Intelligent control system and method based on air purification

Abstract

The invention relates to the technical field of air purification, in particular to an intelligent control system and method based on air purification. The method comprises the following steps: acquiring particulate matter data in an area; performing particulate matter concentration feature extraction on the particulate matter data in the region to obtain particulate matter concentration feature data in the region; performing particulate matter concentration correction on the particulate matter concentration data based on an environment sensor to generate particulate matter concentration correction data; performing heat map conversion on the particulate matter concentration correction data to generate a particulate matter concentration time sequence change heat map; performing particulate matter community area division on the particulate matter concentration time sequence change heat map to generate particulate matter cluster area data; and performing cluster region concentration prediction on the particulate matter cluster region data to generate particulate matter cluster concentration prediction data. By introducing technologies such as particulate matter concentration correction, time sequence change heat map analysis, multi-stage filtration and intelligent control, the control accuracy and flexibility of the air purification equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air purification, and in particular to an intelligent control system and method based on air purification. Background Art

[0002] Initially, air purification technology mainly relied on physical filtration methods, such as HEPA filters and activated carbon adsorption, which remove pollutants from the air through direct physical means, but their shortcomings are that they cannot intelligently identify and respond to different types of air pollution sources, and their efficiency is low. With the rapid development of sensor technology and the Internet of Things, air purification systems are gradually moving towards intelligence. Through integrated sensor technology, air purifiers can detect the concentration of pollutants such as PM2.5, CO2, formaldehyde, etc. in the air in real time, and automatically adjust the working mode based on data feedback. At this time, the core of the intelligent control method lies in the adaptive adjustment ability of the equipment. With the rise of artificial intelligence and machine learning, intelligent air purification systems have become more efficient and accurate. Through big data analysis and deep learning algorithms, intelligent control systems can predict the trend of air quality changes and optimize the purification process based on historical data to achieve more efficient energy consumption management and longer service life. However, the current existing technologies are relatively simple in the implementation of multi-stage filtration, lacking flexibility and refined management. At the same time, traditional air purification equipment often relies only on manual or simple automatic start-up control, but lacks intelligent and flexible adjustment mechanisms, resulting in low accuracy and flexibility in the control of air purification equipment. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent control system and method based on air purification to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent control method based on air purification is provided, the method comprising the following steps: Step S1: acquiring particulate matter data in the area; extracting particulate matter concentration characteristics from the particulate matter data in the area to obtain particulate matter concentration characteristic data in the area; performing particulate matter concentration correction on the particulate matter concentration data based on the environmental sensor to generate particulate matter concentration correction data; Step S2: converting the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; dividing the particle concentration time series change heat map into particle community regions to generate particle cluster region data; predicting the cluster region concentration of the particle cluster region data to generate particle cluster concentration prediction data; dividing the start control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual start control data; Step S3: performing multi-stage filtering on the particle cluster concentration prediction data according to the air purification device pre-start control data or the air purification device manual start control data to generate particle multi-stage filtering data; performing local area air purification on the area according to the particle multi-stage filtering data to generate air purification local adjustment data; performing functional control on the air purification local adjustment data and the particle multi-stage filtering data to generate air purification function control data; Step S4: Perform air quality assessment on the air purification function control data to generate purified air quality assessment data; visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

[0005] The present invention can accurately analyze the air quality status of the region by acquiring the particle data in the region and extracting the concentration characteristics. By correcting the particle concentration based on the environmental sensor, the environmental factors and sensor errors can be compensated, thereby improving the accuracy and reliability of the particle concentration data, and providing accurate basic data for subsequent air purification control. By converting the particle concentration correction data into a time-series change heat map, the change trend of the particle concentration in time and space can be clearly displayed, which is convenient for better understanding the dynamic changes of air pollution. Cluster area division can identify pollution hot spots and carry out targeted treatment to improve air purification efficiency. Cluster area concentration prediction provides a scientific basis for the startup of air purification equipment, ensuring that the purification equipment is accurately started when needed to avoid waste of resources. Through multi-stage filtration, the air purification effect can be optimized layer by layer, particles of different particle sizes can be removed, and the purification efficiency can be improved. Local area air purification can achieve differentiated processing according to the particle concentration in the specific area, making air purification more refined and improving energy utilization efficiency. Functionally controlled data generation makes the control process of the equipment more intelligent and accurate, avoiding the extensive operation in the traditional system. By evaluating the air quality of the air purification function control data, the purification effect can be quantified to ensure that the working efficiency of the air purification equipment meets the expected standards. After visualizing the evaluation data, the user can intuitively understand the changes in air quality after purification, enhance the user experience, and provide real-time feedback, which is convenient for further optimizing the system operation and improving the intelligence level of the system. Therefore, the present invention improves the accuracy and flexibility of air purification equipment control by introducing technologies such as particle concentration correction, time series change heat map analysis, multi-stage filtration and intelligent control.

[0006] Preferably, step S1 comprises the following steps: Step S11: obtaining particulate matter data in the area through a particulate matter sensor; Step S12: extracting particle concentration characteristics from the particle data in the area to obtain particle concentration characteristic data in the area; Step S13: performing data preprocessing on the particle concentration characteristic data in the area to generate standard particle concentration data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization; Step S14: performing particle concentration correction on the standard particle concentration data based on the environmental sensor to generate particle concentration correction data.

[0007] The present invention realizes the accurate collection of particulate matter data in the region by introducing a particulate matter sensor, covers different spatial ranges and concentration gradients, and ensures the comprehensiveness and real-time nature of the data source. Extracting the particle concentration characteristics can effectively capture the key characteristic information of the distribution of particles in the region, and provide high-quality basic data for subsequent data processing. Through data cleaning, denoising, missing value filling and standardization operations, the original data is converted into standard particle concentration data, which significantly improves the consistency and validity of the data and reduces the impact of data deviation on the analysis results. The particle concentration data is corrected by using environmental sensors, and environmental variables (such as humidity, temperature, etc.) are introduced into the analysis, which further optimizes the accuracy of the particle concentration data and makes the data more in line with the actual environment. The particle concentration correction data generated by the above steps has high precision and high reliability, and can be widely used in air quality monitoring, pollution source analysis, urban planning and governance and other fields, providing strong support. Through the systematic particle data collection and processing process, manual intervention and errors are reduced, the monitoring efficiency and automation level are improved, and the cost and complexity of long-term operation are reduced.

[0008] Preferably, step S14 includes the following steps: Step S141: performing particle concentration influence analysis on the standard particle concentration data to generate particle concentration influence data, wherein the particle concentration influence data includes temperature influence data, humidity influence data and air pressure influence data; Step S142: screening the corresponding environmental sensor data according to the temperature influence data, the humidity influence data and the air pressure influence data, and obtaining the particle temperature collection data, the particle humidity collection data and the particle pressure collection data respectively; Step S143: performing a particle concentration diffusion characteristic analysis on the standard particle concentration data through the particle temperature collection data to generate particle diffusion characteristic data; performing a particle concentration hygroscopic characteristic analysis on the standard particle concentration data through the particle humidity collection data to generate particle hygroscopic characteristic data; performing a particle settling characteristic analysis on the standard particle concentration data through the particle pressure collection data to generate particle settling characteristic data; Step S144: using the particle diffusion characteristic data, the particle hygroscopic characteristic data and the particle settling characteristic data to perform particle concentration correction on the standard particle concentration data to generate particle concentration correction data.

[0009] The present invention covers key environmental parameters such as temperature, humidity and air pressure through the analysis of the impact of particle concentration, quantifies the impact of the environment on particle concentration from multiple dimensions, and provides comprehensive data support for subsequent corrections. By screening the data collected by environmental sensors, more targeted particle temperature, humidity and air pressure data are obtained, which improves the relevance and reliability of the analysis data and avoids the impact of data redundancy on the calculation efficiency. Through the particle temperature collection data, the spatial distribution behavior of particles under different temperature conditions is deeply understood, which helps to predict the diffusion trend of particles. The hygroscopic characteristics of particles under humidity conditions are revealed by humidity data, which improves the ability to describe the changes in particle concentration. The analysis of particle sedimentation behavior in combination with air pressure data provides an important reference for the distribution and migration of particles in the atmosphere. The analysis results of diffusion characteristics, hygroscopic characteristics and sedimentation characteristics are comprehensively used for particle concentration correction, and the generated particle concentration correction data is closer to the actual environment, further improving the accuracy and scientificity of the data. The method can flexibly respond to changes in particle concentration under different regions and environmental conditions, and is suitable for a variety of complex scenarios such as atmospheric pollution monitoring, environmental governance effect evaluation and prediction model optimization.

[0010] Preferably, step S2 comprises the following steps: Step S21: performing time series change analysis on the particle concentration correction data to generate particle concentration time series change data; performing heat map conversion on the particle concentration time series change data to generate a particle concentration time series change heat map; Step S22: marking the particle concentration time series change heat map with the particle concentration aggregation center point to obtain the particle concentration center point; dividing the particle concentration time series change heat map into particle cluster areas based on the particle concentration center point to generate particle cluster area data; Step S23: performing cluster area concentration prediction on the particle matter cluster area data to generate particle matter cluster concentration prediction data; comparing the particle matter cluster concentration prediction data with a preset standard particle matter cluster concentration threshold, and when the particle matter cluster concentration prediction data is greater than or equal to the preset standard particle matter cluster concentration threshold, performing pre-start control on the air purification device to generate air purification device pre-start control data; Step S24: When the particle cluster concentration prediction data is less than the preset standard particle cluster concentration threshold, a manual start control instruction is received for the air purification device, thereby generating manual start control data for the air purification device.

[0011] The present invention presents the dynamic changes of particle concentration in an intuitive way by analyzing the time series changes of the particle concentration correction data and generating a heat map, which is convenient for discovering the concentration change trend and abnormal fluctuations. The visualization form of the heat map makes the time and space distribution characteristics of the data clearer, which is convenient for quickly locating the high concentration change area. By marking the particle aggregation center point and dividing the particle community area based on these center points, the aggregation hotspot area of ​​the particle concentration is effectively identified, providing data support for precise governance and intervention. The marking and regional division of the aggregation center improve the spatial resolution of data analysis and optimize the efficiency of resource allocation. Concentration prediction is performed based on the particle cluster area data, so that the system can perceive the formation trend of high concentration areas in advance, and compare it with the preset standard threshold to realize the active early warning function. When the concentration prediction data reaches or exceeds the threshold, the pre-start control data of the air purification equipment is generated, which significantly improves the response speed of air purification and reduces the impact of particle pollution on the environment and health. By receiving the manual start instruction to generate the manual control data of the air purification equipment, the user is given the flexibility to operate the air purification equipment, taking into account the needs of automation and manual control.

[0012] Preferably, performing cluster area concentration prediction on the particulate matter cluster area data includes: Extract the particle cluster distribution characteristics from the particle cluster area data to obtain the particle cluster distribution characteristic data; divide the particle cluster distribution characteristic data into data sets to generate a model training set and a model test set; train the model training set using a long short-term memory neural network algorithm to generate a particle cluster area concentration prediction pre-model; Based on the model test set, the particle matter cluster area concentration prediction pre-model is optimized and iterated to generate a particle matter cluster area concentration prediction model; the particle matter cluster area data is imported into the particle matter cluster area concentration prediction model to perform cluster area concentration prediction and generate particle matter cluster concentration prediction data.

[0013] The present invention can comprehensively capture the spatial distribution characteristics of particles in the cluster area, including concentration gradients, aggregation patterns, etc., by extracting the distribution characteristics of particle clusters before prediction, thereby providing high-quality input data for subsequent modeling. Data feature extraction improves the prediction model's ability to understand the dynamic changes of particles and enhances the applicability and robustness of the model. The extracted feature data is divided into a model training set and a model test set to ensure that the training and evaluation of the model are independent of each other. Data set division provides a stable verification basis for model optimization, avoids the problem of model overfitting, and improves the reliability of model prediction performance. The LSTM algorithm is used to model the particle cluster area data, which can capture the time series characteristics of concentration changes and has a high adaptability to the dynamic change trend of particle concentration. The LSTM algorithm is particularly suitable for processing long dependencies in particle time series data, thereby improving the prediction accuracy. Through optimization iteration based on the model test set, the performance of the prediction pre-model is improved, making the final prediction model more accurate. The model optimization iteration process ensures the stability of the model in a variety of environments and can effectively cope with the particle concentration distribution in different regions. The optimized prediction model takes particulate matter cluster area data as input and quickly outputs high-precision particulate matter cluster concentration prediction data, providing a reliable decision-making basis for subsequent air governance and control.

[0014] Preferably, step S3 comprises the following steps: Step S31: when the air purification device receives the air purification device pre-start control data or the air purification device manual start control data, it performs multi-stage filtration based on the particle cluster concentration prediction data to generate particle multi-stage filtration data; Step S32: performing local air purification on the area according to the multi-stage filtration data of particulate matter, and generating local air purification adjustment data, wherein the local air purification includes dynamic adjustment of local air purification intensity and dynamic adjustment of local air purification wind speed; Step S33: encapsulate the air purification local adjustment data and the particulate matter multi-stage filtration data into control instructions to generate air purification control instructions; use the air purification instructions to control the functions of the air purification equipment to generate air purification function control data.

[0015] The present invention dynamically adjusts the filter efficiency based on the predicted data through multi-stage filtration of particulate matter, and implements graded filtration according to the particle size and concentration level of the particulate matter at different stages. The filtration efficiency is improved, the filter blockage frequency is reduced, and the utilization rate of the filtration resources is optimized. The purification intensity and wind speed of the local air environment in the area are dynamically adjusted. The dynamic adjustment of the local air purification intensity can realize real-time enhancement or weakening of the purification intensity according to the change of the particle concentration, and ensure the rapid removal of pollutants. The dynamic adjustment of the local air purification wind speed improves the coverage of the purification equipment and the uniformity of the airflow distribution, ensuring the maximum purification effect. The filtering and adjustment data are intelligently encapsulated, and the generated air purification control instructions have real-time and adaptability, reducing the complex operation process and improving the automation level of the system. The control instruction encapsulation optimizes the response speed of the purification equipment, and can start or adjust the function in time to cope with the rapidly changing particle concentration. The purification equipment is accurately controlled by the air purification function control data, including filter cleaning reminders, fan speed adjustment and other functions, realizing the comprehensive automatic operation of the purification equipment. The equipment operation efficiency is improved and the service life of the equipment is extended.

[0016] Preferably, step S31 includes the following steps: Step S311: performing primary filtration simulation calculation according to the startup particulate matter prediction data, thereby obtaining primary filtration particulate matter data; Step S312: performing intermediate filtration dynamic optimization calculation on the primary filtration particulate matter data using multi-dimensional filtration parameters, thereby obtaining intermediate filtration particulate matter data; Step S313: Based on a preset aerodynamic model, an advanced filtering path optimization calculation is performed on the intermediate filtering particulate matter data to obtain advanced filtering particulate matter data; multi-stage filtering is performed on the primary filtering particulate matter data, the intermediate filtering particulate matter data and the advanced filtering particulate matter data to generate multi-stage particulate matter filtering data.

[0017] The present invention quickly identifies and removes large particles through primary filtration simulation calculation, reduces the burden for subsequent filtration stages, and improves overall filtration efficiency. The dynamic optimization calculation of intermediate filtration dynamically adjusts the filtration strategy through multi-dimensional filtration parameters (such as particle size, density, concentration, etc.) to provide the optimal filtration effect for different particle characteristics. The advanced filtration path optimization calculation optimizes the filtration path using an aerodynamic model to improve the capture ability of fine particles, thereby achieving a deep purification effect. The filtration process is divided into primary, intermediate and advanced stages, so that particles of different particle sizes and characteristics are effectively filtered in the corresponding stages. The layer-by-layer optimization of filtration calculations at each stage ensures the comprehensive removal of particles, and the filtration process is more targeted and scientific. The dynamic optimization of multi-dimensional filtration parameters can adapt to changes in particle concentration in real time and ensure the continuous stability of the filtration effect under various environmental conditions. The advanced filtration path optimization calculation can adjust the path according to aerodynamic conditions to improve the applicability of the system under different wind speeds and flow directions. Primary filtration reduces the particle load entering the intermediate and advanced filtration stages, thereby reducing the resource consumption and maintenance cost of the filtration system. Dynamic optimization and path optimization reduce energy consumption, increase the life of the filter, and reduce long-term use costs.

[0018] Preferably, performing multi-stage filtering through primary filtering particulate matter data, intermediate filtering particulate matter data, and advanced filtering particulate matter data includes: Based on the particle size separation method, the primary filtration particulate matter data is separated into large particles, thereby obtaining the first-stage filtration data of the particulate matter; the intermediate filtration particulate matter data is analyzed for the particle concentration gradient distribution, and the intermediate filtration particulate matter concentration gradient distribution data is generated; The concentration distribution of the intermediate filtration particulate matter data is homogenized according to the intermediate filtration particulate matter concentration gradient distribution data, thereby obtaining the second stage filtration data of the particulate matter; the surface adsorption rate of the advanced filtration particulate matter data is optimized by the dynamic adsorption method, thereby generating the third stage filtration data of the particulate matter; Multi-stage filtration path interactive optimization calculations are performed on the particulate matter first-stage filtration data, the particulate matter second-stage filtration data, and the particulate matter third-stage filtration data to generate multi-stage filtration path optimization data; multi-stage filtration is performed on the particulate matter cluster concentration prediction data using the multi-stage filtration path optimization data to generate multi-stage filtration data for particulate matter.

[0019] The present invention removes large particles by particle size separation, providing a good foundation for fine filtration in the subsequent stage. By removing larger particles, the burden of the subsequent stage can be significantly reduced, and the overall filtration efficiency of the system can be improved. By analyzing the distribution of particle concentration gradients, it is possible to more accurately identify and optimize areas with uneven concentrations, ensuring that the particle concentration in each area is balanced in the entire filtration system. The surface adsorption of particles is optimized by the dynamic adsorption method to improve the capture rate of fine particles, especially fine particles in the air, such as PM2.5. By path optimization, mutual interference between filters at different stages is avoided, ensuring that different particles can be most effectively processed in each stage, which can optimize the operation of the equipment, reduce energy consumption, and improve the filtration effect. Interactive optimization avoids waste of resources through effective path planning, combined with the characteristics of primary, intermediate and advanced filtration, while increasing the stability and adaptability of the system. This process ensures that the system can efficiently cope with different air quality conditions when processing various particles through precise separation and optimization. Specifically, primary filtration mainly processes larger particles, intermediate filtration balances concentration distribution, and advanced filtration focuses on fine particles to ensure that each type of particle is reasonably purified. The multi-stage filtration data of particulate matter achieves dynamic response to different pollution sources by optimizing the path. It is particularly suitable for dynamically changing environmental conditions, and can automatically adapt to fluctuations in particulate matter concentration and adjust purification strategies in real time.

[0020] Preferably, step S4 comprises the following steps: Step S41: performing air purification feedback on the air purification function control data to generate air purification feedback data; performing air quality evaluation on the air purification feedback data to generate purified air quality evaluation data; Step S42: Visualizing the purified air quality assessment data to generate a purified air quality assessment display interface.

[0021] The present invention can help the system evaluate the operating effect of the current air purification equipment by real-time feedback of the air purification function control data. This feedback mechanism ensures that the equipment is adaptively adjusted according to the real-time air quality, thereby optimizing the purification process. Based on the evaluation of air purification feedback data, the working effect of the air purification system can be accurately reflected, any problems or deficiencies in the purification process can be discovered in time, and the purification effect can be ensured to continuously reach the expected goal. By evaluating the air quality after purification, the system can accurately feedback the improvement of air quality and show the air purification effect to the user in time, which enables the system to have a higher monitoring capability in practical applications, can evaluate the changing trend of air quality, and make corresponding adjustments according to the evaluation data. This evaluation mechanism helps the system judge the change of air quality, provides data support to decision makers or users, and makes the management of air quality more scientific and accurate. The purified air quality evaluation data is converted into a visual display interface, which is convenient for users to clearly understand the real-time status of the current air quality. This visual interface is not only convenient for users to operate and understand, but also can display the improvement of air quality in a graphical way, such as data such as particle concentration, humidity, and temperature. The air quality assessment display interface is designed to be intuitive and easy to understand, which enhances the interactivity between users and the system, allowing users to quickly obtain information on the quality of purified air and determine whether further purification operations are needed.

[0022] In this specification, an intelligent control system based on air purification is provided, which is used to execute the above-mentioned intelligent control method based on air purification. The intelligent control system based on air purification includes: The particle detection module is used to obtain particle data in the area; extract particle concentration characteristics of the particle data in the area to obtain particle concentration characteristic data in the area; perform particle concentration correction on the particle concentration data based on the environmental sensor to generate particle concentration correction data; A startup control module is used to convert the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; divide the particle concentration time series change heat map into particle community areas to generate particle cluster area data; predict the cluster area concentration of the particle cluster area data to generate particle cluster concentration prediction data; divide the startup control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual startup control data; The air filtration module is used to perform multi-stage filtration on the predicted data of particle cluster concentration according to the pre-start control data of the air purification device or the manual start control data of the air purification device to generate multi-stage filtration data of the particle; perform local area air purification on the area according to the multi-stage filtration data of the particle to generate local air purification adjustment data; perform functional control on the local air purification adjustment data and the multi-stage filtration data of the particle to generate air purification function control data; The quality assessment module is used to perform air quality assessment on the air purification function control data to generate purified air quality assessment data; and to visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

[0023] The beneficial effect of the present invention is that by accurately acquiring the particle data in the area and extracting the particle concentration characteristics, the particle characteristics in the area are analyzed. This data precision can provide reliable basic data for subsequent processing. The particle concentration data is corrected by the environmental sensor to ensure the accuracy and stability of the particle concentration data, reduce the impact of external interference on the data, and improve the overall performance of the system. The startup control module can convert the particle concentration time series change data into a heat map and divide the particle community area. This step can effectively identify and locate the aggregation area of ​​particles in the area, providing support for subsequent precise control. By predicting the concentration of the particle cluster area, the system can achieve accurate particle concentration prediction and provide a scientific basis for starting the air purification equipment. This function improves the accuracy of the prediction and ensures the efficiency and timeliness of the air purification process. The air filtration module performs multi-stage filtering on the particle cluster concentration prediction data and adjusts the air purification of the local area according to the filtering data. The system can perform fine processing according to the different stages of the particles to improve the air purification effect. The module ensures continuous optimization of the air quality in the local area by dynamically adjusting the air purification intensity and wind speed. This process is adjusted based on real-time data and predicted information, which enhances the adaptability and efficiency of the system. According to the local adjustment data of air purification and the multi-stage filtration data of particulate matter, the system can achieve precise function control and automatically adjust the operation mode of the air purification equipment. This automated control greatly reduces the need for manual intervention and improves the convenience and accuracy of operation. The startup control module generates pre-start and manual startup control data based on the particle concentration prediction data, ensures the timely startup of the air purification equipment, avoids unnecessary delays, and improves the response speed of air quality adjustment. The quality evaluation module evaluates the air purification function control data in real time and generates the purified air quality evaluation data, which provides a dynamic feedback mechanism for the system, can adjust the operation in time, and ensure continuous improvement of air quality. Therefore, the present invention improves the accuracy and flexibility of air purification equipment control by introducing technologies such as particle concentration correction, time series change heat map analysis, multi-stage filtration and intelligent control. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a process flow of an intelligent control method based on air purification; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 , an intelligent control method based on air purification, the method comprising the following steps: Step S1: acquiring particulate matter data in the area; extracting particulate matter concentration characteristics from the particulate matter data in the area to obtain particulate matter concentration characteristic data in the area; performing particulate matter concentration correction on the particulate matter concentration data based on the environmental sensor to generate particulate matter concentration correction data; Step S2: converting the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; dividing the particle concentration time series change heat map into particle community regions to generate particle cluster region data; predicting the cluster region concentration of the particle cluster region data to generate particle cluster concentration prediction data; dividing the start control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual start control data; Step S3: performing multi-stage filtering on the particle cluster concentration prediction data according to the air purification device pre-start control data or the air purification device manual start control data to generate particle multi-stage filtering data; performing local area air purification on the area according to the particle multi-stage filtering data to generate air purification local adjustment data; performing functional control on the air purification local adjustment data and the particle multi-stage filtering data to generate air purification function control data; Step S4: Perform air quality assessment on the air purification function control data to generate purified air quality assessment data; visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

[0029] The present invention can accurately analyze the air quality status of the region by acquiring the particle data in the region and extracting the concentration characteristics. By correcting the particle concentration based on the environmental sensor, the environmental factors and sensor errors can be compensated, thereby improving the accuracy and reliability of the particle concentration data, and providing accurate basic data for subsequent air purification control. By converting the particle concentration correction data into a time-series change heat map, the change trend of the particle concentration in time and space can be clearly displayed, which is convenient for better understanding the dynamic changes of air pollution. Cluster area division can identify pollution hot spots and carry out targeted treatment to improve air purification efficiency. Cluster area concentration prediction provides a scientific basis for the startup of air purification equipment, ensuring that the purification equipment is accurately started when needed to avoid waste of resources. Through multi-stage filtration, the air purification effect can be optimized layer by layer, particles of different particle sizes can be removed, and the purification efficiency can be improved. Local area air purification can achieve differentiated processing according to the particle concentration in the specific area, making air purification more refined and improving energy utilization efficiency. Functionally controlled data generation makes the control process of the equipment more intelligent and accurate, avoiding the extensive operation in the traditional system. By evaluating the air quality of the air purification function control data, the purification effect can be quantified to ensure that the working efficiency of the air purification equipment meets the expected standards. After visualizing the evaluation data, the user can intuitively understand the changes in air quality after purification, enhance the user experience, and provide real-time feedback, which is convenient for further optimizing the system operation and improving the intelligence level of the system. Therefore, the present invention improves the accuracy and flexibility of air purification equipment control by introducing technologies such as particle concentration correction, time series change heat map analysis, multi-stage filtration and intelligent control.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a step flow chart of an intelligent control method based on air purification of the present invention. In this example, the intelligent control method based on air purification includes the following steps: Step S1: acquiring particulate matter data in the area; extracting particulate matter concentration characteristics from the particulate matter data in the area to obtain particulate matter concentration characteristic data in the area; performing particulate matter concentration correction on the particulate matter concentration data based on the environmental sensor to generate particulate matter concentration correction data; In an embodiment of the present invention, by using an environmental sensor network (such as PM2.5, PM10, VOC sensors, etc.) to collect particulate matter concentration data in the area in real time, these sensors can be distributed in different areas or different levels to achieve multi-dimensional monitoring of particulate matter. Wireless sensor network (WSN) or Internet of Things (IoT) technology is used to transmit sensor data to a central data processing system through a wireless network. Sensors can be installed in multiple locations such as indoors, outdoors, traffic-intensive areas or industrial areas to fully obtain particulate matter data. According to the changing characteristics of particulate matter concentration, the acquisition frequency of the sensor is set. Common acquisition frequencies are once per minute or once per hour, depending on actual needs. Real-time data collection will help to quickly identify pollution sources and concentration change trends in the area. During data transmission, there will be noise and outliers. Therefore, it is necessary to perform preliminary cleaning and correction on the collected data, eliminate obvious erroneous data (such as extreme values ​​caused by sensor failure or error) and fill in missing data points. Time domain feature and frequency domain feature analysis can be used to extract particulate matter concentration features. Common features include: maximum, minimum, average, variance, etc. of particulate matter concentration. Spectral analysis of particle concentration data can reveal periodic fluctuations in particle concentration, and is particularly suitable for monitoring changes in long-term pollution. By smoothing the data, the trend of particle concentration is extracted to determine whether the air quality has deteriorated. The impact of environmental factors such as temperature, humidity, and air pressure on particle concentration can be quantified and extracted through regression analysis or machine learning methods. Using the above feature extraction method, feature data of particle concentration is generated. This data is used to further analyze air quality conditions, identify pollution sources, and predict future changes in particle concentration. Since particle concentration is affected by a variety of environmental factors (such as temperature, humidity, and air pressure), in order to improve the accuracy of particle concentration data, sensor data needs to be corrected. Common correction methods include: temperature changes lead to changes in particle concentration, and by establishing a mathematical model between temperature and particle concentration (such as a regression model), the error caused by temperature changes is corrected. Humidity affects the hygroscopicity of particles, especially in PM2.5 concentration measurement, humidity changes can cause particles to expand or settle, thereby affecting the measurement accuracy. Air pressure changes can affect the distribution and concentration of particles in the air, especially in areas with low air pressure, where particle concentrations fluctuate to varying degrees. Based on the environmental factors (temperature, humidity, air pressure, etc.) collected by the sensor, multivariate regression analysis, machine learning models or traditional correction coefficient methods can be used to correct the particle concentration data. Specifically, a linear regression algorithm can be used to establish the relationship between temperature and particle concentration, and real-time correction can be performed when collecting data. For complex environments, machine learning-based correction methods (such as support vector machines, neural networks, etc.) are used to model and handle particle concentration corrections under different environmental conditions.After correction, the obtained particle concentration data is considered to be a more accurate "standard concentration data", which reflects the particle concentration state after correction of environmental factors. Deploy high-precision particle concentration sensors (such as micro-weather stations, air quality detection equipment, etc.) in the area, and select sensor models according to actual needs to ensure the accuracy and comprehensiveness of data collection. Configure wireless data transmission modules (such as Wi-Fi, LoRaWAN, 5G, etc.) to ensure the real-time and stability of data transmission. Develop or integrate particle concentration correction algorithms, and perform real-time data correction in combination with environmental monitoring data (such as temperature, humidity, air pressure, etc.). The correction algorithm can be adjusted according to regional characteristics (such as cities, industrial areas, etc.) to optimize the accuracy of particle concentration correction.

[0031] Step S2: converting the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; dividing the particle concentration time series change heat map into particle community regions to generate particle cluster region data; predicting the cluster region concentration of the particle cluster region data to generate particle cluster concentration prediction data; dividing the start control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual start control data; In an embodiment of the present invention, a time series change heat map is generated by using the particle concentration correction data (such as the concentration values ​​of PM2.5 and PM10). Each data point represents the particle concentration value at a specific time node, the horizontal axis represents the time, and the vertical axis represents the spatial position. The time series data is converted into a two-dimensional heat map, and the color depth is used to represent the change in particle concentration. Specifically, higher particle concentrations can be represented by red or dark colors, while lower concentrations are represented by blue or light colors. The particle concentration correction data (such as concentration data from different sensors) are space-time gridded, and each grid represents the particle concentration data at a time point and spatial position. Based on the particle concentration correction data, these data are interpolated or smoothed to ensure that the generated heat map data is smoother and continuous, reduce the impact of measurement errors, and the generated heat map can clearly show the spatial distribution of particle concentration changes over time, and provide intuitive data support for subsequent regional division and prediction. By analyzing the concentration distribution of different areas in the particle concentration heat map, different particle community areas are divided. Clustering algorithms (such as K-means clustering, DBSCAN, etc.) can be used to divide the heat map into spatial regions and identify high-concentration regions, medium-concentration regions, and low-concentration regions. According to the similarity of particle concentrations in the region, it is divided into multiple particle cluster regions. The particle concentration changes in each region have certain similarities, forming particle "clusters" or "clusters". The particle heat map is divided into regions according to the clustering results to generate particle cluster region data. Each cluster region can include different particle concentration data, and each region can be marked as a specific category (such as high pollution area, light pollution area, clean area, etc.). When processing cluster region data, the data can be denoised and smoothed to ensure the quality and reliability of particle cluster region data. It is necessary to consider the impact of meteorological factors (such as wind speed and wind direction) on particle concentration, and integrate these factors into the regional division to improve the accuracy of the division. Based on the particle cluster region data, a particle concentration prediction model is established using machine learning or deep learning methods (such as long short-term memory network LSTM, support vector regression SVR, etc.). The input data includes historical data of particle concentration in the area, environmental factors (such as temperature, humidity, air pressure, etc.), and other time series characteristics. Use the trained model to predict the future particle concentration of each particle cluster area. The goal of the prediction is to predict the particle concentration in the area for a certain period of time in the future and identify pollution trends. The particle cluster concentration prediction model is optimized through cross-validation and regression analysis to ensure the accuracy of the prediction results. Regression errors (such as mean square error MSE, root mean square error RMSE, etc.) can be used to evaluate model performance and adjust the model parameters to obtain the best prediction effect. According to the particle cluster concentration prediction data, the air quality status of each cluster area is judged.Specifically, when the predicted value of the particle concentration exceeds the set threshold (such as PM2.5 concentration>75 µg / m³), the start-up of the air purification device can be triggered. According to the predicted particle concentration data, the areas where the air purification device needs to be automatically started (for example, severely polluted areas) and the areas where the device can be manually started (for example, lightly polluted areas) are divided. For areas predicted to be heavily polluted, the air purification device can be started in advance. By starting in advance, pretreatment and purification can be carried out before the pollution reaches a dangerous level to slow down the spread of pollution. For areas with light pollution or occasional pollution, manual start-up control data can be generated, allowing users to start the air purification device as needed, and generate start-up control data for the air purification device, including detailed information such as device start-up time, operating mode (such as high wind speed, low wind speed, etc.), and operating time. The generated start-up control data is transmitted to the corresponding air purification device for automatic or manual control.

[0032] Step S3: performing multi-stage filtering on the particle cluster concentration prediction data according to the air purification device pre-start control data or the air purification device manual start control data to generate particle multi-stage filtering data; performing local area air purification on the area according to the particle multi-stage filtering data to generate air purification local adjustment data; performing functional control on the air purification local adjustment data and the particle multi-stage filtering data to generate air purification function control data; In an embodiment of the present invention, based on the predicted data of the concentration of the particle cluster, the particles in the high concentration area are firstly filtered. Primary filtration usually removes larger particles through a physical filter or primary purification technology (such as an electrostatic filter, a coarse particle filter, etc.). The primary filtration process should accurately start and control the equipment according to the predicted data of the particle concentration to ensure that the purification equipment can effectively play a role when it is started in the polluted area. The particle data after the primary filtration is further processed, and the intermediate filtration technology (such as HEPA filter or activated carbon adsorption filtration) is used to remove fine particles and some harmful gases. The operation mode of the filtration device is adjusted according to the predicted data of the particle concentration through a data dynamic optimization algorithm (such as filter adjustment, air flow optimization, etc.) to ensure the best filtration effect. Based on the predicted data of the particle concentration and the regional air quality prediction, advanced filtration technology (such as ultraviolet disinfection, negative ion generator, etc.) is used to perform more detailed purification treatment on the air after the intermediate filtration. At this time, the filtration path is accurately calculated to ensure that the particles can be completely removed when passing through the equipment. Advanced filtration not only targets particles, but also eliminates existing air pollution sources (such as bacteria, viruses, etc.). After each stage of filtration is completed, multi-stage filtration data of particulate matter is generated to reflect the changes in the concentration of particulate matter in each filtration stage. The final multi-stage filtration data of particulate matter will be fed back through the sensor to form the filtered air quality data. Based on the multi-stage filtration data, the air purification equipment is dynamically adjusted to perform local air purification according to the changes in the concentration of particulate matter in different regions. Specifically: According to the changes in the concentration data of particulate matter in different regions, the purification intensity of the air purification equipment is adjusted. High-pollution areas are adjusted to high-intensity mode, and low-pollution areas are reduced to appropriate purification intensity. The wind speed is adjusted according to the real-time data of air quality to improve the air purification efficiency. The wind speed can be increased in areas with severe pollution to accelerate the air purification process, while the wind speed can be appropriately reduced in areas with less pollution to reduce energy consumption. Based on the multi-stage filtration data of particulate matter, the changes in the concentration of regional particulate matter and the real-time feedback of air purification equipment, the local adjustment data of air purification is generated. The adjustment data includes changes in parameters such as purification intensity, wind speed, and operation mode. In addition, the adjustment data should also include recommendations on the start or stop time of the equipment to ensure that the equipment automatically shuts down when the target purification effect is achieved to avoid waste of resources. Design the control strategy of air purification equipment based on the local adjustment data of air purification and the multi-stage filtration data of particulate matter to ensure the optimal performance of the equipment during operation. Decide when to start or stop the equipment based on the prediction data of the particle cluster concentration and the start-up control data of the air purification equipment. The start and stop time and duration of the equipment must be synchronized with the changes in the particle concentration in the local area. Automatically adjust the wind speed and purification intensity based on the local adjustment data of air purification to ensure that the particle concentration is controlled within a safe range. Generate air purification function control data based on the control strategy.The data includes but is not limited to: controlling the change of wind speed to adapt to different air purification needs. Indicating the purification mode that the equipment should adopt, such as high-efficiency mode, energy-saving mode, sleep mode, etc. Including information such as the current operating status of the equipment, filtration efficiency, fault detection, etc., to help maintain and manage the air purification equipment. The generated air purification function control data will be transmitted to the air purification equipment and implemented through the intelligent control system. Specifically, through intelligent network connection, ensure that the equipment performs purification tasks according to the preset mode and real-time needs. At the same time, the air purification effect can be monitored in real time through equipment feedback, and timely adjustments can be made according to the air quality to ensure that the air purification is continuously effective.

[0033] Step S4: Perform air quality assessment on the air purification function control data to generate purified air quality assessment data; visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

[0034] In an embodiment of the present invention, the air purification function control data includes information such as purification intensity, wind speed, equipment operation status, and particle concentration data collected by the air quality sensor. According to the change in particle concentration, combined with common air quality indicators such as PM2.5 and PM10, the air quality change before and after air purification is evaluated. Specifically, the PM2.5 concentration difference before and after purification, the pollutant removal efficiency, etc. can be calculated. An air quality evaluation algorithm is used, such as a difference method, an index method, a weighted average method, etc., to evaluate the purification effect. The algorithm can give the evaluation result of the purified air quality based on the control mode and real-time feedback of the air purification equipment and the change in particle concentration. Evaluate the change in particle concentration before and after air purification and generate purified air quality evaluation data. This data should include: showing the change in particle concentration before and after purification to help analyze the air purification effect. Calculate the removal efficiency of particles during the purification process to help evaluate the performance of the equipment. According to the air quality standard, evaluate the air quality index (such as AQI) after purification. Output the purified air quality evaluation data and prepare for further data visualization. Display the change in particle concentration before and after purification to facilitate intuitive understanding of the dynamic changes in the air purification process. Specifically, the X-axis represents time, and the Y-axis represents particle concentration, showing the trend of concentration changes before and after air purification. Based on the particle concentration data and air quality assessment results, a heat map or distribution map is generated to show the air purification effect in different areas, which can intuitively show the spatial distribution of air quality changes, such as the changes in particle concentration in various areas. Using the air quality index (AQI) for visual display, different colors (such as green, yellow, and red) can be set to represent different air quality levels to help users quickly understand the air quality status after purification. In the air quality assessment display interface, a real-time monitoring panel is designed to display the particle concentration, PM2.5 and PM10 levels, and air quality index of the area after purification. The interface design should support user interaction with data, such as selecting different time periods for comparison, viewing air quality changes in specific areas, and analyzing pollution sources. The interface should be able to display the operating status of the air purification equipment, including current purification intensity, wind speed and other parameters, to help users adjust or optimize air purification strategies. In the display interface, the air quality assessment data after purification is displayed, and various charts and graphics are used to help users understand the air purification effect more intuitively. Important data such as particle concentration, purification efficiency, AQI, etc. before and after purification can be compared and displayed, allowing users to clearly see the improvements before and after air purification.

[0035] Preferably, step S1 comprises the following steps: Step S11: obtaining particulate matter data in the area through a particulate matter sensor; Step S12: extracting particle concentration characteristics from the particle data in the area to obtain particle concentration characteristic data in the area; Step S13: performing data preprocessing on the particle concentration characteristic data in the area to generate standard particle concentration data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization; Step S14: performing particle concentration correction on the standard particle concentration data based on the environmental sensor to generate particle concentration correction data.

[0036] In the embodiment of the present invention, the coverage of each monitoring point is ensured by deploying particulate matter sensors (such as PM2.5, PM10 sensors, etc.) in the target area. The sensor continuously monitors the particle concentration in the area, collects real-time particle data, and records the particle values ​​at different times and locations. The original data is simply cleaned, such as removing obvious outliers and null values. According to the statistical characteristics of the particle concentration fluctuation, peak value, mean, standard deviation, etc., the key features that can represent the regional air quality, such as the daily average concentration, hourly concentration change trend, etc., are extracted. Methods such as PCA (principal component analysis) are used to reduce the dimension of the particle data and select the characteristic data that best represents the air quality. Noise and outliers in the data are removed, such as data errors caused by sensor failure or short-term abnormal fluctuations. Filtering algorithms (such as low-pass filtering, Kalman filtering, etc.) are used to remove noise data to improve the accuracy of the data. For missing data, interpolation, mean filling, etc. are used to supplement to ensure the integrity of the data. The particle concentration data is standardized so that its value range is within a unified standard range. Common methods include z-score standardization or min-max standardization. By combining with other environmental sensor data (such as temperature, humidity, air pressure, etc.), a regression model between particle concentration and environmental factors is established. Using regression models or machine learning algorithms (such as random forests, support vector machines, etc.), standard particle concentration data is corrected to eliminate concentration fluctuations caused by environmental changes. The corrected particle concentration data further improves the accuracy and credibility of the data, providing accurate basic data for subsequent analysis.

[0037] Preferably, step S14 includes the following steps: Step S141: performing particle concentration influence analysis on the standard particle concentration data to generate particle concentration influence data, wherein the particle concentration influence data includes temperature influence data, humidity influence data and air pressure influence data; Step S142: screening the corresponding environmental sensor data according to the temperature influence data, the humidity influence data and the air pressure influence data, and obtaining the particle temperature collection data, the particle humidity collection data and the particle pressure collection data respectively; Step S143: performing a particle concentration diffusion characteristic analysis on the standard particle concentration data through the particle temperature collection data to generate particle diffusion characteristic data; performing a particle concentration hygroscopic characteristic analysis on the standard particle concentration data through the particle humidity collection data to generate particle hygroscopic characteristic data; performing a particle settling characteristic analysis on the standard particle concentration data through the particle pressure collection data to generate particle settling characteristic data; Step S144: using the particle diffusion characteristic data, the particle hygroscopic characteristic data and the particle settling characteristic data to perform particle concentration correction on the standard particle concentration data to generate particle concentration correction data.

[0038] In an embodiment of the present invention, based on the collected standard particle concentration data and environmental data (such as temperature, humidity, and air pressure), regression analysis or machine learning models (such as linear regression, random forest, etc.) are used to analyze the impact of environmental factors on particle concentration. By analyzing the impact of temperature changes on particle concentration, the relationship between particle concentration and temperature is established. The impact of humidity changes on particle concentration, especially the effect of moisture absorption on fine particles (such as PM2.5) is analyzed. The impact of air pressure changes on particle concentration, especially the sedimentation and distribution of particles under low air pressure, is considered. Output temperature impact data, humidity impact data, and air pressure impact data, respectively reflecting the specific impact of environmental factors on particle concentration. Filter the real-time temperature data provided by the temperature sensor and match it with the particle concentration data to extract the part of the particle concentration affected by temperature. Filter the data collected by the humidity sensor, combine it with the particle concentration data, and extract the part of the humidity that affects the particle concentration. Filter the data of the air pressure sensor, analyze the impact of air pressure on the particle concentration, and extract the air pressure-related impact data. The particle temperature collection data, particle humidity collection data and particle pressure collection data are obtained respectively to provide a basis for subsequent analysis. The relationship between temperature and particle concentration is used to analyze how temperature affects the diffusion behavior of particles, especially the diffusion speed and range under high and low temperature conditions. The particle concentration diffusion characteristic data is generated through model analysis to reflect the diffusion of particles under different temperature conditions. The hygroscopic behavior of particles under different humidity conditions is analyzed through humidity data, especially the effect of humidity on the size, mass and concentration of particles. The hygroscopic characteristics of particle concentration are modeled according to humidity changes to generate particle hygroscopic characteristic data. The effect of air pressure on particle sedimentation is analyzed using air pressure data, especially under low air pressure, particles will settle faster. According to the effect of air pressure on particle sedimentation behavior, particle sedimentation characteristic data is generated. Combined with the particle diffusion characteristics, hygroscopic characteristics and sedimentation characteristics data, a comprehensive correction model is established to correct the standard particle concentration data. The standard particle concentration data is corrected by applying the particle diffusion characteristic data, particle hygroscopic characteristic data and particle sedimentation characteristic data through algorithms (such as weighted average method, regression analysis method, etc.). The final particle concentration correction data is generated based on the correction results to make it more consistent with the actual environmental conditions.

[0039] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing time series change analysis on the particle concentration correction data to generate particle concentration time series change data; performing heat map conversion on the particle concentration time series change data to generate a particle concentration time series change heat map; Step S22: marking the particle concentration time series change heat map with the particle concentration aggregation center point to obtain the particle concentration center point; dividing the particle concentration time series change heat map into particle cluster areas based on the particle concentration center point to generate particle cluster area data; Step S23: performing cluster area concentration prediction on the particle matter cluster area data to generate particle matter cluster concentration prediction data; comparing the particle matter cluster concentration prediction data with a preset standard particle matter cluster concentration threshold, and when the particle matter cluster concentration prediction data is greater than or equal to the preset standard particle matter cluster concentration threshold, performing pre-start control on the air purification device to generate air purification device pre-start control data; Step S24: When the particle cluster concentration prediction data is less than the preset standard particle cluster concentration threshold, a manual start control instruction is received for the air purification device, thereby generating manual start control data for the air purification device.

[0040] In an embodiment of the present invention, the dynamic change pattern of the particle concentration is identified by performing a time series analysis on the particle concentration correction data. A time series analysis method (such as an autoregressive model ARIMA, a long short-term memory network LSTM, etc.) is used to capture the trend of the particle concentration changing over time. According to the time series analysis results, the time series change data of the particle concentration is generated, which reflects the change of the particle concentration at different time points. Using the particle concentration time series change data, a heat map generation algorithm (such as Matplotlib, Seaborn, etc.) is used to convert the time series data into a two-dimensional heat map, which can help to more intuitively display the time change of the particle concentration. The color depth of the heat map represents different particle concentrations. The time dimension is usually along the vertical axis of the heat map, while the particle concentration is displayed along the horizontal axis. Based on the particle concentration time series change heat map, image processing technology (such as edge detection, region growing algorithm, etc.) is used to analyze the area where the particle concentration is concentrated. By identifying the darker color (indicating a higher concentration) area in the heat map, the center point of the particle concentration is marked. Select the areas with high particle concentration in the heat map (i.e., hot spots), and determine the center points of these areas. These center points represent the center of particle concentration aggregation, which can provide a basis for subsequent regional division. Based on the center points of particle aggregation, use clustering algorithms (such as K-means, DBSCAN, etc.) to divide the particle concentration heat map into different particle community areas. Each area represents a particle concentration cluster. The particle concentration in these areas is high, which affects the ambient air quality. According to the clustering results, mark the areas with high particle concentration and generate particle cluster area data. The mark of each area should include information such as its range, concentration, and distance from the center point. Using the particle cluster area data, use prediction algorithms (such as regression models, time series prediction models, neural network models, etc.) to predict the concentration of each cluster area. Use historical particle concentration data, weather data (such as temperature, humidity, air pressure), wind speed and other factors as input variables. Predict the concentration changes in the particle cluster area at a certain moment in the future. Generate particle cluster concentration prediction data based on the data output by the prediction model, which reflects the trend of particle cluster concentration changes in a certain period of time in the future. Compare the predicted particle cluster concentration data with the preset standard particle cluster concentration threshold. The standard threshold can be set based on health standards, environmental protection standards, etc. The control system automatically sends a pre-start control signal for the air purification equipment. This signal triggers the early start of the air purification equipment to ensure that the air purification equipment has started working before the particle concentration reaches the warning value. Including information such as start time, start intensity (such as wind speed, air flow), etc., for precise control of air purification equipment. If the particle concentration does not reach the automatic pre-start condition, the control system will wait for manual intervention. By receiving manual operation instructions, manual start control data for air purification equipment is generated.This data will trigger the manual start of the air purification equipment to operate as needed.

[0041] Preferably, performing cluster area concentration prediction on the particulate matter cluster area data includes: Extract the particle cluster distribution characteristics from the particle cluster area data to obtain the particle cluster distribution characteristic data; divide the particle cluster distribution characteristic data into data sets to generate a model training set and a model test set; train the model training set using a long short-term memory neural network algorithm to generate a particle cluster area concentration prediction pre-model; Based on the model test set, the particle matter cluster area concentration prediction pre-model is optimized and iterated to generate a particle matter cluster area concentration prediction model; the particle matter cluster area data is imported into the particle matter cluster area concentration prediction model to perform cluster area concentration prediction and generate particle matter cluster concentration prediction data.

[0042] In an embodiment of the present invention, the characteristics of the particle concentration distribution are extracted from the particle cluster area data, such as the mean, variance, standard deviation, concentration fluctuation, etc. of the particle concentration. The spatial distribution characteristics of the particle concentration, such as the location of the cluster center point, the cluster size and the boundary, etc., are extracted using spatial analysis methods (such as cluster analysis and heat map generation). In addition to spatial characteristics, it is also necessary to extract trend characteristics of particle concentration changes from the time dimension, including daily changes, seasonal fluctuations, etc. Through the above analysis, the particle cluster distribution characteristic data is obtained, which usually includes the following: the concentration change trend of the cluster (time characteristics), the spatial distribution pattern of the cluster (spatial characteristics), and the degree of mutual influence between clusters. The particle cluster distribution characteristic data is divided into a model training set and a model test set according to a certain ratio. The common ratio is 70% for training, 30% for testing, or 80% / 20%, and the specific division ratio can be adjusted according to the size and needs of the data set. The training set is used to train the neural network model, and the test set is used to evaluate the prediction performance and generalization ability of the model. Standardize the data and convert the feature values ​​into a uniform range (e.g., between 0 and 1) to facilitate the training of the neural network model and avoid the influence of features of different dimensions on the training process. Use the particle cluster distribution feature data as the input of the LSTM model. The input data should contain the characteristics of the particle concentration and other environmental factors at historical time points. The LSTM network processes time series data through memory cells and gates, and can capture the dynamic characteristics of particle concentration over time. Predict the future value of the particle cluster concentration. The output layer is usually a fully connected layer, which is used to predict the next concentration of the time series data. Use a suitable loss function (such as mean square error MSE) to measure the difference between the model prediction value and the actual value. Use the gradient descent method (such as Adam optimizer) to train the LSTM model and optimize the network parameters. During the training process, the weights in the LSTM network are updated using the back propagation algorithm to minimize the loss function. The training set data is repeatedly iterated until the loss function of the model converges to a smaller value. Use the test set to evaluate the trained LSTM model and calculate the error between the predicted value and the actual value (such as mean square error MSE, root mean square error RMSE, etc.). Compare the model's prediction results with the actual situation to evaluate the model's accuracy, stability, and generalization ability. If the prediction performance of the test set is not good, the model can be optimized. Specifically, adjust the hyperparameters of the LSTM model, such as the number of layers, number of nodes, and learning rate. If the training data is insufficient, increase the amount of data or use data enhancement techniques (such as time series data smoothing, generative adversarial networks, etc.) to enhance the robustness of the model. Use L2 regularization, dropout, and other techniques to prevent overfitting. Through multiple iterations of training and optimization, continuously improve the performance of the LSTM model on the test set until the model is stable and the prediction accuracy meets the requirements.The particle cluster area data (including the latest particle concentration, environmental parameters, etc.) is input into the trained and optimized LSTM model for prediction. The LSTM model predicts the future particle cluster concentration based on the input data and generates a prediction result. Based on the output of the LSTM model, the prediction data of the particle cluster concentration is generated, which can reflect the changing trend of the particle cluster concentration in the future. The prediction data can be used for air quality prediction, environmental monitoring and regulation and control decisions of air purification equipment.

[0043] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: when the air purification device receives the air purification device pre-start control data or the air purification device manual start control data, it performs multi-stage filtration based on the particle cluster concentration prediction data to generate particle multi-stage filtration data; Step S32: performing local air purification on the area according to the multi-stage filtration data of particulate matter, and generating local air purification adjustment data, wherein the local air purification includes dynamic adjustment of local air purification intensity and dynamic adjustment of local air purification wind speed; Step S33: encapsulate the air purification local adjustment data and the particulate matter multi-stage filtration data into control instructions to generate air purification control instructions; use the air purification instructions to control the functions of the air purification equipment to generate air purification function control data.

[0044] In an embodiment of the present invention, after receiving the pre-start or manual start control data through the air purification device, the air quality state is evaluated according to the particle concentration prediction data of the current environment. The prediction data includes the change trend of the particle concentration, the concentration peak, etc., so as to determine which filtering stages to start. Preliminary filtration mainly removes larger particles (such as PM10, PM2.5, etc.) through the coarse filter. At this time, the air purification device determines whether to start the coarse filtration mode according to the preliminary results of the particle concentration prediction data. For smaller particles, use the HEPA filter to filter PM2.5 and below. Determine whether to start the second stage based on the concentration prediction data. If the particle concentration is high, turn on the advanced filtration mode, such as using an activated carbon filter to remove gaseous pollutants or using the negative ion function to increase the air purification effect. During the multi-stage filtration process, the concentration change of the particles and the operating status of the air purifier (such as wind speed, filter switch) will feedback data in real time to form multi-stage filtration data of particles. The data records the parameters such as the start-up, running time, purification effect, etc. of each filtration stage, which can be used for subsequent adjustment and optimization. According to the multi-stage filtration data of particles, the working state of the air purifier is dynamically adjusted to optimize the air purification effect. According to the particle concentration change data, the filtration intensity of the air purification equipment is adjusted. Specifically, when the particle concentration in the air is high, the filtration intensity of the purifier is enhanced, otherwise it is weakened. The wind speed is adjusted according to the particle concentration data change, and the most appropriate wind speed is set. Specifically, when the particle concentration is high, the wind speed is increased to improve the air exchange efficiency and quickly purify the air. The local adjustment results (such as air purification intensity and wind speed) are recorded to generate air purification local adjustment data. This data includes: adjustment intensity, wind speed, running time and other parameters to ensure that the air purification process can accurately and efficiently respond to changes in particle concentration. The particle multi-stage filtration data and the air purification local adjustment data are combined and encapsulated to form a complete control instruction package. The instruction package contains the working mode, filtration intensity, wind speed and other settings of the air purification equipment. The encapsulation process can use data structures such as JSON or XML to ensure that the transmission and execution of each parameter are clear. The encapsulated air purification control instructions are sent to the air purification equipment to control its working state. The device adjusts various parameters according to the instructions, such as starting a specific filtration mode, adjusting the wind speed, adjusting the working intensity, etc. Finally, the air purification equipment performs corresponding operations according to the instructions and generates air purification function control data, which includes key parameters such as the equipment's operating status, filter replacement cycle, wind speed, and purification intensity. The air purification function control data not only helps to optimize the purification effect in real time, but also provides a basis for subsequent system maintenance and data analysis.

[0045] Preferably, step S31 includes the following steps: Step S311: performing primary filtration simulation calculation according to the startup particulate matter prediction data, thereby obtaining primary filtration particulate matter data; Step S312: performing intermediate filtration dynamic optimization calculation on the primary filtration particulate matter data using multi-dimensional filtration parameters, thereby obtaining intermediate filtration particulate matter data; Step S313: Based on a preset aerodynamic model, an advanced filtering path optimization calculation is performed on the intermediate filtering particulate matter data to obtain advanced filtering particulate matter data; multi-stage filtering is performed on the primary filtering particulate matter data, the intermediate filtering particulate matter data and the advanced filtering particulate matter data to generate multi-stage particulate matter filtering data.

[0046] In an embodiment of the present invention, real-time or predicted particle concentration data is obtained from a particle concentration prediction system. This data usually comes from a sensor or a preset prediction model, covering the type, concentration distribution and change trend of particles. Primary filtration technology (such as a coarse filter, a pre-filter) is used for simulation calculation, and this calculation process estimates the purification effect of the primary filter based on the particle concentration data. The goal of primary filtration is to remove larger particles (such as PM10 and larger particles), and its effect will be optimized and calculated based on the particle size, concentration and filtering capacity of the filter. Based on the primary filtration simulation calculation, the particle data in the air after primary filtration is obtained. This data includes the concentration of removed particles and their characteristics for use in subsequent filtration stages. Multidimensional filtration parameters include wind speed, filter type, filtration accuracy, filter surface area, etc. According to the actual environment and particle concentration data, the optimal multidimensional filtration parameters are set. The dynamic adjustment of parameters is based on environmental data, particle concentration and equipment performance. The filtration parameters that best suit the current air quality conditions are determined through algorithm optimization. The particle data after primary filtration is secondary filtered (for example, through a HEPA filter, an electrostatic filter, etc.). The optimization algorithm is used to dynamically adjust the filtration intensity and wind speed to remove medium-sized particles (such as PM2.5 and smaller particles). The optimization calculation is based on the aerodynamic model, taking into account the filtration capacity of the filter and the movement trajectory of the particles to determine the filtration effect. According to the results of the dynamic optimization calculation, the intermediate filtration particle data is obtained. This data describes the concentration and distribution characteristics of the particles after the second stage of filtration, ready to enter the next filtration stage. Use the preset aerodynamic model (such as fluid dynamics simulation, particle motion simulation, etc.) to simulate the flow path of particles in the air in the filtration system. The model considers the diffusion, sedimentation, and aggregation of particles, and further optimizes the behavior and filtration effect of particles when passing through the filter. The advanced filtration stage usually uses finer filtration materials or technologies (such as ultra-fine filters, activated carbon filters, etc.) to filter and remove tiny particles and gaseous pollutants. Based on the calculation of the aerodynamic model, the advanced filtration path and treatment method are determined to optimize the path of particles through the high-efficiency filter to ensure the maximum purification effect. After the advanced filtration path optimization calculation, the particle data after advanced filtration is obtained. This data will show the concentration of particles after the final filtration and the distribution characteristics of various types of particles. The primary filtration particulate matter data, intermediate filtration particulate matter data and advanced filtration particulate matter data are integrated to form complete multi-stage particulate matter filtration data. This process covers the entire process of particulate matter from coarse filtration, fine filtration to ultra-fine filtration. The filtration data of each stage will be connected in series to ensure the gradual removal of large particles to small particles, and finally obtain purified air. Based on the data of each filtration stage, the final multi-stage particulate matter filtration data is generated. This data not only includes the concentration changes of particulate matter, but also covers the working status of the filter, operating time, equipment energy efficiency and other information.Multi-stage filtration data is used to feed back to the air purification equipment to further adjust the purification process and ensure improved air quality.

[0047] Preferably, performing multi-stage filtering through primary filtering particulate matter data, intermediate filtering particulate matter data, and advanced filtering particulate matter data includes: Based on the particle size separation method, the primary filtration particulate matter data is separated into large particles, thereby obtaining the first-stage filtration data of the particulate matter; the intermediate filtration particulate matter data is analyzed for the particle concentration gradient distribution, and the intermediate filtration particulate matter concentration gradient distribution data is generated; The concentration distribution of the intermediate filtration particulate matter data is homogenized according to the intermediate filtration particulate matter concentration gradient distribution data, thereby obtaining the second stage filtration data of the particulate matter; the surface adsorption rate of the advanced filtration particulate matter data is optimized by the dynamic adsorption method, thereby generating the third stage filtration data of the particulate matter; Multi-stage filtration path interactive optimization calculations are performed on the particulate matter first-stage filtration data, the particulate matter second-stage filtration data, and the particulate matter third-stage filtration data to generate multi-stage filtration path optimization data; multi-stage filtration is performed on the particulate matter cluster concentration prediction data using the multi-stage filtration path optimization data to generate multi-stage filtration data for particulate matter.

[0048] In the embodiment of the present invention, large particles are separated by using a particle size separation method (such as screening, centrifugation, etc.) according to the particle size of the particles. This process mainly removes particles with larger particle sizes, such as PM10 and above. The particles are screened using a filter or a separation device (such as a cyclone separator, a grid screener, etc.) to ensure that larger particles are initially filtered out. The data filtered by the particle size separation method will include the concentration and characteristics of the particles after the large particles are removed. As the first stage filtration data of the particles, these data will enter the subsequent filtration stage to ensure that the particles are continuously purified in the step-by-step filtration. The particle concentration gradient distribution analysis is performed on the particle data after the intermediate filtration. The analysis involves modeling the distribution of particles in the filter and calculating the changes in particle concentration at different locations and time points. The analysis results will reveal the distribution characteristics of the particle concentration inside the filter and help optimize the subsequent filtration process. Based on the concentration gradient analysis, the intermediate filtration particle concentration gradient distribution data is generated. These data provide a basis for the subsequent homogenization process and help determine how to further homogenize the particle concentration. The particle concentration in the intermediate filtration is averaged using an average algorithm (such as an iteration method, a smoothing filter method, etc.). This process is designed to reduce the difference in particle concentration within the filter and ensure a more uniform and effective filtration process. The average algorithm adjusts the wind speed, filtration force and other parameters in the filter according to the particle concentration gradient distribution data to make the particle concentration more balanced. After the average treatment, the particle concentration distribution will be more uniform, and the second-stage filtration data of the particles will be generated. These data represent the characteristics of the particles after the second-stage filtration for subsequent processing. The advanced filtration stage usually uses adsorption materials (such as activated carbon, molecular sieves, etc.) for fine filtration. The dynamic adsorption method is used to optimize the particle treatment to improve the surface contact efficiency between the particles and the adsorption material. The dynamic adsorption method ensures that the adsorption of particles on the filter surface reaches the best state by real-time monitoring of the adsorption rate of the adsorption material and adjusting parameters such as airflow and adsorption bed. Through the optimized dynamic adsorption treatment, the adsorption rate of particles in the advanced filter is improved, and finally the third-stage filtration data of particles are obtained. These data describe the concentration and removal effect of particles after the adsorption method. Combine the first, second and third stage filtration data to perform interactive optimization calculations on the filtration path. This process involves balancing the particle removal efficiency and filter workload between different stages and optimizing the synergy between the stages. Use optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) to analyze the working status of each stage and adjust the filtration strategy to ensure effective coordination between the stages. Generate multi-stage filtration path optimization data through path interactive optimization calculations. This data will guide the system to adjust the operating mode of each filtration stage to ensure that particulate matter can be removed to the maximum extent. Use multi-stage filtration path optimization data to optimize the particle cluster concentration prediction data.The particle cluster concentration prediction data provides the concentration distribution of particles in the air. Combined with the path optimization data, it can accurately predict the air purification effect. Based on the optimized filtration path, multi-stage filtration of the particle cluster concentration prediction data is completed. The final multi-stage filtration data of particles includes the concentration change, removal effect and air quality improvement data of particles after three-stage filtration.

[0049] Preferably, step S4 comprises the following steps: Step S41: performing air purification feedback on the air purification function control data to generate air purification feedback data; performing air quality evaluation on the air purification feedback data to generate purified air quality evaluation data; Step S42: Visualizing the purified air quality assessment data to generate a purified air quality assessment display interface.

[0050] In an embodiment of the present invention, after the air purification device performs air purification function control, the operating state of the device and the change of air quality are monitored in real time. These data include the working parameters of the purification device (such as wind speed, filtering stage, adsorption efficiency, etc.) and the change of the concentration of particulate matter in the air. According to the monitoring data, the purification effect of the device is fed back. The particle concentration, airflow quality and distribution of pollutants in the air after air purification are collected by sensors to generate air purification feedback data. The air purification feedback data includes indicators such as the concentration of purified particulate matter, air circulation speed, and energy efficiency utilization. These feedback data reflect the actual operation effect of the purification device and provide a basis for subsequent evaluation and optimization. Based on the air purification feedback data, the air quality after purification is evaluated using an air quality evaluation algorithm. Commonly used air quality evaluation standards include PM2.5 concentration, PM10 concentration, VOC concentration, CO2 concentration, etc. Through these indicators, the air quality is comprehensively evaluated, and an indexation method (such as AQI index) can be used to quantitatively evaluate the air quality, or multiple air quality indicators can be weighted based on an algorithm to obtain a comprehensive quality score after air purification. According to the evaluation results, the purified air quality evaluation data is generated. These data contain information such as air quality score, purification effect index, and improved pollutant concentration changes, so as to provide users with the status of purified air quality. The air quality evaluation data is converted into easy-to-understand charts, heat maps or images, and a graphical interface is used to display the purified air quality. These display methods include: displaying the purified air quality evaluation score or AQI index. The changes in the concentration of particulate matter, gas, etc. in different time periods are presented in the form of charts. The spatial distribution of indoor air quality after purification is displayed, indicating the air quality level in different areas. The generated visualization data is integrated into the operation interface or user interaction platform of the air purification equipment. Users can view real-time air quality data through smart terminals (such as mobile phones, computers, smart home systems, etc.) to understand the effect of air purification and the operation status of the equipment. The interface should provide real-time updated air quality scores, filtration efficiency, changes before and after purification, and other information to help users make corresponding adjustments or confirm the purification effect.

[0051] In this specification, an intelligent control system based on air purification is provided, which is used to execute the above-mentioned intelligent control method based on air purification. The intelligent control system based on air purification includes: The particle detection module is used to obtain particle data in the area; extract particle concentration characteristics of the particle data in the area to obtain particle concentration characteristic data in the area; perform particle concentration correction on the particle concentration data based on the environmental sensor to generate particle concentration correction data; A startup control module is used to convert the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; divide the particle concentration time series change heat map into particle community areas to generate particle cluster area data; predict the cluster area concentration of the particle cluster area data to generate particle cluster concentration prediction data; divide the startup control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual startup control data; The air filtration module is used to perform multi-stage filtration on the predicted data of particle cluster concentration according to the pre-start control data of the air purification device or the manual start control data of the air purification device to generate multi-stage filtration data of the particle; perform local area air purification on the area according to the multi-stage filtration data of the particle to generate local air purification adjustment data; perform functional control on the local air purification adjustment data and the multi-stage filtration data of the particle to generate air purification function control data; The quality assessment module is used to perform air quality assessment on the air purification function control data to generate purified air quality assessment data; and to visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

[0052] The beneficial effect of the present invention is that by accurately acquiring the particle data in the area and extracting the particle concentration characteristics, the particle characteristics in the area are analyzed. This data precision can provide reliable basic data for subsequent processing. The particle concentration data is corrected by the environmental sensor to ensure the accuracy and stability of the particle concentration data, reduce the impact of external interference on the data, and improve the overall performance of the system. The startup control module can convert the particle concentration time series change data into a heat map and divide the particle community area. This step can effectively identify and locate the aggregation area of ​​particles in the area, providing support for subsequent precise control. By predicting the concentration of the particle cluster area, the system can achieve accurate particle concentration prediction and provide a scientific basis for starting the air purification equipment. This function improves the accuracy of the prediction and ensures the efficiency and timeliness of the air purification process. The air filtration module performs multi-stage filtering on the particle cluster concentration prediction data and adjusts the air purification of the local area according to the filtering data. The system can perform fine processing according to the different stages of the particles to improve the air purification effect. The module ensures continuous optimization of the air quality in the local area by dynamically adjusting the air purification intensity and wind speed. This process is adjusted based on real-time data and predicted information, which enhances the adaptability and efficiency of the system. According to the local adjustment data of air purification and the multi-stage filtration data of particulate matter, the system can achieve precise function control and automatically adjust the operation mode of the air purification equipment. This automated control greatly reduces the need for manual intervention and improves the convenience and accuracy of operation. The startup control module generates pre-start and manual startup control data based on the particle concentration prediction data, ensures the timely startup of the air purification equipment, avoids unnecessary delays, and improves the response speed of air quality adjustment. The quality evaluation module evaluates the air purification function control data in real time and generates the purified air quality evaluation data, which provides a dynamic feedback mechanism for the system, can adjust the operation in time, and ensure continuous improvement of air quality. Therefore, the present invention improves the accuracy and flexibility of air purification equipment control by introducing technologies such as particle concentration correction, time series change heat map analysis, multi-stage filtration and intelligent control.

[0053] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0054] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent control method based on air purification, characterized in that: The following steps are involved: Step S1: acquiring particulate matter data in the area; extracting particulate matter concentration characteristics from the particulate matter data in the area to obtain particulate matter concentration characteristic data in the area; Performing particle concentration correction on particle concentration data based on an environmental sensor to generate particle concentration correction data; Step S2: converting the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; dividing the particle concentration time series change heat map into particle community regions to generate particle cluster region data; predicting the cluster region concentration of the particle cluster region data to generate particle cluster concentration prediction data; dividing the start control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual start control data; Step S3: performing multi-stage filtering on the particle cluster concentration prediction data according to the air purification device pre-start control data or the air purification device manual start control data to generate particle multi-stage filtering data; performing local area air purification on the area according to the particle multi-stage filtering data to generate air purification local adjustment data; performing functional control on the air purification local adjustment data and the particle multi-stage filtering data to generate air purification function control data; Step S4: Perform air quality assessment on the air purification function control data to generate purified air quality assessment data; visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

2. The intelligent control method based on air purification according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: obtaining particulate matter data in the area through a particulate matter sensor; Step S12: extracting particle concentration characteristics from the particle data in the area to obtain particle concentration characteristic data in the area; Step S13: performing data preprocessing on the particle concentration characteristic data in the area to generate standard particle concentration data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization; Step S14: performing particle concentration correction on the standard particle concentration data based on the environmental sensor to generate particle concentration correction data.

3. The intelligent control method based on air purification according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: performing particle concentration influence analysis on the standard particle concentration data to generate particle concentration influence data, wherein the particle concentration influence data includes temperature influence data, humidity influence data and air pressure influence data; Step S142: screening the corresponding environmental sensor data according to the temperature influence data, the humidity influence data and the air pressure influence data, and obtaining the particle temperature collection data, the particle humidity collection data and the particle pressure collection data respectively; Step S143: performing a particle concentration diffusion characteristic analysis on the standard particle concentration data through the particle temperature collection data to generate particle diffusion characteristic data; performing a particle concentration hygroscopic characteristic analysis on the standard particle concentration data through the particle humidity collection data to generate particle hygroscopic characteristic data; performing a particle settling characteristic analysis on the standard particle concentration data through the particle pressure collection data to generate particle settling characteristic data; Step S144: using the particle diffusion characteristic data, the particle hygroscopic characteristic data and the particle settling characteristic data to perform particle concentration correction on the standard particle concentration data to generate particle concentration correction data.

4. The intelligent control method based on air purification according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing time series change analysis on the particle concentration correction data to generate particle concentration time series change data; performing heat map conversion on the particle concentration time series change data to generate a particle concentration time series change heat map; Step S22: marking the particle concentration time series change heat map with the particle concentration aggregation center point to obtain the particle concentration center point; dividing the particle concentration time series change heat map into particle cluster areas based on the particle concentration center point to generate particle cluster area data; Step S23: performing cluster area concentration prediction on the particle matter cluster area data to generate particle matter cluster concentration prediction data; comparing the particle matter cluster concentration prediction data with a preset standard particle matter cluster concentration threshold, and when the particle matter cluster concentration prediction data is greater than or equal to the preset standard particle matter cluster concentration threshold, performing pre-start control on the air purification device to generate air purification device pre-start control data; Step S24: When the particle cluster concentration prediction data is less than the preset standard particle cluster concentration threshold, a manual start control instruction is received for the air purification device, thereby generating manual start control data for the air purification device.

5. The intelligent control method based on air purification according to claim 4 is characterized in that: Cluster area concentration prediction for particulate matter cluster area data includes: Extract the particle cluster distribution characteristics from the particle cluster area data to obtain the particle cluster distribution characteristic data; divide the particle cluster distribution characteristic data into data sets to generate a model training set and a model test set; train the model training set using a long short-term memory neural network algorithm to generate a particle cluster area concentration prediction pre-model; Based on the model test set, the particle matter cluster area concentration prediction pre-model is optimized and iterated to generate a particle matter cluster area concentration prediction model; the particle matter cluster area data is imported into the particle matter cluster area concentration prediction model to perform cluster area concentration prediction and generate particle matter cluster concentration prediction data.

6. The intelligent control method based on air purification according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: when the air purification device receives the air purification device pre-start control data or the air purification device manual start control data, it performs multi-stage filtration based on the particle cluster concentration prediction data to generate particle multi-stage filtration data; Step S32: performing local air purification on the area according to the multi-stage filtration data of particulate matter, and generating local air purification adjustment data, wherein the local air purification includes dynamic adjustment of local air purification intensity and dynamic adjustment of local air purification wind speed; Step S33: encapsulate the air purification local adjustment data and the particulate matter multi-stage filtration data into control instructions to generate air purification control instructions; use the air purification instructions to control the functions of the air purification equipment to generate air purification function control data.

7. The intelligent control method based on air purification according to claim 6 is characterized in that: Step S31 includes the following steps: Step S311: performing primary filtration simulation calculation according to the startup particulate matter prediction data, thereby obtaining primary filtration particulate matter data; Step S312: performing intermediate filtration dynamic optimization calculation on the primary filtration particulate matter data using multi-dimensional filtration parameters, thereby obtaining intermediate filtration particulate matter data; Step S313: Based on a preset aerodynamic model, an advanced filtering path optimization calculation is performed on the intermediate filtering particulate matter data to obtain advanced filtering particulate matter data; multi-stage filtering is performed on the primary filtering particulate matter data, the intermediate filtering particulate matter data and the advanced filtering particulate matter data to generate multi-stage particulate matter filtering data.

8. The intelligent control method based on air purification according to claim 7 is characterized in that: Multi-stage filtration through primary filter particulate matter data, intermediate filter particulate matter data and advanced filter particulate matter data includes: Based on the particle size separation method, the primary filtration particulate matter data is separated into large particles, thereby obtaining the first-stage filtration data of the particulate matter; the intermediate filtration particulate matter data is analyzed for the particle concentration gradient distribution, and the intermediate filtration particulate matter concentration gradient distribution data is generated; The concentration distribution of the intermediate filtration particulate matter data is homogenized according to the intermediate filtration particulate matter concentration gradient distribution data, thereby obtaining the second stage filtration data of the particulate matter; the surface adsorption rate of the advanced filtration particulate matter data is optimized by the dynamic adsorption method, thereby generating the third stage filtration data of the particulate matter; Multi-stage filtration path interactive optimization calculations are performed on the particulate matter first-stage filtration data, the particulate matter second-stage filtration data, and the particulate matter third-stage filtration data to generate multi-stage filtration path optimization data; multi-stage filtration is performed on the particulate matter cluster concentration prediction data using the multi-stage filtration path optimization data to generate multi-stage filtration data for particulate matter.

9. The intelligent control method based on air purification according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing air purification feedback on the air purification function control data to generate air purification feedback data; performing air quality evaluation on the air purification feedback data to generate purified air quality evaluation data; Step S42: Visualizing the purified air quality assessment data to generate a purified air quality assessment display interface.

10. An intelligent control system based on air purification, characterized in that: Used to execute the intelligent control method based on air purification as claimed in claim 1, the intelligent control system based on air purification comprises: The particle detection module is used to obtain particle data in the area; extract particle concentration characteristics of the particle data in the area to obtain particle concentration characteristic data in the area; perform particle concentration correction on the particle concentration data based on the environmental sensor to generate particle concentration correction data; A startup control module is used to convert the particle concentration correction data into a heat map to generate a particle concentration time series change heat map; divide the particle concentration time series change heat map into particle community areas to generate particle cluster area data; predict the cluster area concentration of the particle cluster area data to generate particle cluster concentration prediction data; divide the startup control of the air purification equipment based on the particle cluster concentration prediction data to generate air purification equipment pre-start control data and air purification equipment manual startup control data; The air filtration module is used to perform multi-stage filtration on the predicted data of particle cluster concentration according to the pre-start control data of the air purification device or the manual start control data of the air purification device to generate multi-stage filtration data of the particle; perform local area air purification on the area according to the multi-stage filtration data of the particle to generate local air purification adjustment data; perform functional control on the local air purification adjustment data and the multi-stage filtration data of the particle to generate air purification function control data; The quality assessment module is used to perform air quality assessment on the air purification function control data to generate purified air quality assessment data; and to visualize the purified air quality assessment data to generate a purified air quality assessment display interface.

Images