitoring a target area by a historical target monitoring point; the data feature type includes a seasonal type and a non-seasonal type; The prediction module 22 is used to determine a prediction model based on the data feature type of the historical first VOCs data, and predict the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is the data obtained by monitoring the VOCs in the target area based on the target monitoring point; The early warning module 23 is used to determine the VOCs early warning level of the target area based on the target prediction result.

[0078] In an embodiment of the present disclosure, the data feature determination module 21 is specifically used to determine a historical time series graph based on the historical first VOCs data; Input the historical time series graph into the first neural network model to obtain the data feature type of the historical first VOCs data; the first neural network model is trained with a certain number of VOCs data and their corresponding data feature type data.

[0079] In an embodiment of the present disclosure, the prediction module 22 is specifically used to, in response to the data type of the historical first VOCs data being a non-seasonal type, determine the autoregressive integrated moving average model as the prediction model; In response to the data feature type of the historical first VOCs data being a seasonal type, the seasonal autoregressive integrated moving average model is determined as the prediction model.

[0080] In an embodiment of the present disclosure, a VOCs monitoring system 20 further includes: an autoregressive order determination module, configured to determine the partial autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the partial autocorrelation function; Determine the autoregressive order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the partial autocorrelation function sequence; In response to the prediction model being the seasonal autoregressive integrated moving average model, perform seasonal differencing on the first VOCs data to obtain seasonally differenced VOCs data, and perform seasonal differencing on the historical first VOCs data to obtain historical seasonally differenced VOCs data; Determine the differenced partial autocorrelation function sequence of the differenced VOCs data and the historical differenced VOCs data based on the partial autocorrelation function; Determine the seasonal autoregressive order of the seasonal autoregressive integrated moving average model based on the differenced partial autocorrelation function sequence.

[0081] In an embodiment of the present disclosure, a VOCs monitoring system 20 further includes: a differencing order determination module, configured to obtain a time series based on the first VOCs data and the historical first VOCs data; Perform an augmented Dickey-Fuller test on the time series. If the test result is non-stationary, perform differencing processing on the time series until the test result is stationary, and use the differencing order corresponding to the stationary test result as the differencing order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model; In response to the prediction model being the seasonal autoregressive integrated moving average model, perform a HEGY test on the time series. If the test result is seasonally non-stationary, perform seasonal differencing processing on the time series until the test result is seasonally stationary, and use the seasonal differencing order corresponding to the seasonally stationary test result as the differencing order of the seasonal autoregressive integrated moving average model.

[0082] In an embodiment of the present disclosure, a VOCs monitoring system 20 further includes: a moving average order determination module, configured to determine the autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the autocorrelation function; Determine the moving average order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the autocorrelation function sequence; In response to the prediction model being a seasonal autoregressive integrated moving average model, determine the seasonal autocorrelation function sequences of the first VOCs data and the historical first VOCs data based on the seasonal autocorrelation function; Determine the seasonal moving average order of the seasonal autoregressive integrated moving average model based on the seasonal autocorrelation function sequences.

[0083] In an embodiment of the present disclosure, the warning module 23 is specifically configured to determine the VOCs concentration index, the VOCs concentration change trend index, and the duration index in the target area based on the target prediction result; Perform weighted calculation on the VOCs concentration index, the VOCs concentration change trend index, and the duration index to obtain a warning index; Determine the VOCs warning level of the target area based on the warning index.

[0084] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. As Figure 3 shown, 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 above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned system embodiments, such as Figure 2 the functions of the modules 21 to 23 shown.

[0085] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (Central Processing Unit, CPU), and this processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0086] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0087] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may further include a non-volatile random access memory. For example, the memory 304 may further store information about the device type.

[0088] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of a VOCs monitoring method provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0089] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It may also be completed by instructing relevant hardware through the computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0090] A computer-readable storage medium may be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store a computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store the data that has been output or is to be output.

[0091] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0092] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0093] In 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 only illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, and can also be an electrical, mechanical, or other form of connection.

[0094] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0095] In addition, in each embodiment of the present disclosure, each functional unit may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0096] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method for monitoring VOCs, characterized in that, Including: Determine the data characteristic type of the historical first VOCs data, where the historical first VOCs data is the data obtained by monitoring a target area at a historical target monitoring point; the data characteristic type includes a seasonal type and a non-seasonal type; Determine a prediction model based on the data characteristic type of the historical first VOCs data, and predict the first VOCs data based on the prediction model to obtain a target prediction result; the first VOCs data is the data obtained by monitoring VOCs in the target area based on the target monitoring point; Determine the VOCs warning level of the target area based on the target prediction result.

2. The VOCs monitoring method according to claim 1, wherein The determination of the data characteristic type of the historical first VOCs data includes: Determine a historical time series graph based on the historical first VOCs data; Input the historical time series graph into a first neural network model to obtain the data characteristic type of the historical first VOCs data; the first neural network model is trained with a certain number of VOCs data and their corresponding data characteristic type data.

3. The VOCs monitoring method according to claim 1, wherein, The determination of the prediction model based on the data characteristic type of the historical first VOCs data includes: In response to the data type of the historical first VOCs data being a non-seasonal type, determine an autoregressive integrated moving average model as the prediction model; In response to the data characteristic type of the historical first VOCs data being a seasonal type, determine a seasonal autoregressive integrated moving average model as the prediction model.

4. The VOCs monitoring method according to claim 3, wherein Also including: Determine the partial autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the partial autocorrelation function; Determine the autoregressive order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the partial autocorrelation function sequence; In response to the prediction model being a seasonal autoregressive integrated moving average model, perform seasonal differencing on the first VOCs data to obtain seasonally differenced VOCs data, and perform seasonal differencing on the historical first VOCs data to obtain historical seasonally differenced VOCs data; Determine the differential partial autocorrelation function sequence of the differenced VOCs data and the historical differenced VOCs data based on the partial autocorrelation function; Determine the seasonal autoregressive order of the seasonal autoregressive integrated moving average model based on the differential partial autocorrelation function sequence.

5. The VOCs monitoring method according to claim 3, characterized in that, Also including: Obtain a time series based on the first VOCs data and the historical first VOCs data; Perform an augmented Dickey-Fuller test on the time series. If the test result is non-stationary, perform differencing on the time series until the test result is stationary, and use the corresponding differencing order when the test result is stationary as the differencing order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model; In response to the prediction model being a seasonal autoregressive integrated moving average model, perform a HEGY test on the time series. If the test result indicates seasonal non-stationarity, perform seasonal differencing on the time series until the test result shows seasonal stationarity, and use the seasonal differencing order corresponding to the seasonal stationarity as the differencing order of the seasonal autoregressive integrated moving average model.

6. The VOCs monitoring method according to claim 3, characterized in that, It further includes: Determine the autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the autocorrelation function; Determine the moving average order of the autoregressive integrated moving average model and the seasonal autoregressive integrated moving average model based on the autocorrelation function sequence; In response to the prediction model being a seasonal autoregressive integrated moving average model, determine the seasonal autocorrelation function sequence of the first VOCs data and the historical first VOCs data based on the seasonal autocorrelation function; Determine the seasonal moving average order of the seasonal autoregressive integrated moving average model based on the seasonal autocorrelation function sequence.

7. The VOCs monitoring method according to claim 1, wherein, The determining the VOCs warning level of the target area based on the target prediction result includes: Determine the VOCs concentration index, the VOCs concentration change trend index, and the duration index in the target area based on the target prediction result; Perform weighted calculation on the VOCs concentration index, the VOCs concentration change trend index, and the duration index to obtain a warning index; Determine the VOCs warning level of the target area based on the warning index.

8. A VOCs monitoring system, characterized in that, It includes: A data feature determination module for determining the data feature type of the historical first VOCs data, where the historical first VOCs data is the data obtained by monitoring the target area by a historical target monitoring point; the data feature type includes a seasonal type and a non-seasonal type; A prediction module for determining a prediction model based on the data feature type of the historical first VOCs data and predicting the first VOCs data based on the prediction model to obtain a target prediction result; The first VOCs data is the data obtained by monitoring the VOCs in the target area based on a target monitoring point; A warning module for determining the VOCs warning level of the target area based on the target prediction result.

9. 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 according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images