Bioaerosol scene simulation system based on artificial intelligence

Abstract

The present invention provides a bioaerosol scene simulation system based on artificial intelligence, which relates to the field of aerosol detection technology, including: a constraint relationship determination module, which is used to perform inter-class interaction analysis and intra-class multiphase flow motion analysis to determine motion constraint relationships; a fitting field construction module, which is used to construct a fitting field; a simulation scene construction module, which is used to build a visual simulation scene; a diffusion behavior analysis module, which is used to perform motion diffusion behavior analysis based on fluid mechanics to determine the first scene simulation data; a scene simulation switching module, which is used to perform scene simulation switching and analysis to determine the second scene simulation data; a simulation result determination module, which is used to determine the scene simulation result. The present invention solves the technical problems that the prior art is difficult to accurately simulate the complex dynamic behavior of bioaerosols, and is difficult to meet the simulation requirements under different demand scenarios, resulting in poor simulation accuracy and operability.

Description

Technical Field

[0001] The present invention relates to the technical field of aerosol detection, and in particular to a bioaerosol scene simulation system based on artificial intelligence. Background Art

[0002] Bioaerosols refer to tiny biological particles suspended in the air, which may pose a potential threat to the environment and human health. Therefore, their propagation and diffusion behaviors need to be accurately simulated and analyzed in order to effectively control them. However, the existing technologies have a series of technical problems in the simulation of bioaerosol scenarios. On the one hand, the movement of bioaerosols is affected by many factors, such as air flow, interaction between particles, etc. The existing technologies are difficult to accurately simulate the dynamic behaviors of bioaerosols caused by these complex factors. On the other hand, in actual scenarios, the propagation and diffusion of bioaerosols may change at any time, and it is necessary to be able to dynamically simulate and control the scenarios. However, the existing technologies are usually simulated based on fixed scenarios, which makes it difficult to meet the simulation needs in different situations. Summary of the invention

[0003] This application provides an artificial intelligence-based bioaerosol scene simulation system to solve the technical problems that the existing technology is difficult to accurately simulate the complex dynamic behavior of bioaerosols and is difficult to meet the simulation requirements in different demand scenarios, resulting in poor simulation accuracy and operability.

[0004] The artificial intelligence-based bioaerosol scene simulation system disclosed in the present application includes: a constraint relationship determination module, the constraint relationship determination module is used to determine the biological particle class of the bioaerosol, perform inter-class interaction analysis and intra-class multiphase flow motion analysis, and determine the motion constraint relationship, wherein the multiphase flow motion is a mixed motion of at least two phases; a fitting field construction module, the fitting field construction module is used to construct a fitting field based on a simulation scene based on the motion influencing factors of the bioaerosol, the fitting field is generated based on multiple factor fields according to the simulation scene factors, and the fitting field can be switched based on the simulation scene; a simulation scene construction module, the simulation scene construction module is used to build a fitting field based on the motion constraint relationship and the fitting field. A visual simulation scene is constructed, and the visual simulation scene is placed in an adaptive simulation module; a diffusion behavior analysis module, and the diffusion behavior analysis module is used to perform a fluid mechanics-based motion diffusion behavior analysis on the bioaerosol based on the visual simulation scene to determine the first scene simulation data; a scene simulation switching module, and the scene simulation switching module is used to take the characteristic value distribution of field factors as the first control target and the self-characteristics of the bioaerosol as the second control target, and based on the adaptive simulation module, perform scene simulation switching and analysis on the visual simulation scene to determine the second scene simulation data; a simulation result determination module, and the simulation result determination module is used to determine the scene simulation result based on the first scene simulation data and the second scene simulation data.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] By determining the biological particle class of bioaerosol, conducting inter-class interaction analysis and intra-class multiphase flow motion analysis, and establishing multiphase flow motion constraint relationships, the simulation and analysis of the dynamic behavior of complex bioaerosols are realized, making the simulation closer to the real situation and improving the credibility of the simulation results; by generating a fitting field based on the motion influencing factors of bioaerosols and fitting the simulation scene factors based on multiple factor fields, a comprehensive modeling of the motion influencing factors is achieved, making the simulation process more precise and improving the accuracy of the simulation results; by building a visual simulation scene and placing it in an adaptive simulation module, the visualization and dynamic regulation of the simulation scene are realized, making the simulation results more intuitive The system improves the interactivity and operability of the simulation process by combining the characteristics of the movement and diffusion behavior based on fluid mechanics and determining the simulation data of the first scenario, which helps to understand the propagation characteristics of bioaerosols in the air. By taking the characteristic value distribution of field factors as the first control target and the self-characteristics of bioaerosols as the second control target, the scene simulation switching and analysis are carried out to determine the simulation data of the second scenario, which realizes the effective simulation of field factors and the self-characteristics of bioaerosols, making the simulation results more flexible and controllable, and meeting the simulation requirements under different demand scenarios. The scene simulation results are determined based on the simulation data of the first scenario and the simulation data of the second scenario, which realizes the comprehensive analysis of the scene simulation results.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the structure of a bioaerosol scene simulation system based on artificial intelligence is provided for the embodiment of the present application;

[0009] Figure 2 A schematic diagram of the execution flow of a constraint relationship determination module in an artificial intelligence-based bioaerosol scene simulation system is provided for an embodiment of the present application.

[0010] Explanation of the reference numerals: constraint relationship determination module 10 , fitting field construction module 20 , simulation scene construction module 30 , diffusion behavior analysis module 40 , scene simulation switching module 50 , simulation result determination module 60 . DETAILED DESCRIPTION

[0011] The embodiments of the present application provide an artificial intelligence-based bioaerosol scene simulation system to solve the technical problems that the prior art has difficulty in accurately simulating complex bioaerosol dynamic behaviors and has difficulty in meeting simulation requirements under different demand scenarios, resulting in poor simulation accuracy and operability.

[0012] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0013] like Figure 1 As shown, the embodiment of the present application provides a bioaerosol scene simulation system based on artificial intelligence, and the system includes:

[0014] The constraint relationship determination module 10 is used to determine the biological particle class of the bioaerosol, perform inter-class interaction analysis and intra-class multiphase flow motion analysis, and determine the motion constraint relationship, wherein the multiphase flow motion is a mixed motion of at least two phases.

[0015] Identify the different types of biological particles present in bioaerosols, such as classification based on the properties, size, shape, density and other characteristics of the particles. Analyze and summarize based on experimental data or existing literature to establish a library of particle categories, and conduct mutual influence analysis on the identified biological particle types, that is, analyze the interaction between particles of different categories, such as whether there is mutual attraction, repulsion, collision, etc.

[0016] The multiphase flow motion inside each type of biological particle is analyzed. Multiphase flow refers to the mixed motion of different phases, such as gas, liquid, and solid, in a fluid. For bioaerosols, it involves the mutual transformation of particles between gas and liquid states, sedimentation velocity, etc. It can be analyzed in combination with factors such as the physical properties of the particles and environmental conditions.

[0017] On the basis of the inter-class interaction analysis and the intra-class multiphase flow motion analysis, a motion constraint relationship is established. This relationship can describe the motion restrictions or laws between different particle classes. For example, some particle classes may repel each other, or aggregation may occur under certain conditions, providing a basis for subsequent simulations.

[0018] Furthermore, if Figure 2 As shown, the constraint relationship determination module 10 includes executing the following operation steps:

[0019] Traverse the biological particle classes, perform mutual influence analysis on any at least two classes, and determine a first motion constraint relationship, wherein the mutual influence analysis is determined based on the motion difference between a single class and multiple classes in coordination; for each biological particle class, perform motion influence analysis based on phase flow differences, and determine a second motion constraint relationship, wherein the second motion constraint relationship is determined based on the motion difference between a single-phase flow and multiple-phase flow in coordination; determine the motion constraint relationship based on the first motion constraint relationship and the second motion constraint relationship.

[0020] Mutual influence analysis is the process of analyzing different categories of biological particles and studying the interactions between them to determine the motion constraint relationship. Specifically, biological particle categories are defined, which can be classified based on the properties, size, shape, density and other characteristics of the particles. Biological particles are divided into different categories, and mutual influence analysis is performed on the defined biological particle categories, including mutual influence analysis between particles of the same type and mutual influence analysis between particles of different types. The mutual influence analysis is determined based on the motion difference between a single category and multiple categories of coordination.

[0021] Specifically, the differences between the movement of a single type of particle and multiple types of particles, such as changes in speed, direction, trajectory, etc., can be compared to analyze the mutual influence relationship between them. Exemplarily, during the simulation or experiment, the relevant data of the movement of a single type of particle and multiple types of particles are collected, including data such as position coordinates, speed, acceleration, and changes in distance between each other. The collected data are analyzed to compare the movement characteristics of a single type of particle and multiple types of particles, such as whether there is mutual attraction, repulsion, collision, etc., and the influence of these characteristics on the movement of particles. Based on the results of the mutual influence analysis, the first motion constraint relationship is determined. The motion constraint relationship includes constraints on particle speed, direction, mutual repulsion or attraction, etc., which are used to simulate and control the movement behavior between particle categories.

[0022] For different types of biological particles, phase flow difference analysis is performed. Phase flow refers to the motion characteristics of each phase in a multiphase fluid system, such as the interaction and flow patterns between gas and liquid and solid particles. The differences in motion characteristics of each type of biological particle under different phase flow conditions are analyzed, including single-phase flow, such as gas flow, liquid flow, etc., and multiphase flow, such as gas-solid flow, gas-liquid flow, etc.

[0023] Based on the results of the phase flow difference analysis, a motion impact analysis is performed, including comparison and analysis of motion influencing factors such as speed, direction, and diffusion degree of biological particle categories under different phase flow conditions, and analysis of the motion difference of biological particle categories in single-phase flow and multi-phase flow, that is, the differences and impacts of particle motion under different phase flow conditions. Based on the results of the motion impact analysis, the second motion constraint relationship is determined, which is a constraint condition on particle speed, diffusion rate, motion direction, etc. under different phase flow conditions.

[0024] The first motion constraint relationship and the second motion constraint relationship are integrated, including integrating the motion constraint relationship obtained from the mutual influence analysis between categories of bioaerosols and the motion influence analysis based on phase flow differences to determine the motion constraint relationship.

[0025] The fitting field construction module 20 is used to construct a fitting field based on a simulation scene based on the movement influencing factors of the bioaerosol. The fitting field is generated based on multiple factor fields according to the simulation scene factors. The fitting field can be switched based on the simulation scene.

[0026] Determine the factors affecting the movement of bioaerosols, including the size, density, shape, environmental conditions (such as temperature, humidity), airflow velocity, and other factors of aerosol particles, which will directly affect the diffusion behavior of aerosols in the air. According to the above factors affecting movement, construct multiple factor fields, each field represents the change of one or more factors, for example, there can be a temperature field, a humidity field, an airflow velocity field, etc.

[0027] Multiple factor fields are integrated to form a comprehensive fitting field, which can be a complex spatial model that reflects the changing distribution of different factors in space. This fitting field is flexible and can be switched according to simulation requirements. For example, if you need to simulate aerosol propagation in different seasons or under different meteorological conditions, you can switch different fitting fields to meet different simulation scenario requirements.

[0028] Furthermore, the fitting field construction module 20 includes executing the following operation steps:

[0029] Determine the simulated space field distribution, traverse the motion influencing factors, and determine multiple factor fields, wherein the field points of the factor field are represented as (x, y, z, f), and f is the field factor value; based on the simulated scene, determine the scene factor class and the scene factor value distribution, wherein the scene factor class is the environmental factor; based on the scene factor class, match and map the multiple factor fields to the field space, fit and perform field restoration of the scene factor value distribution, and determine the fitting field.

[0030] Determine the scope and boundaries of the simulation space, including the length, width, and height dimensions in three-dimensional space, and list various factors that affect the simulation scene, such as environmental factors, bioaerosol concentration, particle movement direction, etc. Environmental factors include temperature, humidity, air flow velocity, etc. For each influencing factor, determine the corresponding factor field. The factor field is a mathematical model that describes a factor in the simulation space. The field point in each factor field can be represented by (x, y, z, f), where (x, y, z) is the spatial position coordinate, and f is the field factor value corresponding to the point.

[0031] Determine the categories of scenario factors that need to be considered, such as environmental factors, bioaerosol characteristics, etc. These factor categories are important factors that need to be paid attention to in the simulation. For each scenario factor category, determine the distribution of scenario factor values ​​at each location point according to the actual scenario or simulation requirements. For example, for the environmental factor category, you can determine the spatial distribution of temperature, humidity, air flow velocity, etc., such as the distribution of temperature at different locations in the room, the distribution of humidity with height, the distribution of air flow velocity at the vents, etc.

[0032] For the defined scenario factor class, the corresponding factor field is matched. Each factor field describes the distribution of the corresponding factor in space. For each factor field, field space mapping is performed, including determining the spatial range and boundaries of each field, and mapping the field points with the positions in the actual simulation space. On the basis of the field space mapping, the fitting field restoration is performed, which means combining the matched factor field and the space mapping results to obtain a complete fitting field. The fitting field can accurately reflect the distribution of various factors in the simulation space, that is, the value obtained through field restoration should be as close to the actual situation as possible.

[0033] Furthermore, the fitting field construction module 20 further includes executing the following operation steps:

[0034] A human motion behavior of the simulated scene is determined, and based on the human motion behavior, a compensation adjustment is performed on the fitting field.

[0035] Define the possible human movement behaviors in the simulation scene, such as people entering and exiting, changes in activity areas, etc., determine factors such as people's activity range, density distribution, and activity time. These factors will affect the distribution of other factors in the scene, such as air flow velocity, diffusion range of bioaerosols, etc.

[0036] According to human movement behavior, the fitting field is compensated and adjusted. This means that on the basis of the fitting field, the corresponding factor distribution is adjusted in combination with the impact of human activities on the environment. For example, if people are active in a certain area, it may affect the temperature, humidity and other environmental factors in that area. The factor values ​​of these areas in the fitting field need to be adjusted to reflect the actual situation. The compensation adjustment can better simulate and reflect the actual impact of human movement behavior on the environment.

[0037] The simulation scene building module 30 is used to build a visual simulation scene based on the motion constraint relationship and the fitting field, and the visual simulation scene is placed in the adaptive simulation module.

[0038] Based on the motion constraint relationship and fitting field, a simulation scene is built using visualization software. This scene can be three-dimensional, showing the movement, interaction and influence of environmental factors of bioaerosol particle categories. The built visualization simulation scene is embedded in the adaptive simulation module. The adaptive simulation module can adjust the simulation scene according to user input or specific conditions to meet different simulation needs. For example, the user can change the simulation scene by adjusting parameters or switching different fitting fields, and then observe the changes in the simulation results.

[0039] The diffusion behavior analysis module 40 is used to perform a fluid mechanics-based motion diffusion behavior analysis on the bioaerosol based on the visual simulation scene to determine the first scene simulation data.

[0040] Based on the constructed visual simulation scene, fluid dynamics simulation methods, such as computational fluid dynamics simulation or discrete element simulation, are used to simulate the movement and diffusion behavior of bioaerosols, including simulating the interaction between gas and particles, turbulence effects, the influence of environmental conditions on diffusion and other factors. During the simulation process, data such as the movement trajectory, distribution and diffusion speed of bioaerosol particles in space are collected. These data can be acquired through real-time monitoring of simulation software, and statistical analysis is performed on the collected data to determine the diffusion behavior characteristics of bioaerosols, such as diffusion range, diffusion rate, diffusion path, etc. According to the results of the analysis, the first scenario simulation data is generated.

[0041] Furthermore, the diffusion behavior analysis module 40 further includes executing the following operation steps:

[0042] After determining the first scene simulation data, the visual simulation scene is identified, the field grid is segmented based on a preset difference, and the grid division result is determined, wherein the segmentation standard is non-uniform grid division based on fitting the field distribution difference; based on the grid division result, the first scene simulation data is divided, and the cross-grid transition analysis is performed to determine the flow characteristics.

[0043] After determining the simulation data of the first scene, identify the visual simulation scene. Generally speaking, the elements in the scene space are unevenly distributed. For example, the ventilation volume and the distribution position of the air inlet and outlet limit the characteristics of wind force, wind direction and air volume. Perform zoning analysis to improve the pertinence. Specifically, for each factor in the fitting field, a difference analysis is performed, including a quantitative evaluation of the distribution differences of each factor in space to determine the difference of each position. Based on the preset difference, the field grid is segmented. This can be achieved through a grid segmentation algorithm to divide the simulation space into different grid areas. The field factor values ​​in each area are relatively uniform, while there are large differences between areas. The segmentation standard is non-uniform grid division based on the distribution difference of the fitting field, that is, according to the distribution of field factors, the space is divided into non-uniform grid areas with large differences.

[0044] The grid division results are applied to the simulation data of the first scenario, which means that the values ​​of various factors in the simulation data are divided according to the grid division results, so that the data values ​​in each grid area represent the typical values ​​of the area. The cross-grid change analysis is performed on the divided simulation data. The cross-grid change analysis can determine the flow change characteristics of the data between grids as the field changes by comparing the changes in the data in adjacent grids. According to the results of the cross-grid change analysis, the flow characteristics are determined, including determining the amplitude and trend of the data changes at the grid boundaries, and determining which factors have obvious changes at the grid boundaries, thereby determining the flow characteristics of these factors.

[0045] During the analysis process, it is necessary to distinguish the sources of data differences. If the data differences are small, they may be caused by fluctuations within the normal range. In this case, they are not representative. Focus on the data differences at the grid boundaries because these data differences may reflect the changing characteristics within the field and are more representative.

[0046] Furthermore, the diffusion behavior analysis module 40 further includes executing the following operation steps:

[0047] Obtain the grid division result and extract the adjacent grid data, the data dimensions including grid field data and grid simulation data; calibrate the adjacent grid data, and based on the field data change and the simulation data change, perform flow analysis based on the grid trend change to determine the flow characteristics.

[0048] For each grid area, the data of its adjacent grids are extracted, including grid field data and grid simulation data. The grid field data includes data describing the values ​​of field factors within the grid area, such as temperature, humidity, air pressure, etc. These data reflect the distribution of various factors in the field; the grid simulation data includes data obtained by simulation calculation, such as air flow velocity, concentration, pressure, etc. These data reflect the calculation results of various factors in the simulation process.

[0049] The extracted adjacent grid data are proofread and verified to ensure the accuracy and completeness of the data and exclude possible abnormal values. The field data and simulation data are analyzed for change. The field data change refers to the trend and change of the field factor value with spatial change, and the simulation data change refers to the trend and change of the simulation calculation results with spatial change. By analyzing the change of data, the change trend of the field factor value and the simulation calculation results between different grid areas can be determined.

[0050] Based on the changes in field data and simulation data, the grid trend change analysis is carried out, including determining the changing trends of adjacent grid data in field factor values ​​and simulation calculation results, and comparing the increase and decrease of data; analyzing the reasons for data changes at the grid boundaries to determine whether they are caused by field trend changes or changes in the simulation calculation process; determining the regularity of grid trend changes, including the consistency and inconsistency of data changes within the grid.

[0051] According to the results of the flow analysis, the flow characteristics are determined, including the trend, change law, mutation point and other characteristics of data change at the grid boundary. The flow characteristics reflect the changes in the field factor values ​​and simulation calculation results of the adjacent grid data.

[0052] The scene simulation switching module 50 is used to use the distribution of characteristic values ​​of field factors as the first control target and the self-characteristics of bioaerosols as the second control target. Based on the adaptive simulation module, the visual simulation scene is subjected to scene simulation switching and analysis to determine the second scene simulation data.

[0053] The first control target is the distribution of characteristic values ​​of field factors. This target refers to the spatial distribution of various factors in the control simulation scene. For example, the distribution of factors such as temperature, humidity, and air flow velocity can be adjusted to explore their impact on the diffusion behavior of bioaerosols. The adaptive simulation module is used to adjust the values ​​of these factors in real time during the simulation process to observe changes in simulation results. For example, the temperature gradient or humidity difference can be adjusted to simulate the aerosol diffusion in different seasons or under different environmental conditions.

[0054] The second control target is the self-characteristics of bioaerosols. This target refers to regulating the characteristics of bioaerosol particles themselves, such as concentration and phase. Phase states include solid, liquid, and gas. By regulating these characteristics, the diffusion behavior of bioaerosols of different types or concentrations in different environments can be simulated. In the adaptive simulation module, the initial conditions and characteristic parameters of bioaerosols are set, such as the initial distribution, size, and density of particles. Then, the simulation results are observed to analyze the changes in the diffusion behavior of bioaerosols.

[0055] An adaptive simulation module is used to switch between different simulation scenarios. That is, different simulation conditions and parameters are switched according to the settings of the first control target and the second control target. In each simulation scenario, the diffusion, concentration distribution, phase change and other data of bioaerosols are collected and analyzed to obtain the simulation data of the second scenario.

[0056] The simulation result determination module 60 is used to determine a scenario simulation result based on the first scenario simulation data and the second scenario simulation data.

[0057] The simulation data of the first scenario and the simulation data of the second scenario are compared, including comparison of concentration distribution, comparison of particle diffusion rate, analysis of phase change, etc. Through comparative analysis, the differences and characteristics of the diffusion behavior of bioaerosols under different simulation conditions are determined. Based on the results of comparative analysis, the scenario simulation results are determined. For example, it is determined under which simulation conditions the diffusion range of bioaerosols is wider, under which simulation conditions the particle concentration changes more significantly, or which environmental conditions have a greater impact on the diffusion rate of bioaerosols.

[0058] Furthermore, the system further includes a steady-state scene analysis module to perform the following operation steps:

[0059] If the scene simulation task is a steady-state scene, the scene self-motion simulation of bioaerosols is performed based on the visual simulation scene to determine the first scene simulation data; if the scene simulation task is a dynamic scene, the time zone evolution data of the fitting field is determined based on the scene trend characteristics; based on the time zone evolution data, the dynamic control and motion simulation of the visual simulation scene are performed based on the adaptive simulation module to determine the second scene simulation data.

[0060] When the scene simulation task is a steady-state scene, determine the simulated steady-state scene, including the settings of environmental factors such as temperature, humidity, air flow velocity, etc. In the visual simulation scene, set the self-motion simulation of the bioaerosol particles, including the initial position, velocity, and direction of movement of the particles. These parameters can be set according to the physical properties and environmental conditions of the bioaerosols. Run the self-motion simulation to obtain the motion trajectory and diffusion of the bioaerosol particles in the simulated scene. During the simulation, collect the motion data of the bioaerosols, including the position coordinates, velocity, diffusion range, and other information of the particles, and determine the simulation data of the first scene.

[0061] When the scene simulation task is a dynamic scene, determine the trend characteristics in the dynamic scene, that is, the characteristics of the scene changing over time, including changes in environmental factors such as temperature, humidity, and airflow velocity, as well as the changing trends of bioaerosol concentration and particle movement direction over time. According to the scene trend characteristics, the data of the fitting field is evolved in time zone to determine the time zone evolution data of the fitting field. These data include the distribution of field factor characteristic values ​​at different times, bioaerosol concentration distribution, particle movement trajectory, etc., reflecting the evolution characteristics under the dynamic scene.

[0062] The collected time zone evolution data are imported into the adaptive simulation module. Based on the time zone evolution data, the parameters and conditions of dynamic control are set. The adaptive simulation module is used to simulate the movement of bioaerosols. According to the settings of dynamic control, the movement trajectory and concentration distribution of particles at different time points are simulated. During the simulation process, the simulation parameters can be adjusted according to real-time data to adapt to the dynamic changes of the scene. During the simulation process, the movement of bioaerosols and changes in the scene are monitored in real time. Based on the results of dynamic control and motion simulation, the simulation data of the second scene are determined. These data include bioaerosol concentration distribution, particle movement trajectory, phase change, etc. in dynamic scenes, which reflect the characteristics of bioaerosol propagation behavior in dynamic scenes.

[0063] Furthermore, the simulation result determination module 60 further includes executing the following operation steps:

[0064] After determining the scenario simulation results, the scenario prevention and control strategy is determined based on the scenario simulation results, and a simulation verification of the scenario prevention and control strategy is performed based on the adaptive simulation module.

[0065] After determining the scenario simulation results, a scenario prevention and control strategy is formulated based on the scenario simulation results, including measures to control the spread of bioaerosols, such as increased ventilation, air filtration, disinfection, etc., as well as prevention and control strategies for specific environments or scenarios, such as office spaces.

[0066] In the adaptive simulation module, the simulation verification parameters of the scenario prevention and control strategy are set, including simulation of bioaerosol diffusion and concentration distribution changes under different prevention and control strategies, to evaluate the prevention and control effect, run simulation verification, monitor the simulation results under different prevention and control strategies, and compare the bioaerosol diffusion, concentration distribution, diffusion rate and other indicators of different strategies to evaluate the effectiveness of prevention and control. Analyze the simulation verification results, evaluate the effectiveness and practicality of various prevention and control strategies, and adjust and optimize the prevention and control strategies according to the simulation results to improve the prevention and control effect.

[0067] In summary, the artificial intelligence-based bioaerosol scene simulation system provided in the embodiments of the present application has the following technical effects:

[0068] 1. By determining the biological particle class of bioaerosol, conducting inter-class interaction analysis and intra-class multiphase flow motion analysis, and establishing multiphase flow motion constraint relationships, the simulation and analysis of the dynamic behavior of complex bioaerosols are realized, making the simulation closer to the real situation and improving the credibility of the simulation results;

[0069] 2. Based on the factors affecting the movement of bioaerosols, a fitting field is generated according to the simulation scenario factors based on multiple factor fields, which realizes the comprehensive modeling of the factors affecting the movement, making the simulation process more precise and improving the accuracy of the simulation results;

[0070] 3. By building a visual simulation scene and placing it in an adaptive simulation module, the visual display and dynamic regulation of the simulation scene are realized, making the simulation results more intuitive and real-time, and improving the interactivity and operability of the simulation process;

[0071] 4. Determine the first scenario simulation data through the analysis of motion diffusion behavior based on fluid mechanics, which helps to understand the propagation characteristics of bioaerosols in the air;

[0072] 5. By taking the characteristic value distribution of field factors as the first control target and the self-characteristics of bioaerosols as the second control target, the scene simulation switching and analysis are carried out to determine the simulation data of the second scene, so as to achieve effective simulation of field factors and self-characteristics of bioaerosols, making the simulation results more flexible and controllable, and meeting the simulation requirements under different demand scenarios;

[0073] 6. The scenario simulation results are determined based on the first scenario simulation data and the second scenario simulation data, thereby achieving a comprehensive analysis of the scenario simulation results.

[0074] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The artificial intelligence-based bioaerosol scene simulation system is characterized by: The system comprises: A constraint relationship determination module, the constraint relationship determination module is used to determine the biological particle class of the bioaerosol, perform inter-class interaction analysis and intra-class multiphase flow motion analysis, and determine motion constraint relationships, wherein the multiphase flow motion is a mixed motion of at least two phases; A fitting field construction module, the fitting field construction module is used to construct a fitting field based on a simulation scene based on the movement influencing factors of the bioaerosol, the fitting field is generated based on multiple factor fields according to the simulation scene factors, and the fitting field can be switched based on the simulation scene; A simulation scene building module, wherein the simulation scene building module is used to build a visual simulation scene based on the motion constraint relationship and the fitting field, and the visual simulation scene is placed in an adaptive simulation module; A diffusion behavior analysis module, wherein the diffusion behavior analysis module is used to perform a fluid mechanics-based motion diffusion behavior analysis on the bioaerosol based on the visual simulation scene to determine first scene simulation data; A scene simulation switching module, wherein the scene simulation switching module is used to take the characteristic value distribution of field factors as the first control target and the self-characteristics of bioaerosols as the second control target, and based on the adaptive simulation module, perform scene simulation switching and analysis on the visual simulation scene to determine the second scene simulation data; A simulation result determination module, the simulation result determination module is used to determine a scenario simulation result based on the first scenario simulation data and the second scenario simulation data; The constraint relationship determination module includes executing the following steps: Traversing the biological particle classes, performing mutual influence analysis on any at least two classes, and determining a first motion constraint relationship, wherein the mutual influence analysis is determined based on the motion difference between a single class and multiple classes in coordination; For each biological particle type, a motion impact analysis based on phase flow difference is performed to determine the second motion constraint relationship, wherein the motion difference based on the coordination of single-phase flow and multi-phase flow is determined; Determining the motion constraint relationship based on the first motion constraint relationship and the second motion constraint relationship; The fitting field construction module includes the following steps: Determine the simulated space field distribution, traverse the motion influencing factors, and determine multiple factor fields, wherein the field point of the factor field is represented by (x, y, z, f), and f is the field factor value; Based on the simulation scenario, determining a scenario factor class and a scenario factor value distribution, wherein the scenario factor class is an environmental factor; Based on the scene factor class, the multiple factor fields are matched and field space mapped, the field distribution of the scene factor value distribution is fitted and restored, and the fitting field is determined.

2. The system according to claim 1, characterized in that The fitting field construction module also includes executing the following operation steps: A human motion behavior of the simulated scene is determined, and based on the human motion behavior, a compensation adjustment is performed on the fitting field.

3. The system according to claim 1, characterized in that The diffusion behavior analysis module further includes executing the following operation steps: After determining the first scene simulation data, the visual simulation scene is identified, field grid segmentation is performed based on a preset difference, and a grid segmentation result is determined, wherein the segmentation standard is non-uniform grid segmentation based on fitting field distribution differences; Based on the grid division result, the first scenario simulation data is divided and analyzed across grid transitions to determine flow characteristics.

4. The system according to claim 3, characterized in that The diffusion behavior analysis module further includes executing the following operation steps: Obtain the grid division results and extract the adjacent grid data. The data dimensions include grid field data and grid simulation data. The adjacent grid data are checked, and based on the field data change and the simulation data change, a flow analysis based on the grid trend change is performed to determine the flow characteristics.

5. The system according to claim 1, wherein: The system also includes a steady-state scene analysis module to perform the following operation steps: If the scene simulation task is a steady-state scene, performing scene self-motion simulation of bioaerosols based on the visual simulation scene to determine the first scene simulation data; If the scene simulation task is a dynamic scene, based on the scene trend characteristics, determine the time zone evolution data of the fitting field; Based on the time zone evolution data, dynamic control and motion simulation of the visual simulation scene are performed based on the adaptive simulation module to determine the second scene simulation data.

6. The system according to claim 1, characterized in that The simulation result determination module further includes executing the following operation steps: After determining the scenario simulation results, the scenario prevention and control strategy is determined based on the scenario simulation results, and a simulation verification of the scenario prevention and control strategy is performed based on the adaptive simulation module.

Images