Indoor air monitoring and early warning system and method based on Internet of Things

Abstract

The invention provides an indoor air monitoring and early warning system and method based on the Internet of Things, and relates to the technical field of indoor environment monitoring. The method comprises the following steps: acquiring air quality detection data corresponding to a plurality of data acquisition points, extracting a plurality of instability characteristic parameters of each data acquisition point, and calculating to obtain a local state instability score of each data acquisition point about each monitored gas; fusing the plurality of state instability scores to generate a global state instability score of the target monitoring area; calculating to obtain a dynamic diffusion coefficient of the target monitoring area about gas component diffusion, determining a local abnormal area of the target monitoring area, constructing an abnormal state diffusion model, and determining pollution risk scores of the plurality of core areas according to the abnormal state diffusion model, and generating air quality early warning information about the plurality of core areas according to the pollution risk scores. According to the invention, the dynamic change of the air quality in a complex indoor environment is accurately monitored, and dynamic early warning is carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor environment monitoring, and particularly to an indoor air monitoring and early warning system and method based on the Internet of Things. Background Art

[0002] With the increasing attention to indoor environmental health problems, the indoor air quality monitoring technology based on the Internet of Things has been widely applied. Currently, the monitoring system usually collects the pollutant concentration data in indoor air, such as PM2.5, CO 2 , VOC, etc., and provides air quality assessment and early warning services in combination with data analysis methods.

[0003] Some methods are based on the pollutant concentration data collected at a single point, and generate early warning information by comparing with preset thresholds. This method fails to extract the instability state information of pollutants in the area based on the potential abnormal characteristics of multi-point data. In practical applications, it usually alarms when the pollution has occurred, lacking the capture of early signals of instability. In a complex environment with large fluctuations in air quality, this static analysis method cannot effectively capture the dynamic characteristics of pollutant concentration changes over time and space in the monitoring area, easily missing potential risks. Moreover, the indoor air quality is affected by multiple factors such as pollutant diffusion, ventilation conditions and environmental layout. The point-to-point analysis method fails to consider the global fusion of multi-point data, resulting in difficulty in accurately reflecting the global state of the entire monitoring area. Summary of the Invention

[0004] To solve the above technical problems, the present invention proposes an indoor air monitoring and early warning system and method based on the Internet of Things, which can effectively improve the perception and prediction ability of pollution risks in the monitoring area, provide accurate and personalized air quality early warning services, and is applicable to complex indoor environment monitoring scenarios.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] In the first aspect of the present invention, an indoor air monitoring and early warning method based on the Internet of Things is provided, including:

[0007] Obtaining the air quality detection data corresponding to multiple data collection points respectively, extracting multiple instability characteristic parameters corresponding to each data collection point for multiple monitored gases according to the air quality detection data, including volatility parameters and correlation parameters, and calculating the local state instability score of each data collection point for each monitored gas according to the multiple instability characteristic parameters;

[0008] Obtain the location data of each data collection point, and fuse the instability scores of each data collection point for each monitored gas based on the location data of the data collection point and the air quality detection data to generate the global instability score of the target monitoring area;

[0009] Calculate the dynamic diffusion coefficient of the target monitoring area for gas component diffusion based on the environmental condition data of the target monitoring area, and determine the local abnormal areas of the target monitoring area based on the global instability score of the target monitoring area and the local instability scores of each data collection point for each monitored gas;

[0010] Construct an abnormal state diffusion model of the target monitoring area based on the air quality detection data and the dynamic diffusion coefficient of the data collection points in the local abnormal areas, determine the pollution risk scores of multiple core areas based on the abnormal state diffusion model, and generate air quality warning information for the multiple core areas based on the pollution risk scores.

[0011] Preferably, fusing the instability scores of each data collection point for each monitored gas based on the location data of the data collection point and the air quality detection data to generate the global instability score of the target monitoring area includes:

[0012] Conduct synchronous deviation analysis on each data collection point according to the air quality detection data, calculate the time synchronization parameters between any two data collection points, calculate the synchronous deviation parameters of each data collection point based on the multiple time synchronization parameters, and correct the instability scores of each data collection point for each monitored gas according to the synchronous deviation parameters to obtain the instability correction scores of each data collection point for each monitored gas;

[0013] Conduct collaborative analysis of monitored gases on each data collection point, calculate the dynamic correlation parameters between any two monitored gases under each data collection point, and calculate the collaborative change parameters of each data collection point for each monitored gas based on the multiple dynamic correlation parameters;

[0014] Fuse the multiple instability correction scores based on the location data of each data collection point and the corresponding multiple collaborative change parameters to generate the global instability score of the target monitoring area, where: In the formula, I ns is the global instability score of the target monitoring area, C i,j is the collaborative change parameter of the i-th data collection point for the j-th monitored gas, R i,j is the instability correction score of the i-th data collection point for the j-th monitored gas, is the location weight of the i-th data collection point, m is the total number of data collection points, and n is the number of categories of monitored gases.

[0015] Preferably, an abnormal state diffusion model of the target monitoring area is constructed based on the air quality detection data and the dynamic diffusion coefficient of the data acquisition points in the local abnormal area, including:

[0016] Determine the concentration parameter of each monitoring gas in the local abnormal area according to the air quality detection data of the data acquisition point, correct the concentration parameter based on the local state instability score corresponding to the monitoring gas to obtain the initial intensity parameter of each monitoring gas, generate a two-dimensional convective diffusion equation of the local abnormal area according to the dynamic diffusion coefficient and the initial intensity parameter of the data acquisition point, and construct an abnormal state diffusion model of the target monitoring area according to the two-dimensional convective diffusion equations of each local abnormal area in the target monitoring area;

[0017] For the local abnormal area of the target monitoring area, after detecting that the global state instability score of the target monitoring area is greater than the preset global instability threshold, determine multiple data acquisition points in the target monitoring area whose local state instability scores are greater than the preset global instability threshold and record them as abnormal nodes, and fuse the multiple abnormal nodes according to the position data of the data acquisition points to determine multiple local abnormal areas.

[0018] Preferably, the dynamic diffusion coefficient of the target monitoring area with respect to the diffusion of gas components is calculated according to the environmental condition data of the target monitoring area, including:

[0019] Input the environmental condition data of the target monitoring area into the diffusion coefficient analysis model, and generate the dynamic diffusion coefficient corresponding to the environmental condition data of the target monitoring area through the diffusion coefficient analysis model;

[0020] For the diffusion coefficient analysis model, a training data set is constructed by obtaining multiple groups of historical data of the target monitoring area. Among them, each group of historical data includes a set of associated environmental condition data and gas component detection data. The target diffusion function is generated by performing time discretization and space discretization on the two-dimensional convective diffusion equation. Each group of historical data is used to fit the target diffusion function respectively to generate the target diffusion coefficient corresponding to each group of historical data. The environmental condition data in each group of historical data is associated with the corresponding target diffusion coefficient and a training data set is constructed. The diffusion coefficient analysis model is trained through the training data set to obtain a trained diffusion coefficient analysis model.

[0021] Preferably, for the synchronous deviation analysis and monitoring gas collaborative analysis of the data acquisition points, it further includes:

[0022] According to the air quality detection data corresponding to the data acquisition points, the following formula is used to calculate the local synchronization parameter of any one monitoring gas between two data acquisition points: where q k1，k2(t) represents the time local synchronization parameter of data acquisition point k1 and data acquisition point k2 at time t with respect to a certain monitored gas, A k1 (t), A k2 (t) respectively represent the concentration values of data acquisition point k1 and data acquisition point k2 at time t with respect to a certain monitored gas, d k1,k2 represents the spatial distance between data acquisition point k1 and data acquisition point k2;

[0023] After calculating the local synchronization parameters between any two data acquisition points with respect to each monitored gas based on the air quality detection data using the above formula, the mean value of multiple local synchronization parameters is taken as the time synchronization parameter between the two data acquisition points, and the mean value of multiple time synchronization parameters corresponding to each data acquisition point is calculated to obtain the synchronization deviation parameter of the data acquisition point;

[0024] According to the air quality detection data corresponding to the data acquisition point, the time-series concentration vector of the data acquisition point with respect to each monitored gas is extracted, and the correlation analysis is performed on any two monitored gases according to the time-series concentration vector to calculate the dynamic correlation parameter between the two monitored gases. After calculating the mean value of multiple dynamic correlation parameters corresponding to each monitored gas, the co-variation parameter of each monitored gas is obtained.

[0025] Preferably, the pollution risk scores of multiple core regions are determined according to the abnormal state diffusion model, including:

[0026] Determine the reference coordinate data corresponding to each core region, and analyze the reference coordinate data corresponding to each core region through the abnormal state diffusion model, including inputting the reference coordinate data corresponding to each core region into multiple two-dimensional convection-diffusion equations respectively, processing the two-dimensional convection-diffusion equations by the finite difference method to obtain the concentration prediction data corresponding to the reference coordinate data at the preset time, and determining the pollution risk score of the core region according to the concentration prediction data.

[0027] Preferably, multiple instability characteristic parameters corresponding to each data acquisition point with respect to multiple monitored gases are extracted according to the air quality detection data, including:

[0028] Calculate the mean value and standard deviation of the time-series concentration vector of each monitored gas, take the ratio of the standard deviation to the mean value of the monitored gas as the volatility parameter of the monitored gas, and perform autocorrelation analysis on the time-series concentration vector of each monitored gas to calculate the correlation parameter of the monitored gas.

[0029] The second aspect of the present invention provides an indoor air monitoring and warning system based on the Internet of Things for implementing the above-mentioned indoor air monitoring and warning method based on the Internet of Things, including:

[0030] The local status analysis module is used to obtain the air quality detection data corresponding to multiple data collection points respectively, extract multiple instability characteristic parameters corresponding to various monitored gases at each data collection point according to the air quality detection data, including volatility parameters and correlation parameters, and calculate the local status instability score of each data collection point for each monitored gas according to the multiple instability characteristic parameters;

[0031] The global status instability analysis module is used to obtain the location data of each data collection point, fuse the status instability scores of each data collection point for each monitored gas according to the location data of the data collection point and the air quality detection data, and generate the global status instability score of the target monitoring area;

[0032] The abnormal area analysis module is used to calculate the dynamic diffusion coefficient of the target monitoring area for gas component diffusion according to the environmental condition data of the target monitoring area, and determine the local abnormal areas of the target monitoring area according to the global status instability score of the target monitoring area and the local status instability scores of each data collection point for each monitored gas;

[0033] The air monitoring and warning module is used to construct an abnormal status diffusion model of the target monitoring area according to the air quality detection data and the dynamic diffusion coefficient of the data collection points in the local abnormal areas, determine the pollution risk scores of multiple core areas according to the abnormal status diffusion model, and generate air quality warning information about the multiple core areas according to the pollution risk scores.

[0034] The present invention has the following beneficial effects:

[0035] By analyzing the air quality detection data collected based on the Internet of Things system, the present invention extracts instability characteristics from the data and calculates the local status scores, analyzes in combination with the time synchronization of the data collection points and the collaborative relationship of the monitored gases, and generates the global status instability score of the target monitoring area; dynamically generates the diffusion coefficient based on the environmental condition data, and constructs an abnormal status diffusion model in combination with the instability characteristics of the abnormal areas; predicts the pollution risk scores of future core areas through the model, and generates personalized air quality warning information, which can accurately monitor the dynamic changes of air quality in complex indoor environments, improve the accuracy of abnormal positioning and warning, effectively reduce monitoring errors and false alarm phenomena, and achieve accurate monitoring and warning of air quality within the area. Description of the Drawings

[0036] Figure 1 It is a schematic flowchart of a method for indoor air monitoring and warning based on the Internet of Things provided by one embodiment of the present invention.

[0037] Figure 2 It is a schematic structural diagram of an indoor air monitoring and warning system based on the Internet of Things provided by one embodiment of the present invention. Specific Embodiments

[0038] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] Please refer to Figure 1 , which shows a schematic flowchart of a method for indoor air monitoring and early warning based on the Internet of Things provided by one embodiment of the present invention. The method specifically includes the following steps:

[0040] Step S10: Obtain the air quality detection data corresponding to multiple data collection points respectively, extract multiple instability characteristic parameters corresponding to each data collection point for various monitored gases according to the air quality detection data, and calculate the local state instability score for each data collection point for each monitored gas according to the multiple instability characteristic parameters.

[0041] In this embodiment, the air quality detection data corresponding to the data collection point includes the concentration change data of various monitored gases such as PM2.5, CO 2 , VOCs, formaldehyde, etc. within a period of time collected through the Internet of Things system. A variety of sensor devices are set at the data collection points, which can monitor and collect gas data in different regions in real time and perform data integration and analysis through the Internet of Things system. According to different indoor environments such as park factories, office buildings and other scenarios, the corresponding monitoring period can be reasonably set according to actual needs. For example, periodic data analysis is performed every 15 minutes. For the data of each data collection point during a certain period, multiple instability characteristic parameters for various monitored gases are extracted to describe the critical instability characteristics of different data collection points in the target monitoring area, that is, the potential abnormal characteristics before the occurrence of air state abnormal events. Taking the volatility parameter and the correlation parameter as examples, the mean and standard deviation of the time series concentration vector of each monitored gas are obtained, and the ratio of the standard deviation to the mean of the monitored gas is used as the volatility parameter of the monitored gas. The time series concentration vector of each monitored gas is subjected to autocorrelation analysis, and the correlation parameter of the monitored gas is calculated through the autocorrelation coefficient formula. Then, based on the multiple instability characteristic parameters of the monitored gas, the local state instability score for each data collection point for each monitored gas is comprehensively calculated. The instability score can be defined as a weighted combination of instability characteristic parameters, reflecting the air quality abnormality degree of the local area corresponding to the data collection point during the current period.

[0042] Step S20: Obtain the location data of each data collection point, and fuse the state instability scores of each data collection point for each monitored gas based on the location data of the data collection point and the air quality detection data, so as to generate the global state instability score of the target monitoring area.

[0043] In this embodiment, after determining the air quality performance states of different local areas in the target monitoring area, the multiple local state instability scores corresponding to multiple data collection points are further fused. During the fusion process, the influence of the spatial position distribution of different data collection points is considered, and the possible data lag or synchronization difference of the sensor data at different positions is also considered, that is, the time-space synchronization of the signal is comprehensively considered to reflect the diffusion dynamics of pollutants. If the synchronization suddenly decreases, it may indicate local anomalies such as the sudden activation of pollution sources, so as to realize the efficient fusion of the characteristics of different data collection points, better apply to the regional air pollution monitoring and early warning in complex indoor environments, and finally generate the global state instability score representing the global state of the target monitoring area, reflecting the overall abnormal degree of the air quality at each position in the area.

[0044] Step S30: Calculate the dynamic diffusion coefficient of the target monitoring area for gas component diffusion according to the environmental condition data of the target monitoring area, and determine the local abnormal areas of the target monitoring area according to the global state instability score of the target monitoring area and the local state instability scores of each data collection point for each monitored gas.

[0045] In this embodiment, for the diffusion phenomenon of pollution sources in a complex environment, considering the influence of key factors such as environmental conditions (e.g., temperature, humidity, ventilation coefficient, etc.) on gas diffusion, based on the environmental condition data of the target monitoring area, the corresponding dynamic diffusion coefficient under the current environment is analyzed and calculated. For the global performance of the target monitoring area, after detecting that the global state instability score of the target monitoring area is greater than the preset global instability threshold, precise detection and division of local abnormal areas are initiated. The preset global instability threshold can be reasonably set according to information such as the characteristics of the monitoring area, air quality standards, or risk levels. For multiple data collection points in the target monitoring area, the local state instability scores of each data collection point regarding each monitored gas are analyzed one by one. Data collection points with any local state instability score greater than the preset global instability threshold among the multiple data collection points are determined and recorded as abnormal nodes. For some data collection points that are relatively close to each other, considering the diversity in the layout positions of data collection points in different scenarios (e.g., in locations such as office areas and green passage areas, the distribution of data collection points is relatively close, and in the presence of pollution sources, abnormal scoring phenomena may occur in all of them). Therefore, the position data of the data collection points are fused to avoid misidentifying a single pollution source as multiple. During the fusion process, data collection points with a distance less than the threshold can be fused according to a preset distance threshold, and the area corresponding to the fused data collection point is recorded as a local abnormal area. In this way, one or more possible local abnormal areas in the target monitoring area are determined.

[0046] Step S40: Construct an abnormal state diffusion model of the target monitoring area based on the air quality detection data and the dynamic diffusion coefficient of the data collection points in the local abnormal area. Determine the pollution risk scores of multiple core areas according to the abnormal state diffusion model, and generate air quality warning information regarding the multiple core areas based on the pollution risk scores.

[0047] In this embodiment, for each locally abnormal area obtained by division, an abnormal state diffusion model corresponding to the target monitoring area is constructed according to the air quality detection data of multiple data collection points included therein and the dynamic diffusion coefficient of the overall target monitoring area. In this process, the location of the pollution source and the corresponding pollution intensity are initially determined based on the air quality detection data of the data collection points in the locally abnormal area, and the diffusion phenomenon of the corresponding monitored gas is described by the dynamic diffusion coefficient, thereby constructing the abnormal state diffusion model. The pollution risk scores of multiple core areas in a future period are predicted and analyzed through the abnormal state diffusion model. These core areas can specifically be some areas that are preset to require key monitoring, or can be areas with a multi-person distribution determined according to the actual situation, such as based on real-time detection by personnel. Finally, air quality warning information regarding these core areas is generated according to the pollution risk scores. For example, if it is determined that mild pollution may occur in a future period, it is recommended to increase ventilation; if it is determined to be moderate pollution, it is recommended to turn on the air purification equipment; if severe pollution may occur, it is recommended that personnel evacuate in advance or strengthen the area sealing measures, etc.

[0048] The above indoor air monitoring and warning method starts from the air quality detection data of the data collection points, gradually extracts local instability features, fuses and generates a global state score, analyzes locally abnormal areas in combination with the dynamic diffusion coefficient, and realizes the pollution risk assessment and refined warning information generation of high-risk areas based on the abnormal diffusion model, solving the deficiencies of some simple monitoring and warning technologies based on thresholds in dynamic monitoring, abnormal positioning, and warning accuracy, and providing a comprehensive and accurate solution for the air quality management of complex indoor environments.

[0049] In one implementation process, for step S20 above, the state instability scores of each data collection point for each monitored gas are fused according to the location data and air quality detection data of the data collection points to generate the global state instability score of the target monitoring area, including:

[0050] Synchronous deviation analysis is performed on each data collection point according to the air quality detection data, the time synchronization parameter between any two data collection points is calculated, the synchronous deviation parameter of each data collection point is calculated based on multiple time synchronization parameters, and the state instability score of each data collection point for each monitored gas is corrected according to the synchronous deviation parameter to obtain the state instability corrected score of each data collection point for each monitored gas.

[0051] In this embodiment, the synchronous deviation analysis mainly focuses on the time synchronization problem between different data collection points. By comparing the gas concentration data of any two data collection points at the same moment, the local time synchronization parameter between the two points is calculated.

[0052] Among them, according to the air quality detection data corresponding to the data acquisition points, the following formula is used to calculate the local synchronization parameter of any monitoring gas between two data acquisition points: In the formula, q k1，k2 (t) represents the time local synchronization parameter of the monitoring gas at time t for data acquisition point k1 and data acquisition point k2, A k1 (t), A k2 (t) respectively represent the concentration values of the monitoring gas at time t for data acquisition point k1 and data acquisition point k2, d k1,k2 represents the spatial distance between data acquisition point k1 and data acquisition point k2.

[0053] Based on the air quality detection data, multiple local synchronization parameters of each monitoring gas between any two data acquisition points can be calculated through the above formula. In this process, considering that the air quality detection data may be high-frequency real-time acquisition, for the time period corresponding to the air quality detection data, based on a preset time window, for example, at intervals of 1 min, the air quality detection data can be traversed by sliding the window to obtain multiple sets of characteristic data, that is, taking the average gas concentration within each sliding window as the concentration value of the gas at the moment corresponding to the center point of the sliding window, so as to determine multiple local synchronization parameters of each monitoring gas in the air quality detection data, taking the average value of the multiple local synchronization parameters as the time synchronization parameter between the two data acquisition points, and finally calculating the average value of the multiple time synchronization parameters corresponding to each data acquisition point to obtain the synchronization deviation parameter of the data acquisition point.

[0054] For the process of correcting the state instability score of the data acquisition point for each monitoring gas according to the synchronization deviation parameter, the following method can be adopted: State instability correction score = State instability score × (1 - Synchronization deviation parameter), so as to obtain the state instability correction score of the data acquisition point for each monitoring gas, effectively compensating for the scoring error caused by the time distribution difference or noise between the acquisition points and improving the accuracy of the global state instability score.

[0055] Perform collaborative analysis of the monitoring gases for each data acquisition point, calculate the dynamic correlation parameter between any two monitoring gases for each data acquisition point, and calculate the co-variation parameter of each data acquisition point for each monitoring gas based on the multiple dynamic correlation parameters.

[0056] In this embodiment, according to the air quality detection data corresponding to the data collection points, the time-series concentration vectors of each monitoring gas for the data collection points are extracted. Correlation analysis is performed on any two monitoring gases based on the time-series concentration vectors to calculate the dynamic correlation parameters between the two monitoring gases. For example, the Pearson correlation coefficient is used to measure the dynamic correlation characteristics between the two time-series concentration vectors. Finally, the average value of the multiple dynamic correlation parameters corresponding to each monitoring gas is calculated to obtain the co-variation parameter of each monitoring gas. Through dynamic co-variation analysis, the complex correlation relationships of multiple monitoring gases can be comprehensively evaluated, effectively making up for the deficiencies of single-gas scoring in the scenario of multi-pollutant co-action, and can be used to further optimize the rationality of the local state instability score.

[0057] To generate the global state instability score of the target monitoring area, by combining the location information of the data collection points and the air quality detection data, compensation is carried out through the synchronous deviation analysis and monitoring gas co-variation analysis of each data collection point, further improving the accuracy and robustness of the global state instability score. This method can consider the correlation characteristics of monitoring gases in space and time on the basis of making full use of the local state information of the collection points, ensuring that the global score calculation has higher adaptability and reliability. In this process, multiple state instability correction scores are fused based on the location data of each data collection point and the corresponding multiple co-variation parameters to generate the global state instability score of the target monitoring area, where: In the formula, I ns is the global state instability score of the target monitoring area, C i,j is the co-variation parameter of the i-th data collection point with respect to the j-th monitoring gas, R i,j is the state instability correction score of the i-th data collection point with respect to the j-th monitoring gas, is the location weight of the i-th data collection point, which can be reasonably set according to the relative distance between the data collection points. In this process, the data collection point with the highest state instability correction score can be used as the initial position for reference. The farther the data collection point is from the initial position, the smaller the corresponding location weight. m is the total number of data collection points, and n is the number of categories of monitoring gases.

[0058] Through synchronous deviation analysis, the problem of insufficient time synchronization between data collection points is solved, and the consistency of the state score in space is improved. Through co-variation analysis, the defect that single-gas scoring may ignore the complex relationships of multiple pollutants is made up, and the robustness of the score is comprehensively improved, so that the calculated global state instability score can more truly reflect the actual air quality dynamic changes in the target monitoring area.

[0059] In one of the implementation processes, for step S40 above, an abnormal state diffusion model of the target monitoring area is constructed based on the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal area, including:

[0060] Determine the concentration parameter of each monitoring gas in the local abnormal area according to the air quality detection data of the data collection points, and perform correction processing on the concentration parameter based on the local state instability score corresponding to the monitoring gas to obtain the initial intensity parameter of each monitoring gas.

[0061] In this embodiment, for the local abnormal area determined in the foregoing step, since it may contain multiple data collection points, first determine the concentration parameter of each monitoring gas under each data collection point. For a single data collection point, the concentration parameter is corrected by the local state instability score corresponding to the monitoring gas to estimate the intensity of the pollution source, and the initial intensity parameter of each monitoring gas is calculated. For the case where there are multiple data collection points, after calculating the initial intensity parameter of each monitoring gas for each collection point, the maximum value can be taken as a representative to obtain the initial intensity parameter of the local abnormal area.

[0062] Generate a two-dimensional convective diffusion equation for the local abnormal area according to the dynamic diffusion coefficient and the initial intensity parameter of the data collection point, and construct an abnormal state diffusion model of the target monitoring area according to the two-dimensional convective diffusion equations of each local abnormal area in the target monitoring area.

[0063] In this embodiment, for the two-dimensional convective diffusion equation, the construction process needs to involve the dynamic diffusion coefficient describing the diffusion state, as well as the initial pollution source position and intensity. Among them, the core position of the local abnormal area can be used as the initial pollution source position, and according to the initial intensity parameter of the local abnormal area and the dynamic diffusion coefficient of the target monitoring area, a two-dimensional convective diffusion equation for each monitoring gas is constructed. The two-dimensional convective diffusion equation is a well-known technical means for those skilled in the art and will not be elaborated here. It is worth noting that the two-dimensional convective diffusion equation considers the boundary conditions compared with the one-dimensional convective diffusion equation. In the specific implementation process, the indoor space boundary such as the wall can be set as an impermeable boundary to reflect the role of the wall. Finally, for each local abnormal area, a two-dimensional convective diffusion equation corresponding to each monitoring gas is constructed, thereby generating an abnormal state diffusion model for the target monitoring area.

[0064] Construct an abnormal state diffusion model of the target monitoring area according to the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal area within the target monitoring area. This process aims to model the diffusion law of the abnormal state, accurately describe the diffusion dynamics of each monitoring gas in the target monitoring area, and provide support for subsequent pollution risk assessment and air quality early warning.

[0065] Among them, for the construction of the two-dimensional convection-diffusion equation, a key point is to determine the dynamic diffusion coefficient describing the diffusion state. Specifically, for the dynamic diffusion coefficient used to describe the diffusion state of gas components in the target monitoring area, it is obtained through the following analysis method:

[0066] Input the environmental condition data of the target monitoring area into the diffusion coefficient analysis model, and generate the corresponding dynamic diffusion coefficient of the environmental condition data of the target monitoring area through the diffusion coefficient analysis model.

[0067] For the diffusion coefficient analysis model, a training data set is constructed by obtaining multiple groups of historical data of the target monitoring area. Among them, each group of historical data includes a set of associated environmental condition data and gas component detection data. The environmental condition data includes data such as the temperature, humidity, and ventilation speed of the target monitoring area changing with time within a certain period, and the gas component detection data includes data on the concentrations of various gases changing with time in different local areas of the target monitoring area during this period.

[0068] In the process of constructing the training data set by analyzing multiple groups of historical data, the two-dimensional convection-diffusion equation is discretized in time and space to generate the target diffusion function. Among them, for time discretization, the finite difference method can be specifically used to convert the time derivative into a difference form. For space discretization, the target monitoring area can be divided into a two-dimensional grid, and the change of gas concentration at each grid point can be calculated according to the difference, so as to construct the target diffusion function that can describe the diffusion behavior of gas components in space and time. The discrete processing of the two-dimensional convection-diffusion equation is a well-known technical means in the art, and specific limitations are not imposed here.

[0069] Then, multiple sets of historical data are used to fit the target diffusion function. The data fitting process can be achieved through methods such as polynomial fitting and random forest model fitting. Those skilled in the art can select a suitable fitting scheme according to actual needs. During the data fitting process, mainly based on the actual change law of the volume concentration, the distribution law of the diffusion coefficient in the time and space dimensions is analyzed, and finally the target diffusion coefficient corresponding to each set of historical data is generated. Then, the environmental condition data in each set of historical data is associated with the corresponding target diffusion coefficient, and a training data set is constructed. The diffusion coefficient analysis model is trained through the training data set. During the training process, specifically, the environmental condition data in the training data set is used as the input feature, and the target diffusion coefficient obtained by fitting is used as the output target to complete the training process. For the diffusion coefficient analysis model, in this embodiment, a multi-layer perceptron is taken as an example of the diffusion coefficient analysis model. After completing the iterative training of the model through the training data set, the finally trained diffusion coefficient analysis model can be used to predict and output the diffusion coefficient corresponding to the target monitoring area under the current environment according to the input environmental condition data. Thus, after generating the dynamic diffusion coefficient of the target monitoring area regarding the gas component diffusion based on the environmental condition data of the target monitoring area, an abnormal state diffusion model of the target monitoring area is constructed.

[0070] In one implementation process, for step 40 above, determining the pollution risk scores of multiple core areas according to the abnormal state diffusion model includes:

[0071] Determine the reference coordinate data corresponding to each core area, which can specifically be the central position of the core area. For the abnormal state diffusion model, after substituting the reference coordinate data corresponding to the core area into any two-dimensional convective diffusion equation, the finite difference method (FDM) can be used to discretize the convective diffusion equation. By iterative methods such as the explicit method or the implicit method, the gas concentration data at the reference coordinates of the core area is gradually calculated to obtain the concentration prediction data of the monitored gas corresponding to the two-dimensional convective diffusion equation at different times. Then, the pollution risk score of the core area is determined according to the concentration prediction data. Solving the two-dimensional convective diffusion equation under specific boundary conditions is a well-known technical means to those skilled in the art, and it is not specifically limited in this embodiment.

[0072] Among them, for the pollution risk score, it can be reasonably set according to the preset scoring rules. For example, the concentration ranges of different gases under mild, moderate, and severe pollution can be determined in advance, and the pollution risk scores corresponding to different pollution levels can be determined, so as to determine the pollution prediction situation of different core areas at a certain future moment, facilitating early warning of possible local air pollution. The indoor air monitoring and early warning method provided by the embodiments of the present invention can be applied to different indoor scenarios, such as park factories, office buildings, laboratories, etc. For some environments where local air pollution may occur due to production processes or experimental operations, real-time monitoring and analysis are carried out through the above-provided monitoring and early warning method to provide accurate and personalized air quality early warning services.

[0073] Please refer to Figure 2 , which shows a schematic structural diagram of an indoor air monitoring and early warning system based on the Internet of Things provided by one embodiment of the present invention. This indoor air monitoring and early warning system can be specifically used to implement the above-provided indoor air monitoring and early warning method based on the Internet of Things, and includes the following structures:

[0074] The local status analysis module is used to obtain the air quality detection data corresponding to multiple data collection points, extract multiple instability characteristic parameters corresponding to each data collection point for each of the multiple monitored gases from the air quality detection data, including volatility parameters and correlation parameters, and calculate the local status instability score of each data collection point for each monitored gas based on the multiple instability characteristic parameters;

[0075] The global status instability analysis module is used to obtain the location data of each data collection point, and fuse the status instability scores of each data collection point for each monitored gas based on the location data and air quality detection data of the data collection point to generate the global status instability score of the target monitoring area;

[0076] The abnormal area analysis module is used to calculate the dynamic diffusion coefficient of the target monitoring area for gas component diffusion according to the environmental condition data of the target monitoring area, and determine the local abnormal areas of the target monitoring area based on the global status instability score of the target monitoring area and the local status instability scores of each data collection point for each monitored gas;

[0077] The air monitoring and early warning module is used to construct an abnormal status diffusion model of the target monitoring area based on the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal areas, determine the pollution risk scores of multiple core areas according to the abnormal status diffusion model, and generate air quality early warning information about the multiple core areas based on the pollution risk scores.

[0078] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The parts not described in detail in this specification belong to the prior art well-known to those skilled in the art.

Claims

1. An indoor air monitoring and early warning method based on the Internet of Things, characterized in that: include: Acquire air quality detection data corresponding to multiple data collection points, extract multiple instability characteristic parameters corresponding to multiple monitoring gases at each data collection point according to the air quality detection data, including volatility parameters and correlation parameters, and calculate the local state instability score of each data collection point for each monitoring gas according to the multiple instability characteristic parameters; Obtain the location data of each data collection point, fuse the state instability score of each data collection point for each monitored gas according to the location data of the data collection point and the air quality detection data, and generate a global state instability score for the target monitoring area; The dynamic diffusion coefficient of the target monitoring area regarding the diffusion of gas components is calculated based on the environmental condition data of the target monitoring area, and the local abnormal area of ​​the target monitoring area is determined based on the global state instability score of the target monitoring area and the local state instability score of each data collection point for each monitored gas; An abnormal state diffusion model for the target monitoring area is constructed based on the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal area. The pollution risk scores of multiple core areas are determined based on the abnormal state diffusion model. Air quality warning information about multiple core areas is generated based on the pollution risk scores.

2. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 1, characterized in that: According to the location data of the data collection point and the air quality detection data, the state instability score of each data collection point for each monitored gas is fused to generate a global state instability score for the target monitoring area, including: Perform synchronization deviation analysis on each data collection point according to the air quality detection data, calculate the time synchronization parameters between any two data collection points, calculate the synchronization deviation parameters of each data collection point according to multiple time synchronization parameters, and correct the state instability score of the data collection point for each monitored gas according to the synchronization deviation parameters to obtain the state instability correction score of the data collection point for each monitored gas; Conduct collaborative analysis of the monitored gases at each data collection point, calculate the dynamic correlation parameters between any two monitored gases at each data collection point, and calculate the collaborative change parameters of each monitored gas at each data collection point based on multiple dynamic correlation parameters; Based on the location data of each data collection point and the corresponding multiple coordinated change parameters, multiple state instability correction scores are fused to generate a global state instability score for the target monitoring area, where: In the formula, I ns is the global state instability score of the target monitoring area, C i,j is the coordinated variation parameter of the i-th data collection point with respect to the j-th monitoring gas, R i,j is the state instability correction score for the jth monitoring gas at the ith data collection point, is the location weight of the ith data collection point, m is the total number of data collection points, and n is the number of monitored gas categories.

3. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 1 is characterized in that: The abnormal state diffusion model of the target monitoring area is constructed based on the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal area, including: Determine the concentration parameters of each monitored gas in the local abnormal area based on the air quality detection data of the data collection point, correct the concentration parameters based on the local state instability score corresponding to the monitored gas to obtain the initial intensity parameters of each monitored gas, generate the two-dimensional convection diffusion equation of the local abnormal area based on the dynamic diffusion coefficient and the initial intensity parameters of the data collection point, and construct the abnormal state diffusion model of the target monitoring area based on the two-dimensional convection diffusion equation of each local abnormal area in the target monitoring area; For local abnormal areas in the target monitoring area, after detecting that the global state instability score of the target monitoring area is greater than the preset global instability threshold, multiple data collection points in the target monitoring area whose local state instability scores are greater than the preset global instability threshold are determined and recorded as abnormal nodes, and multiple abnormal nodes are fused according to the position data of the data collection points to determine multiple local abnormal areas.

4. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 1, characterized in that: The dynamic diffusion coefficient of the target monitoring area regarding the diffusion of gas components is calculated based on the environmental condition data of the target monitoring area, including: The environmental condition data of the target monitoring area is added to the diffusion coefficient analysis model, and the dynamic diffusion coefficient corresponding to the environmental condition data of the target monitoring area is generated by the diffusion coefficient analysis model; For the diffusion coefficient analysis model, a training data set is constructed by acquiring multiple groups of historical data of the target monitoring area, wherein each group of historical data contains a group of associated environmental condition data and gas composition detection data. The target diffusion function is generated by time discretizing and space discretizing the two-dimensional convection-diffusion equation. The target diffusion function is fitted with multiple groups of historical data to generate the target diffusion coefficient corresponding to each group of historical data. The environmental condition data in each group of historical data is associated with the corresponding target diffusion coefficient and constructed to obtain a training data set. The diffusion coefficient analysis model is trained using the training data set to obtain a trained diffusion coefficient analysis model.

5. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 2 is characterized in that: For synchronous deviation analysis of data collection points and coordinated analysis of monitored gases, it also includes: According to the air quality detection data corresponding to the data collection point, the local synchronization parameter between two data collection points for any monitored gas is calculated using the following formula: In the formula, q k1，k2 (t) represents the local synchronization parameter of the data acquisition point k1 and the data acquisition point k2 at time t with respect to a certain monitoring gas, A k1 (t), A k2 (t) represents the concentration value of a certain monitoring gas at the data collection point k1 and the data collection point k2 at time t, d k1,k2 represents the spatial distance between data collection point k1 and data collection point j2; After the local synchronization parameters for each monitored gas between any two data collection points are calculated based on the air quality detection data using the above formula, the average of multiple local synchronization parameters is taken as the time synchronization parameter between the two data collection points, and the average of multiple time synchronization parameters corresponding to each data collection point is calculated to obtain the synchronization deviation parameter of the data collection point; According to the air quality detection data corresponding to the data collection point, the time series concentration vector of each monitoring gas at the data collection point is extracted, and correlation analysis is performed on any two monitoring gases according to the time series concentration vector to calculate the dynamic correlation parameters between the two monitoring gases. The mean of multiple dynamic correlation parameters corresponding to each monitoring gas is calculated to obtain the coordinated change parameter of each monitoring gas.

6. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 3 is characterized in that: The pollution risk scores for multiple core areas are determined based on the abnormal state diffusion model, including: Determine the reference coordinate data corresponding to each core area, and analyze the reference coordinate data corresponding to each core area through the abnormal state diffusion model, including inputting the reference coordinate data corresponding to each core area into multiple two-dimensional convection-diffusion equations respectively, processing the two-dimensional convection-diffusion equations through the finite difference method, and obtaining the concentration prediction data corresponding to the reference coordinate data at a preset time, and determining the pollution risk score of the core area according to the concentration prediction data.

7. The method for indoor air monitoring and early warning based on the Internet of Things according to claim 5, characterized in that: Based on the air quality detection data, multiple instability characteristic parameters corresponding to various monitoring gases at each data collection point are extracted, including: The mean and standard deviation of the time series concentration vector of each monitored gas are calculated, and the ratio of the standard deviation to the mean of the monitored gas is used as the volatility parameter of the monitored gas. An autocorrelation analysis is performed on the time series concentration vector of each monitored gas to calculate the correlation parameter of the monitored gas.

8. An indoor air monitoring and early warning system based on the Internet of Things, characterized in that: The system is used to implement an indoor air monitoring and early warning method based on the Internet of Things as described in any one of claims 1 to 7, comprising: A local state analysis module is used to obtain air quality detection data corresponding to multiple data collection points, extract multiple instability characteristic parameters corresponding to multiple monitoring gases at each data collection point according to the air quality detection data, including volatility parameters and correlation parameters, and calculate the local state instability score of each data collection point for each monitoring gas according to the multiple instability characteristic parameters; The global state instability analysis module is used to obtain the location data of each data collection point, fuse the state instability score of each data collection point for each monitored gas according to the location data of the data collection point and the air quality detection data, and generate the global state instability score of the target monitoring area; The abnormal area analysis module is used to calculate the dynamic diffusion coefficient of the target monitoring area for the diffusion of gas components according to the environmental condition data of the target monitoring area, and determine the local abnormal area of ​​the target monitoring area according to the global state instability score of the target monitoring area and the local state instability score of each data collection point for each monitored gas; The air monitoring and early warning module is used to construct an abnormal state diffusion model of the target monitoring area based on the air quality detection data and dynamic diffusion coefficient of the data collection points in the local abnormal area, determine the pollution risk scores of multiple core areas based on the abnormal state diffusion model, and generate air quality early warning information about multiple core areas based on the pollution risk scores.

Images