Sensor control method of air purification system

Abstract

The invention relates to a sensor control method of an air purification system. The pollutant concentration gradient is monitored in real time by combining initial distribution of the sensors, and a pollutant diffusion path is simulated by utilizing a fluid dynamic model; a pollutant source is reversely deduced through sensor data, and the acquisition range of the sensor is dynamically changed; the method comprises the following steps: acquiring multi-dimensional data through physical sensors including particulate matters, temperature and humidity and chemical sensors including VOC and harmful gas, and extracting pollutant characteristics by utilizing PCA (principal component analysis); constructing hazard indexes of pollutants including AQI grading standards, and dynamically evaluating the priority of the pollutants in combination with real-time monitoring data of a sensor; for pollutants with different priorities, resources of the air purification system are distributed, and the air volume of a filter, the adsorption strength of activated carbon and the turn-on time of an ultraviolet germicidal lamp are adjusted; a self-adaptive calibration algorithm is introduced, and sensor output including interference correction of temperature and humidity on the particulate matter sensor is adjusted in real time according to the environment reference value; and dynamically adjusting the maintenance and replacement period of the sensor.

Description

Technical Field

[0001] The invention relates to the field of air purification, and in particular to a sensor control method for an air purification system. Background Art

[0002] Although the sensor control methods currently used in air purification systems can provide solutions for environmental monitoring and air purification to a certain extent, there are still some obvious deficiencies and drawbacks, which restrict their effectiveness and wide promotion in practical applications. First of all, most traditional air purification system sensors are deployed statically, that is, a fixed number and type of sensors are placed at specific locations. This static deployment cannot dynamically respond to environmental changes and is prone to monitoring blind spots. Especially when there is a sudden change in the air pollution source or pollutant concentration, it is difficult for the system to respond in time. For example, when the diffusion path of the air pollution source changes, the fixed sensor cannot adjust its position and density in real time, resulting in incomplete monitoring of pollutant concentrations, which in turn affects the precise control of the air purification system.

[0003] Secondly, existing sensor control methods usually lack sufficient intelligence and adaptive capabilities. Most systems simply control the operation of purification equipment based on the concentration data of certain specific pollutants in the air, while ignoring the diffusion path of pollutants, the rate of concentration change, and the relative degree of harm between different pollutants. In this way, the system will start high-intensity purification equipment when the pollutant concentration is low or changes slowly, while when the pollutant concentration is high and the diffusion is rapid, the response of the equipment is not timely or strong enough, resulting in reduced purification efficiency and waste of resources. Furthermore, most of the current air purification sensors rely on the monitoring of a single pollutant, ignoring the interaction of various pollutants in air quality. Pollutants in the air are usually diverse, such as PM2.5, nitrogen dioxide (NO2), carbon monoxide (CO), volatile organic compounds (VOCs), etc., and different pollutants have different degrees of harm to health, and their diffusion characteristics and interactions are also quite different. However, the existing sensor control method fails to comprehensively consider these diverse pollutants and their interactions with environmental factors (such as wind speed, temperature, humidity, etc.), resulting in the system's failure to fully evaluate the true state of air quality, and lack of scientificity in the scheduling and use of purification resources, which ultimately affects the purification effect and the overall performance of the system. In addition, most current sensor control methods rely on simple monitoring data to control the on / off of air purification equipment, but lack in-depth analysis based on fluid dynamics or pollutant diffusion models. The diffusion process of pollutants is not only affected by air flow, but also closely related to factors such as temperature and humidity. Existing systems often ignore the interaction of these complex factors and cannot accurately predict the distribution changes of pollutants in different environments.

[0004] Even if some systems can monitor and predict according to the location of pollution sources, they usually rely on static pollutant diffusion models, ignore the dynamic characteristics of air quality, and cannot make timely adjustments when sudden pollution sources or pollutant concentrations fluctuate greatly. In addition, most sensor controls in existing air purification systems cannot achieve intelligent resource allocation. Air purification equipment usually has multiple working parameters, such as air volume, filter performance, activated carbon adsorption intensity, ultraviolet lamp switching time, etc. These parameters have an important impact on the purification effect of different pollutants. However, most current air purification systems fail to dynamically adjust these working parameters based on factors such as pollutant concentration, change rate, diffusion path and priority. In this way, when the concentration of certain pollutants is high, the system will adjust multiple parameters, resulting in a waste of resources. When the concentration of pollutants is low, the system ignores the purification needs of some key pollutants and cannot ensure good air quality. Summary of the invention

[0005] The purpose of the present invention is to provide a sensor control method for an air purification system, so as to solve some of the drawbacks and shortcomings pointed out in the background technology; the present invention adopts the following technical solutions to solve the above-mentioned technical problems: the sensor control method for an air purification system comprises: S1, dynamic deployment of sensors based on the diffusion law of pollutants:

[0006] S1.1. Combined with the initial distribution of sensors, the pollutant concentration gradient is monitored in real time, and the pollutant diffusion path is simulated using a fluid dynamics model;

[0007] S1.2. Infer the source of pollutants through sensor data and dynamically change the sensor collection range;

[0008] S2. Multidimensional modeling of pollutant characteristics and decoupling of sensor signals:

[0009] S2.1. Obtain multidimensional data through physical sensors including particulate matter, temperature and humidity, and chemical sensors including VOC and harmful gases, and extract pollutant characteristics using principal component analysis (PCA);

[0010] S2.2, design a decoupling model and use blind source separation technology to separate the characteristics of each pollutant from the sensor composite signal;

[0011] S3, multi-level response control driven by pollutant priority:

[0012] S3.1. Construct a hazard index for pollutants including AQI grading standards, and dynamically evaluate pollutant priorities based on real-time sensor monitoring data;

[0013] S3.2. Allocate resources of the air purification system according to pollutants of different priorities, including adjusting the filter air volume, activated carbon adsorption intensity and UV germicidal lamp opening time;

[0014] S4. Data-driven sensor health management:

[0015] S4.1. Build a sensor data anomaly detection mechanism and analyze the sensor operation status through machine learning algorithms;

[0016] S4.2, introduce an adaptive calibration algorithm to adjust the sensor output including the interference correction of temperature and humidity on the particle sensor in real time according to the environmental reference value;

[0017] S4.3. Dynamically adjust sensor maintenance and replacement cycles based on sensor health status prediction results;

[0018] S5. Sensor energy consumption management with multi-objective collaborative optimization:

[0019] S5.1. Record the energy consumption characteristics of the sensor at different sampling frequencies and establish a mapping model between energy consumption and monitoring accuracy;

[0020] S5.2. Dynamically adjust the sampling frequency and operating mode based on pollutant priority, monitoring range, and sensor health status.

[0021] Furthermore, the sensor dynamic deployment method based on pollutant diffusion law includes:

[0022] Each sensor collects real-time data on the concentration of pollutants in the air and transmits the data to the control center. The control center updates the fluid dynamics model of pollutant diffusion based on real-time sensor data and environmental conditions including temperature, humidity, and wind speed, and calculates the diffusion path and concentration changes of pollutants in the air. The fluid dynamics model establishes an equation based on the time change of pollutant concentration and diffusion speed, which is described by the following control equation:

[0023]

[0024] Among them, ΔC(x,t) represents the rate of change of pollutant concentration at position x and time t, reflecting the change of pollutant concentration over time; C(x,t) is the pollutant concentration, describing the pollutant concentration value at position x and time t; D(x) is the diffusion coefficient of the pollutant, indicating the ability of the pollutant to diffuse in the air. The value is usually related to the ambient temperature and humidity factors, reflecting the rate at which the pollutant diffuses from the high concentration area to the low concentration area; is the diffusion term, where represents the spatial gradient operator, represents the divergence operator, which calculates the spatial change rate of pollutant concentration; S(x,t) is the pollution source term, which represents the amount of pollutants released by the pollution source per unit time.

[0025] Furthermore, the sensor dynamic deployment method based on pollutant diffusion law includes:

[0026] By calculating the pollutant concentration gradient, the diffusion direction of the pollutants and the location of the pollution source are evaluated; the pollutant concentration gradient calculation is based on the output of the fluid dynamics model, combined with the actual data collected by the sensor, to predict and evaluate the pollution source and diffusion path; and the calculation of the pollutant concentration gradient uses the following calculus formula:

[0027]

[0028] in, It represents the gradient of pollutant concentration at position x and time t, reflecting the degree to which pollutant concentration changes with spatial position, that is, the concentration difference of pollutants diffused from a certain position to an adjacent position in space; It represents the spatial first-order derivative of the pollutant concentration C at position x, reflecting the rate of change of the concentration at different positions; is an integral operation, representing the cumulative effect of concentration changes over time.

[0029] Furthermore, the sensor dynamic deployment method based on pollutant diffusion law includes:

[0030] According to the real-time calculated pollutant concentration gradient and diffusion path, the position and number of sensors are dynamically adjusted to optimize the density distribution of sensors. The process of dynamically optimizing sensor deployment is adjusted through the following formula:

[0031]

[0032] Where N(x,t) represents the sensor density at location x and time t, the number of sensors at the location or the deployment frequency; ΔC(x,t) is the change in pollutant concentration, which represents the change in the concentration of the pollutant in area x and time t; ΔC max It is the concentration change limit preset by the system, used to standardize the effect of concentration change; It is an integral operation in space, reflecting the cumulative effect of changes in pollutant concentration in the region [x0, x].

[0033] Furthermore, the pollutant priority-driven multi-level response control method includes:

[0034] By monitoring the concentration changes, diffusion paths, and health hazards of different pollutants, each pollutant is assigned a priority coefficient; the priority of pollutants changes dynamically over time. Based on the comprehensive consideration of pollutant concentration and environmental factors, the priority evaluation formula is:

[0035]

[0036] The priority evaluation formula is used to evaluate the priority P of pollutant i at time t. i (t); By weighted integration of pollutant concentration, concentration change rate and diffusion characteristics, the priority of pollutants is comprehensively calculated; C i (t′) represents the concentration of pollutant t at time t′, reflecting the current pollution level of the pollutant; R i (t′) is the pollutant i The concentration change rate indicates the speed of concentration change and reflects the diffusion rate of pollutants; D i (t′) is the diffusion characteristic of the pollutant; λ1, λ2, λ3 are weight coefficients used to adjust the influence of concentration, change rate and diffusion characteristics on priority; a, b, c are exponents that control the nonlinear influence of concentration, change rate and diffusion characteristics on priority.

[0037] Furthermore, the pollutant priority-driven multi-level response control method includes:

[0038] A multidimensional mapping control model between pollutant concentration and purification equipment processing efficiency is introduced; the multidimensional mapping control model includes pollutant concentration, purification equipment processing capacity and environmental factors, and adaptively adjusts the working state of the purification equipment within different pollutant concentration ranges; the multidimensional mapping control formula is:

[0039]

[0040] The multidimensional mapping control formula is used to calculate the treatment efficiency E of pollutant i at time t. i (t), and establish the relationship between pollutant concentration and purification equipment efficiency through integration; where C i (t) is the concentration of pollutant i at time t, indicating the current concentration level of the pollutant; α and β are parameters that control the amplitude and decay rate of the exponential decay part respectively; γ and δ are parameters that control the amplitude and periodic change of the cosine function part, representing the periodic adjustment of the treatment efficiency within the concentration change range; the upper and lower limits of the integral are 0 and C i (t), and the treatment efficiency is calculated over the range of pollutant concentrations by integration.

[0041] Furthermore, the pollutant priority-driven multi-level response control method includes:

[0042] A system based on fluid dynamics model and pollutant diffusion prediction algorithm is introduced to simulate the diffusion path and concentration changes of pollutants. By considering the distribution and intensity of pollution sources and meteorological conditions including wind speed, temperature and humidity, the diffusion process of pollutants in the air is dynamically simulated, and the future distribution of pollutants is predicted. Diffusion simulation and prediction formula:

[0043]

[0044] The diffusion simulation and prediction formula describes the pollutants In space The diffusion and migration process under time t is combined with the principles of fluid dynamics to simulate the diffusion path and concentration changes of pollutants; It's location and the pollutant concentration at time t, reflecting the distribution of pollutants in space; It's location and the pollutant diffusion coefficient at time t, which reflects the diffusion capacity of pollutants; is the air velocity vector, which indicates the migration rate of pollutants with the air flow; is the intensity of the pollution source, describing the rate at which pollutants are produced; is the gradient operator, which is used to calculate the rate of change of concentration in space, It represents the divergence operation of the diffusion flow and represents the diffusion trend of pollutants.

[0045] Furthermore, the pollutant priority-driven multi-level response control method includes:

[0046] Adopting an adaptive resource allocation mechanism, the working parameters of the air purification system are dynamically adjusted according to the priority, concentration and diffusion prediction of pollutants; the filter air volume, activated carbon adsorption intensity and ultraviolet light switch time resources are dynamically adjusted based on the concentration, health impact and diffusion trend of pollutants. The resource allocation model formula is:

[0047]

[0048] The resource allocation model formula is used to calculate the resource allocation amount R required for pollutant i at time t. i (t), adjust the resource allocation of purification equipment based on the priority of pollutants; where P j (t) is the priority of pollutant j at time t, reflecting the urgency of pollutant treatment; α j is the weighting coefficient, which indicates the contribution of pollutant j to the resource allocation of purification equipment; β is the overall resource adjustment coefficient, which is used to control the total amount of resource allocation; n represents the number of pollutants, and the model considers the weighted sum of the priorities of all pollutants.

[0049] The sensor control method of the air purification system of the present invention combines pollutant concentration monitoring, dynamic resource allocation, pollutant diffusion prediction and priority-driven multi-level response control, effectively improving the intelligence and adaptive ability of the air purification system. Its beneficial effects can be summarized as follows:

[0050] Through real-time monitoring and diffusion prediction based on pollutant concentration, the system can timely obtain the concentration changes and diffusion paths of pollutants in the air and dynamically adjust the location and number of sensors. This adaptive deployment method can ensure that areas with changing pollutant concentrations are fully covered, thereby improving monitoring accuracy and response speed.

[0051] By evaluating the concentration, change rate and diffusion characteristics of pollutants, the control method of the present invention can assign different priorities to different pollutants. Combining pollutant concentration, priority and diffusion prediction, the system can intelligently adjust resource allocation and optimize the working parameters of air purification equipment (such as filter air volume, activated carbon adsorption intensity and ultraviolet lamp switching time, etc.). BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 The figure is a flow chart of the sensor control method of the air purification system of the present invention.

[0053] Figure 2 This is a flow chart of the sensor dynamic deployment method based on the pollutant diffusion law of the present invention.

[0054] Figure 3 This is a flow chart of the pollutant priority-driven multi-level response control method of the present invention. DETAILED DESCRIPTION

[0055] The specific implementation modes of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0056] Combined with Figure 1 The sensor control method of the air purification system of the present invention first optimizes the response capability of the system through the dynamic deployment of sensors based on the diffusion law of pollutants. Step S1 aims to monitor the changes in pollutant concentrations in real time and simulate the pollutant diffusion path in combination with a fluid dynamics model, and dynamically adjust the distribution of sensors based on this to ensure that the system can work efficiently under different environmental conditions.

[0057] S1.1. Combined with the initial distribution of sensors, the pollutant concentration gradient is monitored in real time, and the pollutant diffusion path is simulated using a fluid dynamics model. The distribution of pollutants in the air is constantly changing, usually affected by multiple factors such as wind speed, temperature, and humidity, so the concentration of pollutants forms a gradient in space. When the sensors are initially deployed, they are laid out according to the expected location and diffusion characteristics of the pollutant source, but as air flow and meteorological conditions change, the distribution of pollutants will also change. In order to adapt to this dynamic change, this method adopts the method of real-time monitoring of the pollutant concentration gradient. The sensor can sense the changes in the pollutant concentration in the surrounding environment in real time, and simulate the diffusion path of the pollutant based on this data. The fluid dynamics model plays an important role here, and can simulate the characteristics of air flow, the diffusion rate of pollutants, and how pollutants flow and diffuse to different areas with the wind. This model usually includes parameters such as the diffusion coefficient of pollutants in the airflow and wind speed. By calculating these parameters, the diffusion path of pollutants from the source to various areas can be predicted, thereby providing a scientific basis for adjusting the sensor layout. Through this dynamic deployment, sensors can more accurately capture the distribution of pollutants in space, ensuring that sensors can collect data in areas with the most concentrated pollutant concentrations at all times, thereby improving detection sensitivity and response speed.

[0058] S1.2. Infer the source of pollutants through sensor data and dynamically change the sensor collection range. The data collected by the sensor not only reflects the concentration of pollutants in the current area, but also provides time series information on the diffusion of pollutants. Through the analysis of sensor data, the source location of pollutants can be further inferred. Specifically, the concentration change, diffusion rate and time difference of pollutants can provide a basis for the location of pollution sources. Assuming that the diffusion of pollutants presents a certain regularity, the sensor can infer the initial release point of pollutants and the intensity of the pollution source based on the collected concentration data. This process usually combines the reverse diffusion model and the time series analysis method to gradually determine the location and intensity of the pollution source by simulating the propagation process of pollutants from the source to the sensor. Once the pollution source is determined, the system can dynamically adjust the sensor collection range according to the location of the pollutant source, so that the sensor can more intensively monitor the area around the pollutant source. This dynamic adjustment process not only optimizes the utilization of resources, but also improves the accuracy and response speed of the system. For example, if the sensor detects that the pollution concentration in a certain area is rising rapidly, the system can quickly infer the source of the pollutant and conduct intensive monitoring of the source area to ensure that changes are captured in time. This approach enables the air purification system to adjust the position and collection range of the sensor in a timely manner according to changes in pollutant diffusion, thereby improving the effect and efficiency of air purification.

[0059] The S2 step aims to further improve the system's ability to accurately monitor and process pollutants through the decoupling of multidimensional modeling of pollutant characteristics and sensor signals. During the air purification process, sensors usually collect composite signals from multiple pollutant sources, which include multidimensional data measured by physical sensors and chemical sensors. Therefore, how to extract independent characteristics of pollutants and accurately reflect their concentrations and types is the key to improving system accuracy and response speed. Step S2.1 obtains multidimensional data of pollutants by using different types of sensors, including physical sensor data of particulate matter, temperature and humidity, and chemical sensor data of volatile organic compounds (VOCs), harmful gases, etc. In order to extract the most representative pollutant features from these multidimensional data, the present invention adopts the principal component analysis (PCA) method. Principal component analysis is a data processing technology commonly used for dimensionality reduction. By linearly transforming multidimensional data, redundant information in the original data can be removed, and the principal components that best represent the data characteristics can be extracted, thereby reducing the complexity of the data and retaining important information. Specifically, in the air purification system, PCA can convert multidimensional sensor data into fewer principal components, and can effectively focus on the main influencing factors of pollutants, such as particulate matter concentration, volatile organic compound concentration, and air humidity and temperature, so as to improve the accuracy and efficiency of the system in data analysis and decision-making. S2.2 step designs a decoupling model, and adopts blind source separation technology to process the composite signal collected by the sensor. Because in the application, the signal collected by the sensor is usually a superposition signal of multiple pollutants, there is mutual interference and overlap between these signals, and it is difficult for traditional signal processing methods to effectively separate the independent signal characteristics of each pollutant. In order to solve this problem, the present invention introduces blind source separation (BSS) technology, especially independent component analysis (ICA) or non-negative matrix decomposition (NMF) and other methods, by utilizing the statistical characteristics of the signal, such as signal independence, non-Gaussianity, etc., it is possible to separate the independent signal of each pollutant from the composite signal of the sensor without knowing the pollutant source signal. Through blind source separation technology, the system can disassemble the multiple signals collected by the sensor into independent pollutant concentration signals, thereby accurately reflecting the concentration and change trend of each pollutant. The innovation of this technology lies in the fact that it can extract effective pollutant information from complex signals without the need for prior modeling of pollutant sources and sensor response functions, thereby improving the monitoring accuracy and adaptability of the system, and can efficiently separate different pollutant signals, improving the system's real-time response capability and purification efficiency.

[0060] The S3 step aims to dynamically adjust the resource allocation and operation of the purification system according to the degree of harm and concentration changes of pollutants through multi-level response control driven by pollutant priority. Step S3.1 first constructs a pollutant hazard index and evaluates different pollutants in combination with the air quality index (AQI) classification standard. Specifically, the hazard index not only considers the concentration of pollutants, but also comprehensively evaluates factors such as the type of pollutants, exposure time, and harm to human health. The system dynamically calculates the hazard index of pollutants based on the pollutant data monitored in real time by the sensor, and evaluates the priority of various pollutants based on the index. Pollutants with high priority usually refer to those that are more harmful to human health, or those with high current concentrations and rapid diffusion, such as PM2.5, nitrogen dioxide (NO2), ozone (O3), etc. These pollutants will be given a higher priority and processed first. Traditional air purification systems generally operate according to preset standards or fixed thresholds, while the present invention monitors pollutant data in real time and dynamically adjusts priorities, so that the system can flexibly adjust the purification strategy according to the actual pollution situation, thereby improving purification efficiency and response speed. Step S3.2 dynamically adjusts the resource allocation of the air purification system according to the priority of the pollutants to ensure that high-priority pollutants can be treated in a timely and effective manner. Specifically, the system can optimize resource allocation by adjusting the air volume of the filter, the adsorption strength of the activated carbon, and the opening time of the ultraviolet germicidal lamp. For high-priority pollutants, the system can increase the air volume of the filter to increase the air flow and further improve the removal efficiency of pollutants in the air; at the same time, the adsorption strength of the activated carbon can be enhanced to improve its adsorption capacity for harmful gases, especially for the removal of pollutants such as volatile organic compounds (VOCs). The opening time of the ultraviolet germicidal lamp can also be adjusted according to the type and concentration of the pollutant. For high-concentration microbial contamination, the irradiation time of the ultraviolet lamp can be extended to enhance the sterilization effect.

[0061] Step S4 aims to ensure the continuous and accurate operation of each sensor in the system and optimize its performance and service life through data-driven sensor health management. Step S4.1 first constructs a sensor data anomaly detection mechanism, which relies on a machine learning algorithm to analyze the operating status of the sensor. As a core component of the air purification system, the sensor may experience performance degradation or data anomalies due to environmental factors, aging, damage, etc. In order to detect these problems in a timely manner, the present invention uses machine learning technology, such as a classification model in supervised learning, to train a model that can identify abnormal data patterns based on historical data and real-time monitoring data. When the output value of the sensor deviates from the normal range, the model can promptly identify and issue an alarm signal to prompt the system operator to check the health of the sensor, thereby avoiding air quality monitoring errors caused by sensor failure or inaccurate data. Step S4.2 introduces an adaptive calibration algorithm, which aims to eliminate interference with sensor performance due to environmental factors by adjusting the output value of the sensor in real time. For example, changes in temperature and humidity will affect the sensitivity of the particle sensor. Therefore, the system will adjust the calibration parameters of the sensor in real time based on environmental reference values, such as the current air temperature and humidity, to ensure that the value output by the sensor is consistent with the actual pollutant concentration. This process is completed through an adaptive algorithm without the need for human intervention, allowing the system to operate stably under different environmental conditions and improving the accuracy and reliability of the sensor. Step S4.3 dynamically adjusts the maintenance and replacement cycle of the sensor based on the prediction results of the sensor's health status. By continuously tracking and analyzing the sensor's historical operating data and combining the machine learning algorithm's prediction of the sensor's health status, the system can predict the sensor's failure trend and life cycle. In this way, the system can reasonably arrange regular maintenance, calibration, and replacement of the sensor based on its actual status, avoiding data loss or accuracy loss due to sensor failure, and ensuring the stability and accuracy of the system in long-term operation.

[0062] Step S5 achieves a balance between the energy consumption management and monitoring accuracy of the sensor through multi-objective collaborative optimization to improve the efficiency of the system and reduce energy consumption. Step S5.1 first requires recording the energy consumption characteristics of the sensor at different sampling frequencies. The energy consumption of the sensor is usually proportional to its sampling frequency, that is, the higher the sampling frequency, the greater the power consumption of the sensor, but at the same time, the increase in sampling frequency will improve the accuracy and timeliness of the monitoring data. In order to effectively manage the energy consumption of the sensor, the present invention designs a mapping model between energy consumption and monitoring accuracy. Through this model, the system can quantify the impact of different sampling frequencies on energy consumption and data accuracy. The model associates the energy consumption of the sensor with factors such as its working mode, sampling frequency and monitoring accuracy, and uses statistical analysis methods or machine learning algorithms to establish an accurate energy consumption-accuracy model based on the actual energy consumption and accuracy data of the sensor at different sampling frequencies. The establishment of this model enables the system to better understand how to adjust the sampling frequency to achieve the best energy efficiency ratio under different working conditions, which can not only maintain a certain monitoring accuracy, but also reduce unnecessary energy consumption. Step S5.2 dynamically adjusts the sampling frequency and working mode of the sensor based on multiple factors such as pollutant priority, monitoring range, and sensor health status. Specifically, the system adjusts the working mode of the sensor according to the priority of the pollutant. For example, when the pollutant concentration is high, the system will increase the sampling frequency of the sensor to ensure that it can track the changes in pollutants in real time; when the pollutant concentration is low, the system will reduce the sampling frequency to save energy. At the same time, the system will also optimize and adjust according to the health status of the sensor. If some sensors fail or their performance degrades, the system will reduce their workload, adjust their sampling frequency, or temporarily switch to low power mode to extend their service life and reduce energy consumption.

[0063] Embodiment 1:

[0064] See also Figure 2 Process, in this embodiment, in the air purification system of the present invention, the sensor control method optimizes the monitoring effect and response speed of the system through dynamic deployment based on the law of pollutant diffusion. Taking the application scenario as an example, set in an office building, the system deploys a series of sensors to monitor indoor air quality. These sensors can collect concentration data of various pollutants in the air (such as PM2.5, CO2, TVOCs, etc.) in real time, and transmit these data to the central control center. The control center updates the fluid dynamics model of pollutant diffusion based on real-time sensor data and external environmental conditions (including temperature, humidity, wind speed, etc.), and calculates the diffusion path and concentration changes of pollutants in the air. This process is described by a mathematical model, and the specific mathematical expression is:

[0065]

[0066] In this equation, ΔC(x, t) represents the rate of change of pollutant concentration at position x and time t, reflecting the dynamic change of pollutant concentration over time; C(x, t) is the pollutant concentration, describing the pollutant concentration at a specific position x and time t; D(x) is the diffusion coefficient of the pollutant, indicating the diffusion capacity of the pollutant in the air; and the diffusion term The spatial rate of change of pollutant concentration is calculated by the gradient operator. Finally, S(x,t) is the pollution source term, which represents the amount of pollutant released per unit time.

[0067] Set in an office with a pollution source, the source of the pollution is a printer, which is emitting harmful gases and particulate matter. There are multiple sensors in the office, which are distributed in different areas, and the deployment positions will be dynamically adjusted according to the real-time monitoring data to optimize the monitoring coverage.

[0068] After the sensor collects the data, the control center first calculates the diffusion coefficient D(x) of the pollutant according to the environmental conditions in the formula (such as temperature 25℃, humidity 60%, wind speed 1.5m / s). In this example, the diffusion coefficient is set to be linearly related to the ambient humidity and temperature. The specific formula is:

[0069] D(x)=D0·(1+α·T-β·H)

[0070] Where D0 is the base diffusion coefficient (e.g., 1.0 m 2 / s), T is temperature (unit: °C), H is humidity (unit: %), α and β are the influence factors of temperature and humidity on the diffusion coefficient, respectively, and α=0.01 and β=0.005 are set.

[0071] In the application, the sensor collects pollutant concentration data, such as PM2.5 concentration of 80μg / m 3 , CO2 concentration is 400ppm, TVOCs concentration is 150ppb, combined with temperature, humidity and wind speed, the control center will update the diffusion path of pollutants in the air according to the formula. Through calculation, the diffusion trend and concentration change of pollutants in the next hour can be obtained. This information will help the control center dynamically adjust the location of sensors. For example, when the PM2.5 concentration in a certain area continues to rise, while the concentration in another area is lower, the system will instruct the sensors in that area to increase the sampling frequency or increase the coverage to ensure that the changing trend of pollutants is accurately captured.

[0072] At the same time, the control center will also use the pollutant source term S(x,t) to analyze the intensity of the pollution source. In this example, the printer is the pollution source, and its pollutant release can be estimated by factors such as the use time of the equipment and emission characteristics. Set the PM2.5 emitted by the printer to 5μg per minute and CO2 to 20ppm. The system can input these data into the source term equation to obtain the impact range of the pollution source on the ambient air quality.

[0073] Through this system, the dynamic deployment of sensors can respond to changes in air quality in real time, flexibly adjusting the location and working status of sensors to adapt to changing environmental conditions and fluctuations in pollution sources. The control center continuously optimizes the monitoring layout based on the diffusion model to ensure that the concentration distribution of pollutants can be accurately monitored, thereby achieving the optimal configuration of system resources.

[0074] For example, if the pollution source in a certain area of ​​the office suddenly increases, causing the PM2.5 concentration in that area to rise sharply, the system will increase the sensor sampling frequency in that area in a short period of time, and deploy new sensors on the pollution diffusion path to ensure more comprehensive air quality monitoring. In areas with lower pollution concentrations, the system will reduce the sampling frequency to save energy and reduce the workload of sensors.

[0075] Specifically, in an office building environment, multiple sensors are deployed in the air purification system. These sensors are distributed in different floors and areas to collect real-time concentration data of different types of pollutants in the air (such as PM2.5, CO2, TVOCs, etc.). Assume that the diffusion of PM2.5 is being processed. A printer in the office is a pollution source and is continuously emitting PM2.5 particles.

[0076] In order to evaluate the diffusion path of pollutants and predict the location of pollution sources in real time, the control center calculates the concentration distribution of pollutants in the air through the fluid dynamics model, obtains the concentration gradient of pollutants, and makes dynamic adjustments based on the data actually collected by the sensors. The following calculus formula is used to calculate the concentration gradient of pollutants:

[0077]

[0078] in, It represents the gradient of pollutant concentration at position x and time t, reflecting the degree of change of pollutant concentration in spatial position, that is, the concentration difference of pollutants diffused from a certain position to an adjacent position in space; It represents the spatial first-order derivative of the pollutant concentration C at position x, reflecting the rate of change of the concentration at different positions; is an integral operation, representing the cumulative effect of concentration changes over time.

[0079] The printer is set to release 5μg of PM2.5 particles per minute, and the pollution source is located in the central area of ​​the office. The PM2.5 concentration data collected by the sensor in real time is: the sensor concentration near the printer is 80μg / m 3 , while the concentration of the sensor farther from the printer was 40μg / m 3 The control center first calculates the spatial gradient of PM2.5 concentration:

[0080]

[0081] This means that within a range of 1 meter around the printer, the concentration change rate of PM2.5 is 20μg / m 3 Next, the system substitutes this gradient value into the integral formula for the concentration gradient and calculates the concentration gradient change accumulated over time:

[0082]

[0083] Assuming that the system calculates the pollutant diffusion process within 1 hour, then:

[0084]

[0085] This indicates that within 1 hour, the cumulative change in pollutant concentration in the air from the pollution source (printer) to the surrounding area is 1200 μg / m 3 Through this calculation, the control center can evaluate the spread of pollutants in space and, combined with real-time data, predict the location of pollution sources and the spread path of pollutants.

[0086] After the system is set up to identify the location of the pollution source, it will dynamically adjust the location of the sensor based on the calculation results of the pollutant concentration gradient and diffusion path. For example, if the pollutant concentration in a certain area is too high, the control center can instruct to increase the sampling frequency of the sensors in that area, or even temporarily deploy more sensors; while in areas with lower pollution concentration, the system will reduce the sampling frequency, thereby saving energy and improving the overall efficiency of the system.

[0087] After calculating the pollutant concentration gradient, the sensor on a certain floor decides to adjust its working mode according to the gradient change. For example, in areas with higher pollution concentration, the sensor will increase the sampling frequency from once every 10 minutes to once every minute. In this way, the system can capture the changes in pollutant concentration more accurately and adjust the purification strategy more timely.

[0088] In addition, the system will adjust the operation mode of the air purification equipment according to the direction of pollutant diffusion. For example, based on the calculation of the pollutant concentration gradient, the system will increase the air volume and the working time of the ultraviolet lamp in certain areas to accelerate the removal of pollutants; while in areas with lower pollutant concentrations, the system will reduce the workload of the purification equipment to achieve energy-saving effects.

[0089] The dynamic deployment method of sensors based on the diffusion law of pollutants optimizes the layout and density of sensors by calculating the concentration gradient and diffusion path of pollutants in real time to improve the accuracy of air quality monitoring and ensure the efficient operation of the purification system. To achieve this goal, the system dynamically adjusts the number and deployment frequency of sensors according to the changes in pollutants in space and time to ensure that it can cope with changes in pollution concentration in different areas.

[0090] In the case of an office building, it is assumed that there is a PM2.5 pollution source in a certain area of ​​the building - a printer that emits 5μg of PM2.5 particles per minute, and the pollution source is located in the central area of ​​the office building. In order to achieve accurate monitoring, the air purification system uses multiple sensors arranged on different floors and areas to monitor the concentration of pollutants in real time. The distribution between these sensors will be dynamically adjusted according to the law of pollutant diffusion to ensure that areas with higher pollutant concentrations receive more attention. At this point, the calculation of pollutant diffusion paths and concentration gradients becomes a key step. The system first calculates the concentration distribution of PM2.5 in the air based on the fluid dynamics model, and combines the actual data of the sensor to evaluate the diffusion of pollutants.

[0091] During this process, the system uses the following calculus formula to calculate the density distribution and deployment frequency of sensors:

[0092]

[0093] Where N(x, t) represents the sensor density at position x and time t, reflecting the number of sensors in the area or the sampling frequency; ΔC(x, t) is the change in pollutant concentration, indicating the change in the concentration of pollutants in area x and time t; ΔC max It is the concentration change limit preset by the system, used to standardize the effect of concentration change; It is an integral operation in space, representing the cumulative effect of changes in pollutant concentration in the region [x0, x].

[0094] Set the system preset concentration change limit ΔC max 100 μg / m 3, that is, the system will make adjustments based on this concentration range when deploying sensors. Based on the data actually collected by the sensors, the control center can calculate the concentration changes near the pollution source and set the sensor concentration within 1 meter around the printer to 80μg / m 3 , while the concentration of the sensor 2 meters away is 40μg / m 3 Therefore, the concentration change ΔC(x,t) is 40 μg / m 3 . Calculate the sensor density according to the formula, set the length of the area to 2 meters, and calculate:

[0095]

[0096] This means that the sensor density per meter in this area is 0.8, and the system will determine the layout density and sampling frequency of sensors in this area based on this density.

[0097] In addition, the control system is set to adjust different time periods in the area. Specifically, during high pollution periods (such as when the printer is working), the system will increase the sensor density in the area and monitor the pollutant concentration more accurately by increasing the sampling frequency. For example, when the printer is working, the system will increase the sampling frequency from once every 10 minutes to once every minute to capture the concentration changes of PM2.5 in real time. During periods with less pollution, the system will reduce the sampling frequency of sensors in the area to reduce unnecessary energy consumption.

[0098] Based on the gradient of pollutant concentration and dynamically adjusted sensor layout, the air purification system can effectively identify and respond to pollution conditions in different areas. On a certain floor, the density and deployment frequency of sensors are dynamically optimized according to the direction of pollutant diffusion and concentration changes. The system can promptly identify changes in pollution sources and reasonably deploy sensors according to the predicted diffusion path to ensure the accuracy of air quality monitoring while avoiding over-deployment and waste of resources. For example, if a printer malfunctions and causes an abnormal increase in pollutant concentration, the system can immediately identify and conduct emergency monitoring by increasing the density of sensors in the area. This flexible adjustment not only improves the accuracy of pollutant monitoring, but also enables the air purification system to respond quickly according to real-time changes in pollutants and optimize purification efficiency.

[0099] Embodiment 2:

[0100] Combination Figure 3In this embodiment, the pollutant priority-driven multi-level response control method assigns a dynamically changing priority to each pollutant by comprehensively evaluating the concentration changes, diffusion paths, and health hazards of different pollutants. The core of this method is to dynamically adjust the priority of pollutants by real-time monitoring of factors such as pollutant concentration, concentration change rate, diffusion characteristics, and weighted integration, thereby adjusting the response strategy of the air purification system. In a typical office building environment, the system first monitors the concentration of pollutants in the air in real time through a group of sensors installed in various areas, including PM2.5, PM10, VOC (volatile organic compounds), and NO2 (nitrogen oxides), and then performs priority evaluation based on these data.

[0101] For example, in a certain office area, the PM2.5 concentration collected by the sensor is 150μg / m 3 , VOC concentration is 100μg / m 3 , NO2 concentration is 40μg / m 3 The air purification system will assign a priority coefficient to each pollutant based on its concentration, concentration change rate, and diffusion characteristics. The priority of pollutants is dynamically adjusted over time. The system uses the following priority evaluation formula to comprehensively evaluate the degree of harm and priority of pollutants:

[0102]

[0103] In this formula, P i (t) represents the priority of pollutant i at time t; C i (t′) represents the concentration of pollutant i at time t′, reflecting the current pollution level of the pollutant; R i (t′) is the concentration change rate of pollutant i, reflecting the speed of change of pollutant concentration and characterizing the diffusion rate of pollutants; D i (t′) is the diffusion characteristic of the pollutant, which describes the ability of the pollutant to diffuse; λ1, λ2, λ3 are weight coefficients, which are used to adjust the influence of concentration, concentration change rate and diffusion characteristics on the priority; a, b, c are exponents that control the nonlinear influence of concentration, change rate and diffusion characteristics on the priority.

[0104] Assume that at a certain moment, the concentration of PM2.5 is 150μg / m 3 The concentration change rate is 0.5 μg / m 3 / min, the diffusion coefficient is 0.02m 2 / s; VOC concentration is 100μg / m 3 The concentration change rate is 0.2μg / m 3 / min, the diffusion coefficient is 0.05m 2 / s; the concentration of NO2 is 40μg / m 3 The concentration change rate is 0.1 μg / m 3 / min, the diffusion coefficient is 0.1m 2 / s. At the same time, the weight coefficients are set to λ1=0.4, λ2=0.3, λ3=0.3, and the exponential parameters are set to a=1, b=2, c=1.

[0105] Substituting these data into the formula for calculation, first calculate the priority of PM2.5:

[0106]

[0107] The calculation results are:

[0108]

[0109]

[0110] If the evaluation time t is set to 10 minutes (i.e. 600 seconds), the priority is:

[0111] P PM2.5 (600) = 60.081 × 600 = 36048.6

[0112] Next, calculate the priority of the VOC:

[0113]

[0114] The calculation results are:

[0115]

[0116]

[0117] Similarly, if the evaluation time t is set to 10 minutes, the priority is:

[0118] P VOC (600) = 40.027 × 600 = 24016.2

[0119] Finally, calculate the priority of NO2:

[0120]

[0121] The calculation results are:

[0122]

[0123] The priorities are:

[0124] P NO2 (600) = 16.033 × 600 = 9618

[0125] According to the priority evaluation results, PM2.5 has a priority of 36048.6, VOC has a priority of 24016.2, and NO2 has a priority of 9618. Based on these priority values, the system will adopt different response strategies for pollutants. Since PM2.5 has the highest priority, the system will increase the working intensity of the air purifier in this area to enhance the filtering effect of PM2.5. VOC and NO2 have lower priorities, so the system chooses to maintain the normal working mode to reduce unnecessary energy consumption.

[0126] The pollutant priority-driven multi-level response control method further introduces a multi-dimensional mapping control model between pollutant concentration and purification equipment processing efficiency, and adaptively adjusts the working state of the purification equipment based on pollutant concentration, purification equipment processing capacity and environmental factors. Specifically, based on the change in pollutant concentration, the purification equipment processing efficiency will be adjusted through the following multi-dimensional mapping control formula:

[0127]

[0128] In this formula, E i (t) represents the treatment efficiency of pollutant i at time t; C i (t) is the concentration of pollutant i at time t, indicating the current pollutant concentration level; α and β are parameters that control the amplitude and decay rate of the exponential decay part; γ and δ are parameters that control the amplitude and periodic change of the cosine function part, representing the periodic adjustment of the treatment efficiency within the concentration change range; the upper and lower limits of the integral are 0 and C i (t), and the treatment efficiency is calculated over the range of pollutant concentrations by integration.

[0129] Suppose that in a certain office environment, the concentration of PM2.5 is 200 μg / m at a certain moment. 3 . The system finds that the PM2.5 concentration has reached a high level based on real-time monitoring data, so it will adjust the efficiency of the purification equipment. The set environmental factors have a greater impact on the treatment efficiency. The treatment efficiency of the purification equipment is affected by both concentration and environmental changes. The following parameters are selected for calculation: α = 0.5, β = 0.01, γ = 0.3, δ = 2. These parameters determine the degree of influence of the exponential decay part and the periodic adjustment part on the treatment efficiency. According to these parameters, substitute them into the formula for calculation:

[0130]

[0131] First, the integral of the exponential decay part is calculated:

[0132]

[0133] Next, we integrate the cosine function:

[0134]

[0135] Since sin(400) is periodic, the value can be directly calculated as:

[0136] sin(400)≈-0.7457

[0137] Therefore, the integral of the cosine function is:

[0138] 0.15·(-0.7457-0)=-0.111855

[0139] Adding the two parts together gives the processing efficiency:

[0140] E PM2.5 (t)=0.43235+(-0.111855)=0.320495

[0141] This means that when the PM2.5 concentration is 200 μg / m 3 When the air purification system is set to 0.320495, the processing efficiency is 0.320495. Based on this processing efficiency, the system will dynamically adjust the operating status of the purification equipment according to the preset working mode. For example, when the PM2.5 concentration is high, the purification equipment will increase the air flow and filtration capacity to cope with the higher pollution level; when the concentration is low, the purification equipment will appropriately reduce power consumption according to the multi-dimensional mapping control model to maintain optimal energy efficiency.

[0142] In addition, the multi-dimensional mapping control model can also adapt to environmental changes. For example, when the ambient temperature is high or the humidity is high, the purification equipment needs more processing power to cope with the spread of pollutants. Therefore, environmental factors will further adjust the operating efficiency of the purification equipment. Through this model, the air purification system can accurately match the processing requirements of different pollutant concentration ranges, ensuring that the system operates in the most suitable way, improving the efficiency and energy saving of air purification.

[0143] In order to improve purification efficiency and reduce energy consumption, a multi-level response control method driven by pollutant priority is adopted, and a system based on fluid dynamics model and pollutant diffusion prediction algorithm is introduced. The system can dynamically adjust the working state of air purification equipment by simulating the diffusion path and concentration changes of pollutants, thereby improving air quality and optimizing equipment operation efficiency. The diffusion simulation and prediction formula is deeply analyzed.

[0144] The basic form of the diffusion simulation and prediction formula is:

[0145]

[0146] in, Indicates at location and the pollutant concentration at time t, which reflects the distribution of pollutants in space; is the diffusion coefficient of the pollutant, which indicates the diffusion capacity of the pollutant at that location and time; is the air velocity vector, which indicates the speed and direction of air flow, thus affecting the migration of pollutants; is the intensity of the pollution source, describing the rate at which pollutants are generated. This formula is based on the principles of fluid dynamics and simulates the diffusion process of pollutants by considering environmental factors such as the diffusion path of pollutants, wind speed, temperature and humidity.

[0147] In a certain city, the PM2.5 concentration is high and the environmental conditions in the area are changing. The real-time data obtained by the sensor shows that the pollutant concentration is 200μg / m 3 Based on this data, the system will combine the fluid dynamics model to dynamically simulate the diffusion path of pollutants. The following known environmental parameters are set:

[0148] Air flow rate 10m / s (represents wind speed);

[0149] Diffusion coefficient 0.01m 2 / s (represents the diffusion capacity of pollutants);

[0150] Pollution source intensity 50 μg / m 3 ·s (represents the intensity of the pollution source).

[0151] In addition, the ambient temperature is 25°C and the humidity is 60%, these two data will affect the diffusion coefficient and air velocity Therefore, the system dynamically simulates the diffusion process of pollutants in space and predicts future pollutant concentrations.

[0152] Based on these data, the system will calculate the diffusion trend of pollutants in the next few hours through a fluid dynamics model. The pollutant concentration at a specific location is set to 200μg / m 3 , and the pollution source intensity is 50μg / m 3 ·s, the model calculation can predict that the pollutant concentration in the area will increase to 250μg / m in 1 hour. 3 .

[0153] Next, the system dynamically adjusts the working state of the air purification equipment according to the pollutant concentration prediction results. To this end, a multi-dimensional mapping control model between pollutant concentration and purification equipment processing efficiency is adopted. The PM2.5 concentration in the area is predicted to be 250μg / m 3 , the purification equipment adjusts its treatment efficiency according to this data. The following parameters are set to calculate the treatment efficiency:

[0154] α = 0.5 (controls the amplitude of the exponential decay part);

[0155] β = 0.01 (controls the decay speed of the exponential decay part);

[0156] γ = 0.3 (controls the amplitude of the cosine function part);

[0157] δ=2 (controls the periodic change of the cosine function part).

[0158] Based on these parameters, the treatment efficiency of the purification equipment will be calculated according to the formula:

[0159]

[0160] First, the integral of the exponential decay part is calculated:

[0161]

[0162] Next, we integrate the cosine function:

[0163]

[0164] Since sin(500) is periodic, we can calculate:

[0165] sin(500)≈0.3491

[0166] Therefore, the integral of the cosine function is:

[0167] 0.15·(0.3491-0)=0.052365

[0168] Adding the two parts together gives the processing efficiency:

[0169] E PM2.5 (t)=0.45895+0.052365=0.511315

[0170] This means that when the PM2.5 concentration is 250 μg / m 3 When the treatment efficiency of the purification equipment is 0.511315, the system will adjust the operation mode of the purification equipment according to this treatment efficiency, increase the air flow and filtering capacity, and treat pollutants more effectively.

[0171] Air quality is optimized through a multi-level response control method driven by pollutant priority, and the system's operating parameters are dynamically adjusted to achieve more efficient purification.

[0172] First, the resource allocation model is used to dynamically adjust the working parameters of the air purification system. The specific formula is:

[0173]

[0174] in:

[0175] R i (t) represents the resource allocation required by pollutant i at time t;

[0176] P j (t) is the priority of pollutant j at time t, reflecting the urgency of pollutant treatment;

[0177] α j is the weighting coefficient, which indicates the contribution of pollutant j to the resource allocation of purification equipment;

[0178] β is the overall resource adjustment coefficient, which is used to control the total amount of resource allocation;

[0179] n represents the number of pollutants, and the model considers the weighted sum of the priorities of all pollutants.

[0180] Assume that the pollutants in the air of a certain area are mainly PM2.5, and the real-time monitoring data shows that the current PM2.5 concentration is 200μg / m 3 In order to effectively control the operation of air purifiers, the system needs to first analyze the priority of pollutants and dynamically adjust the resource allocation of air purification equipment based on concentration, health impact and diffusion trend.

[0181] There are three main pollutants: PM2.5, NO2 and CO, and their real-time concentrations and priorities are as follows:

[0182] PM2.5 concentration: 200 μg / m 3 , priority P1(t) = 3

[0183] NO2 concentration: 50μg / m 3 , priority P2(t) = 2

[0184] CO concentration: 30 μg / m 3 , priority P3(t) = 1

[0185] The system allocates corresponding resources according to these priorities. Set the weighting coefficients α1 = 0.5, α2 = 0.3, α3 = 0.2, and the overall resource adjustment coefficient β = 1, then the resource allocation amount R1(t) required for the pollutant PM2.5 is:

[0186] R1(t)=(0.5·3+0.3·2+0.2·1)·1=(1.5+0.6+0.2)=2.3

[0187] This means that the air purification system needs to allocate 2.3 units of resources to PM2.5.

[0188] Next, the working state of the air purification equipment will be dynamically adjusted according to the change in pollutant concentration. The working parameters of the purification equipment include: filter air volume, activated carbon adsorption intensity and UV lamp switching time. Through the resource allocation model, these parameters can be adjusted according to the priority and concentration prediction of pollutants.

[0189] The concentration of PM2.5 pollutants is set to increase to 250 μg / m in the next hour. 3 , the system will calculate the required treatment efficiency based on the fluid dynamics model and pollutant dispersion prediction. Specifically, the treatment efficiency E of the purification equipment PM2.5 (t) can be calculated by the following model:

[0190]

[0191] Where x represents the pollutant concentration, and the integral range is 0 to 250 μg / m 3 . First, calculate the exponential decay part:

[0192]

[0193] Next, we integrate the cosine part:

[0194]

[0195] Therefore, the treatment efficiency of the purification equipment is:

[0196] E PM2.5 (t)=0.45895+0.052365=0.511315

[0197] This processing efficiency value E PM2.5 (t) = 0.511315 indicates that the purification equipment has an efficiency of 51.13% in treating PM2.5 pollutants. The system adjusts the air flow and filtering capacity according to this treatment efficiency to treat pollutants more effectively.

[0198] The core of the multi-level response control method driven by pollutant priority is to be able to adjust the working state of the equipment in real time according to the changes in pollutant concentration and priority. Through the adaptive resource allocation mechanism, the system can optimize the purification process according to environmental changes. For example, if the PM2.5 concentration is expected to reach 250μg / m in the next hour, 3 , while the concentration of other pollutants remains unchanged, the system will give priority to PM2.5 and increase the processing efficiency of the purification equipment to achieve the best purification effect.

[0199] In addition, as the concentration and priority of pollutants change, the system will continuously adjust working parameters such as filter air volume, activated carbon adsorption intensity and UV lamp switching time to ensure that the air purification equipment is always in the best working condition.

[0200] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A sensor control method for an air purification system, characterized in that The following steps are involved: S1. Dynamic deployment of sensors based on pollutant diffusion rules: S1.

1. Combined with the initial distribution of sensors, the pollutant concentration gradient is monitored in real time, and the pollutant diffusion path is simulated using a fluid dynamics model; S1.

2. Infer the source of pollutants through sensor data and dynamically change the sensor collection range; S2. Multidimensional modeling of pollutant characteristics and decoupling of sensor signals: S2.

1. Obtain multidimensional data through physical sensors including particulate matter, temperature and humidity, and chemical sensors including VOC and harmful gases, and extract pollutant characteristics using principal component analysis (PCA); S2.2, design a decoupling model and use blind source separation technology to separate the characteristics of each pollutant from the sensor composite signal; S3, multi-level response control driven by pollutant priority: S3.

1. Construct a hazard index for pollutants including AQI grading standards, and dynamically evaluate pollutant priorities based on real-time sensor monitoring data; S3.

2. Allocate resources of the air purification system according to pollutants of different priorities, including adjusting the filter air volume, activated carbon adsorption intensity and UV germicidal lamp opening time; S4. Data-driven sensor health management: S4.

1. Build a sensor data anomaly detection mechanism and analyze the sensor operation status through machine learning algorithms; S4.2, introduce an adaptive calibration algorithm to adjust the sensor output including the interference correction of temperature and humidity on the particle sensor in real time according to the environmental reference value; S4.

3. Dynamically adjust sensor maintenance and replacement cycles based on sensor health status prediction results; S5. Sensor energy consumption management with multi-objective collaborative optimization: S5.

1. Record the energy consumption characteristics of the sensor at different sampling frequencies and establish a mapping model between energy consumption and monitoring accuracy; S5.

2. Dynamically adjust the sampling frequency and operating mode based on pollutant priority, monitoring range, and sensor health status.

2. The sensor control method of the air purification system according to claim 1, characterized in that The sensor dynamic deployment method based on pollutant diffusion law includes: Each sensor collects real-time data on the concentration of pollutants in the air and transmits the data to the control center. The control center updates the fluid dynamics model of pollutant diffusion based on real-time sensor data and environmental conditions including temperature, humidity, and wind speed, and calculates the diffusion path and concentration changes of pollutants in the air. The fluid dynamics model establishes an equation based on the time change of pollutant concentration and diffusion speed, which is described by the following control equation: Among them, ΔC(x,t) represents the rate of change of pollutant concentration at position x and time t, reflecting the change of pollutant concentration over time; C(x,t) is the pollutant concentration, describing the pollutant concentration value at position x and time t; D(x) is the diffusion coefficient of the pollutant, indicating the ability of the pollutant to diffuse in the air. The value is usually related to the ambient temperature and humidity factors, reflecting the rate at which the pollutant diffuses from the high concentration area to the low concentration area; is the diffusion term, where represents the spatial gradient operator, represents the divergence operator, which calculates the spatial change rate of pollutant concentration; S(x,t) is the pollution source term, which represents the amount of pollutants released by the pollution source per unit time.

3. The sensor control method of the air purification system according to claim 2, characterized in that The sensor dynamic deployment method based on pollutant diffusion law includes: By calculating the pollutant concentration gradient, the diffusion direction of the pollutants and the location of the pollution source are evaluated; the pollutant concentration gradient calculation is based on the output of the fluid dynamics model, combined with the data actually collected by the sensor, to predict and evaluate the pollution source and diffusion path.

4. The sensor control method of the air purification system according to claim 3, characterized in that The sensor dynamic deployment method based on pollutant diffusion law includes: According to the real-time calculated pollutant concentration gradient and diffusion path, the position and number of sensors are dynamically adjusted to optimize the density distribution of sensors. The process of dynamically optimizing sensor deployment is adjusted through the following formula: Where N(x,t) represents the sensor density at location x and time t, the number of sensors at the location or the deployment frequency; ΔC(x,t) is the change in pollutant concentration, which represents the change in the concentration of the pollutant in area x and time t; ΔC max It is the concentration change limit preset by the system, used to standardize the effect of concentration change; It is an integral operation in space, reflecting the cumulative effect of changes in pollutant concentration in the region [x0, x].

5. The sensor control method of the air purification system according to claim 1, characterized in that The pollutant priority-driven multi-level response control method includes: By monitoring the concentration changes, diffusion paths, and health hazards of different pollutants, each pollutant is assigned a priority coefficient; the priority of pollutants changes dynamically over time. Based on the comprehensive consideration of pollutant concentration and environmental factors, the priority evaluation formula is: The priority evaluation formula is used to evaluate the priority P of pollutant i at time t. i (t); By weighted integration of pollutant concentration, concentration change rate and diffusion characteristics, the priority of pollutants is comprehensively calculated; C i (t′) represents the concentration of pollutant i at time t′, reflecting the current pollution level of the pollutant; R i (t′) is the concentration change rate of pollutant i, indicating the speed of concentration change and reflecting the diffusion rate of pollutants; D i (t′) is the diffusion characteristic of the pollutant; λ1, λ2, λ3 are weight coefficients used to adjust the influence of concentration, change rate and diffusion characteristics on priority; a, b, c are exponents that control the nonlinear influence of concentration, change rate and diffusion characteristics on priority.

6. The sensor control method of the air purification system according to claim 5, characterized in that The pollutant priority-driven multi-level response control method includes: A multidimensional mapping control model between pollutant concentration and purification equipment processing efficiency is introduced; the multidimensional mapping control model includes pollutant concentration, purification equipment processing capacity and environmental factors, and adaptively adjusts the working state of the purification equipment within different pollutant concentration ranges.

7. The sensor control method of the air purification system according to claim 6, characterized in that The pollutant priority-driven multi-level response control method includes: A system based on fluid dynamics model and pollutant diffusion prediction algorithm is introduced to simulate the diffusion path and concentration changes of pollutants. By considering the distribution and intensity of pollution sources and meteorological conditions including wind speed, temperature and humidity, the diffusion process of pollutants in the air is dynamically simulated, and the future distribution of pollutants is predicted. Diffusion simulation and prediction formula: The diffusion simulation and prediction formula describes the pollutants In space The diffusion and migration process under time t is combined with the principles of fluid dynamics to simulate the diffusion path and concentration changes of pollutants; It's location and the pollutant concentration at time t, reflecting the distribution of pollutants in space; It's location and the pollutant diffusion coefficient at time t, which reflects the diffusion capacity of pollutants; is the air velocity vector, which indicates the migration rate of pollutants with the air flow; is the intensity of the pollution source, describing the rate at which pollutants are produced; is the gradient operator, which is used to calculate the rate of change of concentration in space, It represents the divergence operation of the diffusion flow and represents the diffusion trend of pollutants.

8. The sensor control method of the air purification system according to claim 7, characterized in that The pollutant priority-driven multi-level response control method includes: An adaptive resource allocation mechanism is used to dynamically adjust the working parameters of the air purification system according to the priority, concentration and diffusion prediction of pollutants; the filter air volume, activated carbon adsorption intensity and UV lamp switching time resources are dynamically adjusted based on the concentration, health impact and diffusion trend of pollutants.

Images