Self-cleaning method based on airflow field reconstruction and particle track intervention

Abstract

The invention relates to the technical field of self-cleaning, and discloses a self-cleaning method based on airflow field reconstruction and particle track intervention. The method comprises the steps of collecting airflow and particle state parameters of a target space in real time, dynamically constructing and updating an airflow field model and a particle field model, predicting a target particle track based on the particle field model, calculating a risk coefficient of the target particle track relative to a sensitive area, and generating a regulation and control scheme containing parameters such as an airflow direction and a wind speed interval when the risk coefficient exceeds a preset threshold value. A guide airflow field is generated through the airflow regulation and control device and superposed with an original airflow field to form a reconstructed airflow field, and particles are guided to deviate from a sensitive area and converge to a collection area to complete capture. According to the method, accurate track intervention and efficient capturing of particles are achieved, sensitive areas are effectively protected, and self-cleaning pertinence and reliability are improved.

Description

Technical Field

[0001] This invention relates to a self-cleaning method based on airflow field reconstruction and particle trajectory intervention, belonging to the field of self-cleaning technology. Background Technology

[0002] In environments with stringent cleanliness requirements, such as electronics manufacturing, precision laboratories, and high-end equipment rooms, sensitive areas (e.g., core components of precision instruments, experimental sample storage areas) are susceptible to contamination by suspended particulate matter. Existing self-cleaning technologies struggle to meet the dual demands of precise protection and efficient particle capture. Traditional methods often rely on passive filtration or general ventilation. Passive filtration can only intercept particles flowing through the filter, failing to intervene in the movement trajectory of free particles and thus hindering their diffusion into sensitive areas. General ventilation lacks specificity, easily creating dead zones and failing to dynamically adjust airflow based on real-time particle distribution. Furthermore, existing technologies lack a mechanism for predicting particle trajectories, only addressing issues when particles contact sensitive areas or filters, resulting in significant lag in protection. Airflow control schemes often use fixed parameters, failing to dynamically optimize based on real-time airflow distribution, particle movement characteristics, and the protection needs of sensitive areas. This leads to low particle capture efficiency, leaving sensitive areas still at high risk of contamination, highlighting the technical challenge of balancing precise protection with efficient cleaning. Summary of the Invention

[0003] This invention provides a self-cleaning method based on airflow field reconstruction and particle trajectory intervention, which solves the problem that existing self-cleaning technologies are unable to accurately intervene in particle movement trajectories and efficiently capture them by combining real-time particle status with the protection requirements of sensitive areas, leading to the susceptibility of sensitive areas to contamination. The technical solution adopted is as follows: A self-cleaning method based on airflow field reconstruction and particle trajectory intervention includes the following steps: Real-time acquisition of airflow parameters and particle state parameters within the target space; dynamic construction and updating of the airflow field model of the target space based on the airflow parameters; dynamic construction and updating of the particle field model of the target space based on the particle state parameters; the particle field model includes information on the position, velocity, and motion trend of the particles. Based on the particle field model, a trajectory prediction algorithm is used to predict the trajectory of the target particle in advance. Combined with the spatial range of the preset sensitive area and the protection requirements, the risk coefficient of the target particle relative to the sensitive area is calculated. If the risk coefficient exceeds the preset threshold, an airflow field control scheme containing airflow direction, wind speed range, area of ​​effect, and time sequence is generated based on real-time airflow distribution, particle prediction trajectory, and sensitive area protection requirements. Based on the airflow field control scheme, a guiding airflow field is actively generated by the airflow control device, and the guiding airflow field is superimposed with the original airflow field of the target space to form a reconstructed airflow field. By continuously applying guiding force through the reconstructed airflow field, the target particles are guided to the preset collection area and captured.

[0004] Furthermore, the dynamic updating of the airflow field model and the particle field model is adaptively corrected based on the real-time parameter acquisition, specifically including: After each round of airflow and particle state parameter acquisition, the newly acquired parameter data is compared with the current parameter configuration of the model to extract parameter difference information. Based on the difference information, the model adaptive correction process is initiated. During the correction process, the coupling relationship between the airflow field model and the particle field model is associated to keep the model parameter adjustment synchronized with the actual state changes of airflow and particles in the target space.

[0005] Furthermore, the particle field model integrates the physical property information of the particles, specifically including: During the process of collecting particle state parameters, the physical property information of the particles is acquired simultaneously, and the physical property information is associated and mapped with the position, velocity and motion trend information of the particles according to a preset data format. A particle field model is constructed, and the integrated related data is embedded into the model structure according to preset dimensions to form a model data system containing multi-dimensional particle information.

[0006] Furthermore, the calculation of the risk coefficient, combining the spatial and temporal correlation between particles and sensitive areas, as well as the influence weight of particles on sensitive areas, satisfies the following formula: ), in: For risk coefficient, The spatial correlation degree is obtained by analyzing the geometric relationship between the predicted trajectory of particles and the spatial boundary of the sensitive area. The temporal correlation degree is determined based on the estimated time it takes for a particle to move to the boundary of the sensitive area according to its predicted trajectory. The influencing weights are obtained through matching analysis of the particle physical properties and the protection requirements of sensitive areas; The allocation coefficients for each associated item are determined based on the correlation analysis between the protection priority of sensitive areas and each associated item. The calculation process is initiated after the trajectory prediction algorithm outputs the trajectory of the target particle.

[0007] Furthermore, the preset threshold is dynamically adjusted based on the protection level of the sensitive area, specifically including: Establish a mapping relationship between the protection level of sensitive areas and preset thresholds in advance, and monitor the protection level status of sensitive areas in real time; When the protection level changes, the information of the changed protection level is extracted, the corresponding threshold adjustment range is determined based on the preset mapping relationship, the value of the preset threshold is updated according to the adjustment range, and the benchmark parameters for risk coefficient judgment are updated synchronously.

[0008] Furthermore, the construction of the airflow field model and the particle field model involves multi-source data fusion processing of the collected airflow parameters and particle state parameters.

[0009] Furthermore, in the aforementioned airflow field control scheme, the boundary of the airflow action area is determined based on the envelope range of the predicted particle trajectory, specifically including: The trajectory prediction algorithm outputs multiple possible motion trajectories of the target particle, and extracts the endpoint coordinates and critical path point coordinates of each trajectory. The envelope range of the predicted trajectory of the particles is obtained by fitting the coordinates of the key path points. The boundary of the envelope range is expanded according to the preset rules. The expanded boundary is the boundary of the airflow action area. The boundary determination process is carried out simultaneously with the generation of other parameters of the airflow field control scheme to ensure that the action area covers the key path segments of particle movement.

[0010] Furthermore, a correction coefficient is introduced during the dynamic update process of the model, satisfying the formula: in: These are the model correction coefficients. This refers to the deviation between the model's predicted values ​​and the actual collected values. As the model baseline value, This is the deviation adjustment factor.

[0011] Secondly, the present invention also provides a self-cleaning system based on airflow field reconstruction and particle trajectory intervention, used in the self-cleaning method based on airflow field reconstruction and particle trajectory intervention, comprising: Parameter acquisition module: configured to acquire airflow parameters and particle state parameters within the target space; Model building module: configured to build and update airflow field model and particle field model based on collected parameters; Trajectory prediction and risk assessment module: configured to predict the trajectory of target particles in advance and calculate the risk coefficient relative to the sensitive area; Control scheme generation module: Configured to generate an airflow field control scheme containing airflow direction, wind speed range, area of ​​effect, and time sequence when the risk coefficient exceeds the threshold; Airflow control module: includes airflow control device, configured to generate a guiding airflow field and form a reconstructed airflow field based on the control scheme; Particle collection module: Located in a preset collection area, configured to capture the converged target particles; Feedback adjustment module: Configured to adjust the airflow field control scheme based on monitoring data.

[0012] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the self-cleaning method based on airflow field reconstruction and particle trajectory intervention as described in any one of the claims.

[0013] Beneficial effects of this invention: This invention provides a self-cleaning method based on airflow field reconstruction and particle trajectory intervention. Firstly, by real-time acquisition of airflow and particle state parameters and dynamic updating of the dual-field model, it achieves precise adaptation to the physical state of the target space. Combined with advanced particle trajectory prediction and risk coefficient assessment, it overcomes the limitations of traditional technology's lagging protection and proactively identifies the risk of particles spreading to sensitive areas. Secondly, based on real-time airflow distribution, particle motion characteristics, and the protection requirements of sensitive areas, it dynamically generates airflow field control schemes. By directionally guiding airflow and superimposing it with the original airflow field to form a reconstructed airflow field, it achieves precise intervention in particle motion trajectories, avoiding the airflow dead zones and interference issues present in traditional overall ventilation. The system addresses several key issues: First, it avoids blind spots in airflow. Second, by reconstructing the airflow field and continuously applying guiding forces, it forces particles to deviate from sensitive areas and converge into pre-set collection areas, thus blocking the contamination path of particles to sensitive areas at the source and significantly improving the cleanliness and protection effect of sensitive areas. Third, the airflow field control scheme can be dynamically adjusted according to the real-time status of particles and changes in the spatial environment, adapting to the characteristics of particles and protection needs in different scenarios, enhancing the versatility and adaptability of self-cleaning technology. Fourth, it eliminates the need to rely on large-area passive filtration or high-intensity overall ventilation, improving particle cleaning efficiency through precise control and directional capture, reducing energy consumption while ensuring cleanliness, and achieving a balance between protection precision and cleaning economy. Attached Figure Description

[0014] Figure 1 A flowchart of a self-cleaning method based on airflow field reconstruction and particle trajectory intervention provided in one embodiment of the present invention; Figure 2 A block diagram of a self-cleaning system based on airflow field reconstruction and particle trajectory intervention, provided as one embodiment of the present invention. Detailed Implementation

[0015] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0016] refer to Figure 1 The self-cleaning method based on airflow field reconstruction and particle trajectory intervention proposed in this embodiment of the invention includes the following steps: S1. Real-time acquisition of airflow parameters and particle state parameters in the target space; dynamic construction and updating of the airflow field model of the target space based on the airflow parameters; dynamic construction and updating of the particle field model of the target space based on the particle state parameters; the particle field model includes information on the position, velocity and motion trend of the particles. S2. Based on the particle field model, a trajectory prediction algorithm is used to predict the trajectory of the target particle in advance. Combined with the spatial range of the preset sensitive area and the protection requirements, the risk coefficient of the target particle relative to the sensitive area is calculated. S3. If the risk coefficient exceeds the preset threshold, an airflow field control scheme containing airflow direction, wind speed range, area of ​​action, and time sequence is generated based on real-time airflow distribution, particle prediction trajectory, and sensitive area protection requirements. S4. Based on the airflow field control scheme, a guiding airflow field is actively generated by the airflow control device, and the guiding airflow field is superimposed with the original airflow field of the target space to form a reconstructed airflow field. S5. By continuously applying a guiding force through the reconstructed airflow field, the target particles are guided to the preset collection area and captured.

[0017] It should be noted that, in some embodiments, in the electronic laboratory scenario, a sensor array deployed in the space collects the flow state parameters of the airflow and the state parameters of suspended particles in real time. The airflow parameters are input into the fluid dynamics model framework to construct an initial airflow field model, and the position, velocity, and motion trend data of the particles are input into the particle motion model to construct an initial particle field model. The model receives new collected parameters at fixed intervals for dynamic updates. Based on the particle motion data output by the particle field model, a trajectory prediction algorithm is called to calculate the particle motion trajectory for a future period of time. Combined with the spatial coordinates and protection requirements of the sensitive area where the precision instrument is located, the risk coefficient of the trajectory and the sensitive area is calculated. When the risk coefficient exceeds a set value, the system retrieves real-time airflow distribution data, predicted trajectory paths, and sensitive area protection parameters to generate an airflow field control scheme that includes airflow guidance angle, wind speed range, coverage area, and activation sequence. After receiving the scheme, the airflow control device generates guiding airflow through array-type jet nozzles and adjustable-speed fans. This airflow is superimposed with the original airflow in the space to form a reconstructed airflow field. The reconstructed airflow field applies a continuous guiding force to the particles, pushing them away from the sensitive area until the particles are captured by the collection area set at the confluence of airflow in the space.

[0018] Preferably, the dynamic updating of the airflow field model and the particle field model is adaptively corrected based on the real-time nature of parameter acquisition, specifically including: After each round of airflow and particle state parameter acquisition, the newly acquired parameter data is compared with the current parameter configuration of the model to extract parameter difference information. Based on the difference information, the model adaptive correction process is initiated. During the correction process, the coupling relationship between the airflow field model and the particle field model is associated to keep the model parameter adjustment synchronized with the actual state changes of airflow and particles in the target space.

[0019] It should be noted that, in some embodiments, during the dynamic model update process, after the sensor array completes each round of airflow parameters and particle state parameters acquisition, the new data is transmitted to the data processing unit. The data processing unit compares the newly acquired parameters with the parameter configurations in the current airflow field model and particle field model point by point, extracting the numerical differences and trend information between the two. Based on this difference information, an adaptive correction process is initiated. During correction, the influence of airflow field changes on particle motion is first analyzed, and then the corresponding parameters of the particle field model are adjusted accordingly. At the same time, the local parameters of the airflow field model are calibrated in reverse according to the changes in particle motion state, ensuring that the coupling relationship between the airflow field model and the particle field model conforms to the actual space physics laws, so that the model parameter adjustment is synchronized with the real-time state changes of airflow and particles.

[0020] Furthermore, the particle field model integrates the physical property information of the particles, specifically including: During the process of collecting particle state parameters, the physical property information of the particles is acquired simultaneously, and the physical property information is associated and mapped with the position, velocity and motion trend information of the particles according to a preset data format. A particle field model is constructed, and the integrated related data is embedded into the model structure according to preset dimensions to form a model data system containing multi-dimensional particle information.

[0021] It should be noted that, in some embodiments, during the process of collecting particle state parameters, the particle analysis sensor simultaneously acquires physical characteristic information such as particle size, density, and charge properties. After standardizing this information according to a preset data format, a one-to-one correlation mapping relationship is established with the particle's position coordinates, velocity vector, and motion trend data to form a unified particle data set. When constructing the particle field model, the integrated correlation data is embedded into the corresponding data layer of the model according to three dimensions: physical characteristic type, spatial location, and motion state, forming a model data system containing multi-dimensional particle information. When the model calls the data, the corresponding complete particle data can be extracted through any dimension index.

[0022] Preferably, the calculation of the risk coefficient, combining the spatial and temporal correlation between the particles and the sensitive area, as well as the influence weight of the particles on the sensitive area, satisfies the following formula: ), in: For risk coefficient, The spatial correlation degree is obtained by analyzing the geometric relationship between the predicted trajectory of particles and the spatial boundary of the sensitive area. The temporal correlation degree is determined based on the estimated time it takes for a particle to move to the boundary of the sensitive area according to its predicted trajectory. The influencing weights are obtained through matching analysis of the particle physical properties and the protection requirements of sensitive areas; The allocation coefficients for each associated item are determined based on the correlation analysis between the protection priority of sensitive areas and each associated item. The calculation process is initiated after the trajectory prediction algorithm outputs the trajectory of the target particle.

[0023] It should be noted that, in some embodiments, when calculating the risk coefficient, firstly, based on the coordinate data of the predicted trajectory of the particle and the spatial boundary coordinates of the sensitive area, the overlapping area ratio of the two is calculated using a geometric relationship analysis method to obtain the spatial correlation degree S; then, based on the current movement speed of the particle and the predicted trajectory length, the estimated time for the particle to move to the boundary of the sensitive area is calculated, and the time is converted into a time correlation degree T according to a preset rule; by comparing the degree of adaptation between the physical characteristics of the particle and the protection requirements of the sensitive area, the influence weight W of the particle on the sensitive area is determined; based on the protection priority of the sensitive area, the allocation coefficient is determined using the analytic hierarchy process (AHP). The risk coefficient R is obtained by multiplying S, T, and W by their respective coefficients and summing the results. This calculation process is initiated immediately after the trajectory prediction algorithm outputs the results to ensure the real-time nature of the risk assessment.

[0024] Preferably, the preset threshold is dynamically adjusted based on the protection level of the sensitive area, specifically including: Establish a mapping relationship between the protection level of sensitive areas and preset thresholds in advance, and monitor the protection level status of sensitive areas in real time; When the protection level changes, the information of the changed protection level is extracted, the corresponding threshold adjustment range is determined based on the preset mapping relationship, the value of the preset threshold is updated according to the adjustment range, and the benchmark parameters for risk coefficient judgment are updated synchronously.

[0025] It should be noted that in some embodiments, multiple protection levels are pre-defined based on the protection requirements of sensitive areas. For each level, the corresponding risk coefficient threshold is determined through experimental testing. A mapping relationship table between protection levels and thresholds is established and stored in the system. The status monitoring module set up in the sensitive area monitors the protection level status in real time. When a change in protection level is detected, the system extracts the changed protection level information, queries the mapping relationship table to determine the corresponding threshold adjustment range, updates the current preset threshold value according to the adjustment range, and synchronizes the updated threshold to the risk coefficient judgment unit as a benchmark parameter for subsequent risk assessment, ensuring that the threshold adjustment is consistent with the change in protection level.

[0026] Furthermore, the construction of the airflow field model and the particle field model involves multi-source data fusion processing of the collected airflow parameters and particle state parameters.

[0027] It should be noted that, in some embodiments, before constructing the airflow field model and the particle field model, the collected airflow parameters and particle state parameters undergo multi-source data fusion processing: first, the collected data from different devices such as wind speed sensors, air pressure sensors, and particle counters are preprocessed to filter outliers and noise data; then, based on the measurement accuracy and reliability of each sensor, corresponding confidence weights are assigned to the data from different sources; the DS evidence theory is used to synthesize the weighted multi-source data to obtain a unified and stable parameter dataset; the fused dataset is then input into the corresponding model framework to complete the construction of the airflow field model and the particle field model, ensuring the accuracy of the model input data.

[0028] Preferably, in the airflow field control scheme, the boundary of the airflow action area is determined based on the envelope range of the predicted particle trajectory, specifically including: The trajectory prediction algorithm outputs multiple possible motion trajectories of the target particle, and extracts the endpoint coordinates and critical path point coordinates of each trajectory. The envelope range of the predicted trajectory of the particles is obtained by fitting the coordinates of the key path points. The boundary of the envelope range is expanded according to the preset rules. The expanded boundary is the boundary of the airflow action area. The boundary determination process is carried out simultaneously with the generation of other parameters of the airflow field control scheme to ensure that the action area covers the key path segments of particle movement.

[0029] It should be noted that, in some embodiments, when generating the airflow field control scheme, the trajectory prediction algorithm simultaneously outputs 10 possible motion trajectories of the target particles, extracts the starting point coordinates, ending point coordinates, and intermediate critical path point coordinates of each trajectory, and summarizes all coordinate points to form a trajectory point set; a polynomial fitting method is used to perform curve fitting on the trajectory point set to obtain the envelope range curve of the particle's predicted trajectory; the boundary of the envelope range curve is expanded according to a preset expansion ratio (set based on the characteristics of the spatial environment), and the area enclosed by the expanded curve is the boundary of the airflow action area; the boundary determination process is carried out simultaneously with the generation of other control parameters such as airflow direction and wind speed range to ensure that the action area can completely cover the critical path segment of particle motion.

[0030] Preferably, a correction coefficient is introduced during the dynamic update process of the model, satisfying the formula: in: These are the model correction coefficients. This refers to the deviation between the model's predicted values ​​and the actual collected values. As the model baseline value, This is the deviation adjustment factor.

[0031] It should be noted that, in some embodiments, during the dynamic model update process, the predicted value output by the current model (predicted airflow parameters or predicted particle state) is first extracted, and the difference between this value and the actual value collected by the sensor during the same period is calculated to obtain the deviation. Set the calibration parameter values ​​used during model initialization as the model baseline values. ;Preset the deviation adjustment factor k according to the environmental characteristics of the target space (such as space size and airflow stability);According to the formula Calculate the model correction coefficients ; Adjust the coefficient Substitute the parameters into the model parameter adjustment formula to perform linear correction on the corresponding parameters of the airflow field model and the particle field model. Each time a round of parameter acquisition and model update is completed, the correction coefficient is calculated and the parameters are adjusted once.

[0032] refer to Figure 2 The present invention also provides an embodiment of a self-cleaning system based on airflow field reconstruction and particle trajectory intervention, used in the self-cleaning method based on airflow field reconstruction and particle trajectory intervention, comprising: Parameter acquisition module: configured to acquire airflow parameters and particle state parameters within the target space; Model building module: configured to build and update airflow field model and particle field model based on collected parameters; Trajectory prediction and risk assessment module: configured to predict the trajectory of target particles in advance and calculate the risk coefficient relative to the sensitive area; Control scheme generation module: Configured to generate an airflow field control scheme containing airflow direction, wind speed range, area of ​​effect, and time sequence when the risk coefficient exceeds the threshold; Airflow control module: includes airflow control device, configured to generate a guiding airflow field and form a reconstructed airflow field based on the control scheme; Particle collection module: Located in a preset collection area, configured to capture the converged target particles; Feedback adjustment module: Configured to adjust the airflow field control scheme based on monitoring data.

[0033] Thirdly, the present invention also provides an embodiment of a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements any of the self-cleaning methods based on airflow field reconstruction and particle trajectory intervention.

[0034] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROM, floppy disk, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDRRAM, SRAM, EDORAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which a program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0035] This embodiment provides a clear and feasible execution path for the self-cleaning method through specific parameter acquisition layout, dual-field model construction logic, trajectory prediction and risk assessment process, airflow control scheme generation method, and system module collaboration mechanism. It comprehensively collects airflow and particle parameters through a sensor array, and combines multi-source data fusion processing and model coupling correction to ensure that the dual-field model can accurately reflect the actual space conditions, providing reliable data support for subsequent intervention. The risk coefficient is calculated using multi-dimensional correlation terms and weighted, combined with dynamic threshold adjustment based on protection level, to achieve accurate judgment of particle pollution risk and avoid misjudgment or omission. The airflow action area is determined by fitting and expanding the trajectory envelope range. The control scheme integrates key parameters such as direction, wind speed, and time sequence, and works in conjunction with the collaborative work of distributed airflow control devices to achieve directional and precise intervention on particle trajectories, effectively avoiding airflow dead zones. During the model update process, dynamic calibration of correction coefficients is introduced, combined with real-time data feedback from the feedback adjustment module, so that the scheme can adapt to changes in the space environment and particle state. The various modules of the system are linked in an orderly manner according to preset logic, and the program code pre-stored in the storage medium ensures that the method can be quickly deployed and executed. This not only ensures the stability and continuity of the self-cleaning process, but also adapts to the protection needs of different scenarios such as electronic laboratories and precision machine rooms, providing comprehensive and targeted clean protection support for sensitive areas.

[0036] Of course, the computer-executable instructions provided in this application embodiment are not limited to the self-cleaning method based on airflow field reconstruction and particle trajectory intervention as described above. They can also execute related operations in the self-cleaning method based on airflow field reconstruction and particle trajectory intervention provided in any embodiment of this application. Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations of this invention fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A self-cleaning method based on airflow field reconstruction and particle trajectory intervention, characterized in that, Includes the following steps: Real-time acquisition of airflow parameters and particle state parameters within the target space; dynamic construction and updating of the airflow field model of the target space based on the airflow parameters; dynamic construction and updating of the particle field model of the target space based on the particle state parameters; the particle field model includes information on the position, velocity, and motion trend of the particles. Based on the particle field model, a trajectory prediction algorithm is used to predict the trajectory of the target particles in advance. Combined with the spatial range of the preset sensitive area and the protection requirements, the risk coefficient of the target particles relative to the sensitive area is calculated. If the risk coefficient exceeds the preset threshold, an airflow field control scheme containing airflow direction, wind speed range, area of ​​effect, and time sequence is generated based on real-time airflow distribution, particle prediction trajectory, and sensitive area protection requirements. Based on the airflow field control scheme, a guiding airflow field is actively generated by the airflow control device, and the guiding airflow field is superimposed with the original airflow field of the target space to form a reconstructed airflow field. By continuously applying guiding force through the reconstructed airflow field, the target particles are guided to the preset collection area and captured.

2. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The dynamic updating of the airflow field model and the particle field model is based on real-time parameter acquisition and adaptive correction, specifically including: After each round of airflow and particle state parameter acquisition is completed, the newly acquired parameter data is compared with the current parameter configuration of the model to extract parameter difference information. Based on the difference information, the model adaptive correction process is initiated. During the correction process, the coupling relationship between the airflow field model and the particle field model is associated to keep the model parameter adjustment synchronized with the actual state changes of airflow and particles in the target space.

3. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The particle field model integrates the physical property information of particles, specifically including: During the process of collecting particle state parameters, the physical property information of the particles is acquired simultaneously, and the physical property information is associated and mapped with the position, velocity and motion trend information of the particles according to a preset data format. A particle field model is constructed, and the integrated related data is embedded into the model structure according to preset dimensions to form a model data system containing multi-dimensional particle information.

4. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The calculation of the risk coefficient, combining the spatial and temporal correlation between particles and sensitive areas, as well as the influence weight of particles on sensitive areas, satisfies the following formula: ), in: For risk coefficient, The spatial correlation degree is obtained by analyzing the geometric relationship between the predicted trajectory of particles and the spatial boundary of the sensitive area. The temporal correlation degree is determined based on the estimated time it takes for a particle to move to the boundary of the sensitive area according to its predicted trajectory. The influencing weights are obtained through matching analysis of the particle physical properties and the protection requirements of sensitive areas; The allocation coefficients for each associated item are determined based on the correlation analysis between the protection priority of sensitive areas and each associated item. The calculation process is initiated after the trajectory prediction algorithm outputs the trajectory of the target particle.

5. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The preset threshold is dynamically adjusted based on the protection level of the sensitive area, specifically including: Establish a mapping relationship between the protection level of sensitive areas and preset thresholds in advance, and monitor the protection level status of sensitive areas in real time; When the protection level changes, the information of the changed protection level is extracted, the corresponding threshold adjustment range is determined based on the preset mapping relationship, the value of the preset threshold is updated according to the adjustment range, and the benchmark parameters for risk coefficient judgment are updated synchronously.

6. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The construction of the airflow field model and the particle field model involves multi-source data fusion processing of the collected airflow parameters and particle state parameters.

7. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, In the aforementioned airflow field control scheme, the boundary of the airflow action area is determined based on the envelope range of the predicted particle trajectory, specifically including: The trajectory prediction algorithm outputs multiple possible motion trajectories of the target particle, and extracts the endpoint coordinates and critical path point coordinates of each trajectory. The envelope range of the predicted trajectory of the particles is obtained by fitting the coordinates of the key path points. The boundary of the envelope range is expanded according to the preset rules. The expanded boundary is the boundary of the airflow action area. The boundary determination process is carried out simultaneously with the generation of other parameters of the airflow field control scheme to ensure that the action area covers the key path segments of particle movement.

8. The self-cleaning method based on airflow field reconstruction and particle trajectory intervention according to claim 1, characterized in that, The model is dynamically updated by introducing a correction coefficient, which satisfies the formula: in: These are the model correction coefficients. This refers to the deviation between the model's predicted values ​​and the actual collected values. As the model baseline value, This is the deviation adjustment factor.

9. A self-cleaning system based on airflow field reconstruction and particle trajectory intervention, used in the self-cleaning method based on airflow field reconstruction and particle trajectory intervention as described in any one of claims 1-7, characterized in that, include: Parameter acquisition module: configured to acquire airflow parameters and particle state parameters within the target space; Model building module: configured to build and update airflow field model and particle field model based on collected parameters; Trajectory prediction and risk assessment module: configured to predict the trajectory of target particles in advance and calculate the risk coefficient relative to the sensitive area; Control scheme generation module: Configured to generate an airflow field control scheme containing airflow direction, wind speed range, area of ​​effect, and time sequence when the risk coefficient exceeds the threshold; Airflow control module: includes airflow control device, configured to generate a guiding airflow field and form a reconstructed airflow field based on the control scheme; Particle collection module: Located in a preset collection area, configured to capture the converged target particles; Feedback adjustment module: Configured to adjust the airflow field control scheme based on monitoring data.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the self-cleaning method based on airflow field reconstruction and particle trajectory intervention as described in any one of claims 1-8.

Images