Air purification filter element control method and system based on environment perception

Abstract

The invention provides an air purification filter element control method and system based on environment awareness, and the method comprises the steps: collecting environment parameter data of a to-be-purified space and working state data of purification equipment, extracting the spatial and temporal change characteristics of the pollutant concentration in the environment parameter data, and generating environment characteristic data; based on the ventilation quantity and the environment characteristic data in the working state data, calculating the mass flow of each pollutant passing through the filter element, and performing weighted correction on the mass flow through a preset load coefficient to obtain a current load value; cumulative calculation is conducted on the load history data, the pressure difference distribution data and the current load value, and filter element service life parameters are obtained; target operation parameters are determined based on the filter element service life parameters and the environment parameter data, and a fan and a valve of the purification equipment are adjusted; according to the method, accurate evaluation of the state of the filter element is realized through multi-point environmental perception and load accumulation calculation, and dynamic regulation and control are performed by combining the environmental pollution degree and the service life of the filter element, so that the purification efficiency is improved and the service life of the filter element is prolonged.

Description

Technical Field

[0001] This invention relates to the field of air purification technology, and in particular to an air purification filter control method and system based on environmental perception. Background Technology

[0002] In existing air purification systems, filter control typically relies on monitoring pressure drop or cumulative operating time to determine the degree of filter clogging and trigger replacement reminders, thus maintaining the system's basic functionality. However, air purification filters face complex and variable pollution environments during actual operation. The concentration of different types of pollutants, humidity conditions, and airflow load all significantly affect the filter's consumption rate, and these environmental parameters exhibit dynamic changes in both time and space. This environmental dynamism is often insufficiently considered in existing filter control methods, leading to discrepancies between control decisions and actual operating conditions.

[0003] Because existing methods fail to incorporate real-time changes in environmental pollution parameters, they are prone to decreased purification efficiency, filter overload, or energy waste when assessing filter status and adjusting operating parameters. When pollutant concentrations suddenly rise, fixed-mode operation cannot respond promptly, leading to deterioration of indoor air quality; conversely, excessive purification at lower pollution levels accelerates filter consumption. This not only reduces the overall performance of the purification system but may also cause sudden filter failure in critical application scenarios, thus affecting the stability and reliability of environmental safety. Particularly in complex environments with large spaces and multiple pollution sources, single-point monitoring data is insufficient to reflect the overall pollution situation, further exacerbating the problems of insufficient control precision and delayed decision-making. Summary of the Invention

[0004] The main objective of this invention is to solve the technical problem that existing air purification filter control methods fail to adjust operation in accordance with the dynamic changes in environmental pollution parameters, resulting in a mismatch between control decisions and actual workload.

[0005] The first aspect of this invention provides an air purifier filter control method based on environmental perception, the air purifier filter control method based on environmental perception includes: Collect environmental parameter data of the space to be purified and working status data of the purification equipment, and extract the spatiotemporal variation values ​​of pollutant concentration in the environmental parameter data to generate environmental characteristic data. Based on the ventilation volume and environmental characteristic data in the working status data, the mass flow rate of each pollutant passing through the filter element is calculated; Based on a preset load factor, the mass flow rate is adjusted by a load-weighted correction of the filter element to obtain the current load value; The load history data, differential pressure distribution data, and current load value in the working status data are accumulated and calculated to obtain the filter life parameter. Based on the filter life parameter and the environmental parameter data, the target operating parameters are determined, and the corresponding fans and valves of the purification equipment are adjusted.

[0006] A second aspect of the present invention provides an air purification filter control system based on environmental perception, the air purification filter control system based on environmental perception comprising: The feature generation unit is used to collect environmental parameter data of the space to be purified and working status data of the purification equipment, and extract the spatiotemporal variation values ​​of pollutant concentration in the environmental parameter data to generate environmental feature data. The flow calculation unit is used to calculate the mass flow rate of each pollutant through the filter element based on the ventilation volume in the working status data and the environmental characteristic data; The load assessment unit is used to perform load-weighted correction of the mass flow rate of the filter element based on a preset load coefficient to obtain the current load value; The control and adjustment unit is used to accumulate and calculate the load history data, differential pressure distribution data and current load value in the working status data to obtain filter life parameters, and based on the filter life parameters and environmental parameter data, determine the target operating parameters and adjust the fans and valves corresponding to the purification equipment.

[0007] The aforementioned air purification filter control method and system based on environmental perception collects environmental parameter data of the space to be purified and operating status data of the purification equipment, and extracts the spatiotemporal variation characteristics of pollutant concentration to generate environmental characteristic data. Based on the ventilation volume and environmental characteristic data in the operating status data, the mass flow rate of each pollutant through the filter is calculated, and a preset load coefficient is used to weight and correct the mass flow rate to obtain the current load value. By accumulating the load history data, pressure difference distribution data, and the current load value, the filter life parameter is obtained. Based on the filter life parameter and environmental parameter data, the target operating parameters are determined, and the corresponding fans and valves of the purification equipment are adjusted accordingly. Because this method achieves precise control through multi-dimensional environmental perception and dynamic load assessment, it can adaptively adjust the operating parameters according to changes in pollutant concentration and the actual state of the filter, maximizing the filter life while ensuring purification effect, thereby improving the working efficiency of the air purification system and the utilization rate of filter resources.

[0008] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0009] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of the first embodiment of the air purification filter control method based on environmental perception in this invention. Figure 2 This is a schematic diagram of the second embodiment of the air purification filter control method based on environmental perception in this invention. Figure 3 A schematic diagram of an embodiment of the air purification filter control system based on environmental perception in this invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] The terms "comprising" and "having," and any variations thereof, used in the embodiments of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0013] To facilitate understanding of this embodiment, a detailed description of an air purification filter control method based on environmental perception disclosed in this embodiment of the invention will be provided first. For example... Figure 1 As shown, this method includes the following steps: 101. Collect environmental parameter data of the space to be purified and working status data of the purification equipment, and extract the spatiotemporal variation values ​​of pollutant concentration in the environmental parameter data to generate environmental characteristic data. In this embodiment, environmental parameter data of the space to be purified and working status data of the purification equipment are collected: Multiple environmental sensing nodes deployed at different locations in the space to be purified synchronously collect environmental parameter data of various pollutants, as well as various operating parameters of the purification equipment under current air purification conditions, current fan speed and filter pressure difference, load history data stored in the purification equipment, and pressure difference distribution data of the filter inlet and outlet surfaces collected through a pressure difference sensor array. The working status data includes operating setting parameters, current fan speed and filter pressure difference, load history data, and pressure difference distribution data. The concentration difference of each pollutant in the environmental parameter data between the current time and the previous time is calculated, and the concentration difference is divided by the time difference between the current time and the previous time to obtain the time change rate. Based on the multiple environmental sensing nodes deployed at different locations in the space to be purified, the spatial mean and spatial standard deviation of each pollutant concentration in the environmental parameter data at different locations are calculated. Based on the time change rate, the spatial mean, the spatial standard deviation, and the environmental parameter data, environmental feature data is generated.

[0014] Specifically, firstly, environmental parameter data is collected through multiple environmental sensing nodes pre-deployed at different locations in the space to be purified. These environmental sensing nodes are independent monitoring units integrating various gas and particulate matter sensors. Each node is equipped with a laser scattering PM2.5 sensor, a light scattering PM10 sensor, an electrochemical volatile organic compound sensor, and a capacitive temperature and humidity sensor. In actual deployment in the factory workshop, the node location selection needs to consider the distribution characteristics of pollution sources. Specifically, nodes are placed near production equipment to monitor dust-generating areas, at ventilation duct inlets to monitor intake air quality, in worker work areas to monitor air quality in breathing zones, and in workshop corners to monitor pollution accumulation in dead corners. The spacing between nodes is maintained within ten to fifteen meters to ensure coverage of the entire workshop space. Each node transmits the collected pollutant concentration data, temperature data, and humidity data to the purification equipment controller via the ZigBee wireless communication protocol. All nodes are triggered by a unified collection command sent by the controller, with a collection cycle set every thirty seconds. This cycle takes into account the relatively rapid changes in pollutant concentration in industrial environments, capturing dynamic changes without generating redundant data due to excessively high sampling frequencies. The acquisition of operating status data is divided into four parts: First, the current operating settings parameters are obtained by reading the controller register, including the target air volume value set by the user and the selected filtration mode type; second, the fan speed value is obtained in real time by the Hall effect speed sensor installed at the fan shaft end, and the pressure difference between the two ends of the filter element is measured by silicon piezoresistive differential pressure sensors installed on the air inlet and air outlet sides of the filter element (in addition, data related to the operation of the equipment filter element can be collected or read from the memory through other sensors); third, the load history data is read from the controller's non-volatile memory, which records the load value and the actual running time of the equipment every hour in time series form; finally, the differential pressure distribution data is collected by a differential pressure sensor array consisting of nine differential pressure measuring points evenly distributed on the air inlet surface of the filter element and nine differential pressure measuring points corresponding to the air outlet surface. These measuring points cover the entire effective filtration area of ​​the filter element in a three-row, three-column grid layout. This multi-source data acquisition method can simultaneously acquire the spatial distribution characteristics of environmental pollution and the multi-dimensional status information of equipment operation. Compared with single-parameter monitoring at a single location, it can identify uneven pollution distribution in factory workshops caused by local equipment emissions or uneven ventilation, as well as local overload of filter cartridges caused by uneven pollutant deposition.

[0015] Secondly, for the various pollutant concentration data collected by each environmental sensing node, the controller in the purification equipment calculates their temporal change characteristics. Specifically, the controller retrieves the current concentration value of a certain pollutant at a given node and the concentration value of the same pollutant at the previous moment from memory. It subtracts the previous value from the current value to obtain the concentration difference, and then divides this difference by the time interval between the two measurements, which is 30 seconds. The result is the temporal change rate of the pollutant concentration at that node. For example, in a factory workshop, a node near a cutting machine measures a PM10 concentration of 150 micrograms per cubic meter at 9:00 AM and 210 micrograms per cubic meter at 9:05 AM, with a 30-second interval. Therefore, the temporal change rate of PM10 at this node is 60 micrograms per cubic meter divided by 30 seconds, resulting in an increase of 2 micrograms per cubic meter per second. The controller performs this calculation process for all pollutant types at all nodes in the workshop, ultimately forming a temporal change rate data table. Each row in the table corresponds to a node, and each column corresponds to a pollutant type. The value of the rate of change over time reflects the direction of pollutant concentration evolution; a positive value indicates that the pollutant concentration is increasing, and a negative value indicates that the pollutant concentration is decreasing. The absolute value represents the speed of concentration change. By introducing the rate of change over time, sudden pollution events can be identified. For example, when a grinding machine in a workshop suddenly starts up and generates a large amount of dust, the PM10 rate of change over time at nearby nodes will jump from near zero to a level of several micrograms per cubic meter per second in a short period of time. This indicates that the pollution is rapidly intensifying, allowing for an immediate increase in purification intensity without waiting for the pollutant concentration to accumulate to a set threshold before initiating an emergency response.

[0016] Furthermore, based on multiple environmental sensing nodes deployed in different locations within the factory workshop, the controller performs spatial statistical analysis on the concentration of each pollutant. The spatial mean is calculated by summing the concentration values ​​of a certain pollutant measured by all nodes at the same acquisition time, and then dividing the sum by the total number of nodes. For example, assuming six environmental sensing nodes are deployed in the workshop, and at a certain moment the formaldehyde concentrations measured by these six nodes are 0.06 mg / m³, 0.09 mg / m³, 0.05 mg / m³, 0.12 mg / m³, 0.07 mg / m³, and 0.08 mg / m³, the controller adds these six values ​​to obtain 0.47 mg / m³, then divides this by the number of nodes (six) to calculate the spatial mean of 0.078 mg / m³. The spatial standard deviation is calculated as follows: First, the controller calculates the deviation between the concentration value measured at each node and the spatial mean. This is done by subtracting 0.078 from each node's value, resulting in six deviation values. Then, each deviation value is squared. The sum of all squared values ​​is divided by the number of nodes (six) to obtain the variance. Finally, the square root of the variance is taken to obtain the spatial standard deviation. In the example above, a spatial standard deviation of 0.02 mg / m³ indicates that the formaldehyde concentration at each location is relatively concentrated around the mean, showing a relatively uniform spatial distribution. However, a spatial standard deviation of 0.06 mg / m³ indicates significant differences in formaldehyde concentration at different locations, suggesting the existence of clearly defined high-concentration pollution areas. The spatial mean reflects the overall pollutant load level of the entire workshop and is a comprehensive indicator for assessing the overall pollution level. The spatial standard deviation, on the other hand, quantifies the dispersion of pollution distribution; a larger value indicates a more uneven pollution distribution. In a factory workshop setting, when production equipment in a certain area continuously emits pollutants while other areas are relatively clean, the spatial standard deviation of the pollutants will increase significantly. At this point, it can be determined that the pollution is localized rather than globally diffused. Therefore, differentiated control strategies can be adopted, such as strengthening air intake or adjusting the working intensity of filter elements in high-pollution areas.

[0017] Finally, the calculated temporal rate of change, spatial mean, and spatial standard deviation are summarized and integrated with the original environmental parameter data to generate an environmental characteristic data set. Compared to the raw concentration readings directly output by the sensors, the environmental characteristic data adds two dimensions of statistical analysis: temporal trend and spatial distribution characteristics. This allows the data to not only reflect the current instantaneous pollution state but also reveal the dynamic evolution and spatial distribution patterns of pollution. This multi-dimensional characteristic description enables the system to distinguish different pollution scenarios. For example, when the temporal rate of change of a pollutant is positive and the spatial standard deviation is large, it indicates that the pollution is rapidly deteriorating locally, requiring immediate and intensified purification measures for that area. Conversely, when the temporal rate of change is negative and the spatial standard deviation is small, it indicates that the pollution is gradually receding globally, allowing for a reduction in purification intensity to conserve energy.

[0018] 102. Based on the ventilation volume in the working status data and the environmental characteristic data, calculate the mass flow rate of each pollutant passing through the filter element; In this embodiment, the rated ventilation volume corresponding to the current fan speed is determined, and a pressure difference correction coefficient is determined based on the ratio of the filter element pressure difference to the preset rated pressure difference. The rated ventilation volume is multiplied by the pressure difference correction coefficient to obtain the actual ventilation volume. Based on the spatial distance of each environmental sensing node, the pollutant concentration of each environmental sensing node is weighted and averaged to obtain the equivalent pollutant concentration. The equivalent pollutant concentration is multiplied by the actual ventilation volume to obtain the mass flow rate of each pollutant through the filter element.

[0019] Specifically, firstly, the pre-stored fan characteristic curve data table is read from the device's memory. This data table organizes data according to a correspondence between rotational speed as the index and rated ventilation volume as the value. Rated ventilation volume refers to the standard airflow that the fan can provide at a specific rotational speed and when the filter element is in a brand-new, unclogging state. Based on the fan rotational speed value currently measured by the speed sensor, the matching rotational speed value is found row by row in the data table, and the corresponding rated ventilation volume value is read. For example, in a factory workshop, the speed sensor measures the fan speed to be 1200 revolutions per minute, thus finding the corresponding rated ventilation volume record of 3000 cubic meters per hour in the data table. Next, the differential pressure correction factor is calculated. Specifically, the preset rated differential pressure value is divided by the filter element differential pressure value currently measured by the differential pressure sensor to obtain the differential pressure correction factor. The preset rated differential pressure refers to the standard pressure difference when the filter element is running in a brand-new state; this value is preset at the factory according to the filter element model and specifications. Assuming the preset rated differential pressure is 200 Pa, and the currently measured differential pressure of the filter element is 400 Pa, then the differential pressure correction factor is 200 divided by 400, which equals 0.5. A differential pressure correction factor less than 1 indicates that the filter element is clogged; the smaller the value, the more severe the clog, and the actual airflow through the filter element will decrease accordingly. This factor quantifies the degree of filter element clogging into a calculable numerical parameter, allowing the ventilation volume calculation to reflect the true working state of the filter element.

[0020] Secondly, the rated ventilation volume is multiplied by the pressure difference correction factor to obtain the actual ventilation volume. In the example above, 3,000 cubic meters per hour multiplied by 0.5 yields an actual ventilation volume of 1,500 cubic meters per hour. Next, the equivalent pollutant concentration is calculated. Specifically, the pollutant concentrations at each environmental sensing node are weighted and averaged according to the spatial distance from the node to the filter element. First, the straight-line distance of each node relative to the filter element is calculated. Assume the six nodes in the workshop are 8 meters, 12 meters, 5 meters, 10 meters, 11 meters, and 9 meters from the filter element, respectively. In the weighted calculation, the closer the node, the greater its weight. The weight value is the reciprocal of the distance; that is, the first node has a weight of one-eighth, the second node one-twelfth, the third node one-fifth, and so on. The reciprocal weight is based on the airflow diffusion law; the closer a location is to the filter element, the higher the proportion of air drawn into the filter. Then, the concentration of a certain pollutant measured at each node is multiplied by the corresponding node's weight value. All multiplications are summed and divided by the sum of all weights to obtain the equivalent pollutant concentration. For example, if the PM10 concentrations at the six nodes are 180, 150, 220, 160, 190, and 170 micrograms per cubic meter, respectively, and a weighted average is calculated using the reciprocal of the aforementioned distances, the equivalent pollutant concentration of PM10 is 185 micrograms per cubic meter. This equivalent pollutant concentration represents the overall pollution level of the air actually drawn into the filter cartridge, more accurately reflecting the actual contribution of pollutants from different spatial locations to the filter cartridge's load.

[0021] Finally, the equivalent pollutant concentration for each pollutant is multiplied by the actual ventilation volume to obtain the mass flow rate of that pollutant through the filter element. For example, the equivalent pollutant concentration of PM10 is 185 micrograms per cubic meter, and the actual ventilation volume is 1500 cubic meters per hour. Multiplying the two gives 277,500 micrograms per hour, which is equivalent to 277.5 grams per hour. By performing this calculation separately for all monitored pollutant types, the mass flow rates of various pollutants such as PM2.5, PM10, and volatile organic compounds are obtained. The mass flow rate directly characterizes the mass of pollutants captured by the filter element per unit time and is a quantitative indicator for assessing the actual workload of the filter element. This parameter comprehensively reflects the pollution intensity and treatment capacity, providing an accurate calculation basis for subsequent load-weighted correction.

[0022] 103. Based on a preset load coefficient, the mass flow rate is adjusted by a filter element load weighting correction to obtain the current load value; In this embodiment, a pre-set load factor configuration table is read from the device memory. This configuration table is indexed according to pollutant type, with each pollutant corresponding to a load factor value. The load factor refers to the actual load on the filter element when a unit mass of a certain pollutant passes through it. This factor reflects the difference in the rate at which different pollutants consume the filter element's lifespan. In a factory workshop scenario, the load factor is set based on actual test data. The value is calibrated by having the filter element process a single type of pollutant and monitoring its clogging rate. For example, tests show that the pressure difference rise rate caused by processing one kilogram of oily particulate matter is 1.5 times that of processing one kilogram of dry dust. Therefore, the load factor for oily particulate matter is set to 1.5, and the load factor for dry dust is set to 1. Although volatile organic compounds are gaseous molecules, their adsorption on the activated carbon layer occupies adsorption sites and reduces subsequent filtration efficiency. Through a similar testing method, their load factor is determined to be 1.2. By obtaining the mass flow rate values ​​of each pollutant calculated in the aforementioned steps, the mass flow rate of each pollutant is multiplied by its corresponding load factor to obtain the corrected mass flow rate of each pollutant after load weighting. In practical calculations, the synergistic effects between particulate contaminants and the influence of ambient humidity on the filter element's operating status also need to be considered. These correction factors will be described in detail in the subsequent claims. The corrected mass flow rates of all contaminants are summed to obtain the current load value characterizing the overall working intensity of the filter element. This value is expressed in mass per hour; a larger value indicates a heavier load on the filter element. By introducing a load coefficient for weighted correction, the essential differences in the degree of burden caused by different contaminants on the filter element can be distinguished. This ensures that load assessment is no longer a simple mass accumulation but a true reflection of the combined effect of various contaminants on the actual consumption of filter element lifespan, avoiding lifespan prediction errors caused by treating all contaminants equally.

[0023] 104. Accumulate and calculate the load history data, differential pressure distribution data, and current load value in the working status data to obtain the filter life parameter. Based on the filter life parameter and the environmental parameter data, determine the target operating parameters and adjust the corresponding fan and valve of the purification equipment.

[0024] In this embodiment, the load history data in the working status data is multiplied by the historical load value of each time period and the corresponding working duration, and then summed to obtain the equivalent usage time; the ratio of the equivalent usage time to the rated life of the filter element is calculated to obtain the current clogging rate, and the benchmark filtration efficiency is determined based on the current clogging rate and a preset efficiency decay coefficient; the benchmark filtration efficiency is corrected based on the ratio of the current load value to the standard load value to obtain the current filtration efficiency, and the local clogging area and the corresponding priority clogging area of ​​the filter element are identified based on the differential pressure distribution data; the remaining usable time of the filter element is calculated based on the current filtration efficiency, and the filter element life parameters are generated based on the remaining usable time, the local clogging area, and the priority clogging area; based on a preset safety concentration threshold, The process involves determining whether the equivalent pollutant concentration exceeds pollution limits, obtaining a status determination result, determining the filter element status level corresponding to the filter element lifespan parameter based on preset clogging rate and time thresholds, determining the target ventilation volume and target filtration count for the purification equipment based on the status determination result and the filter element status level, and generating target operating parameters. The target fan speed is determined based on the target ventilation volume and preset fan characteristic curve, and the target fan speed is compensated and corrected based on the current clogging rate to obtain the corrected target fan speed. The internal circulation ratio of the purification equipment is calculated based on the target filtration count, and the target opening angle of the internal circulation valve is calculated based on the internal circulation ratio. The opening angle of the air inlet valve for the corresponding filter element area is adjusted based on the location distribution information of the priority clogging area. After adjusting the fans and valves corresponding to the purification equipment, the process includes: generating a corresponding level of early warning message based on the current blockage rate and the remaining available time, according to a preset grading threshold. The early warning message includes the current blockage rate, predicted remaining available time, and filtration efficiency information. When a preset advanced early warning threshold is triggered, the intelligent filter element recommendation process is initiated to obtain the user's historical replacement records and commonly used filter element models. Based on the historical replacement records and commonly used filter element models, the current filter element specifications and equipment model are determined to filter suitable candidate filter element models, and a recommendation scheme is generated and sent to the user's mobile terminal via a wireless communication module.

[0025] Specifically, the system first reads load history data from the memory. This data records the historical load value and corresponding working time for each period during the filter's operation in a time-series format. For example, the factory workshop memory records "Period 1 load value 800 grams per hour, running for 2 hours," "Period 2 load value 600 grams per hour, running for 3 hours," and "Period 3 load value 1 kilogram per hour, running for 1.5 hours." The controller reads these records one by one, multiplying the historical load value of each period by the corresponding working time and summing the results. In the example above, the contribution of period 1 is 800 multiplied by 2 equals 1600, period 2 is 600 multiplied by 3 equals 1800, and period 3 is 1000 multiplied by 1.5 equals 1500, with a total sum of 5000. The unit of this sum is grams per hour, representing the total amount of pollutants cumulatively processed by the filter. Next, the standard load value is read from the memory. This value represents the reference load that the filter withstands per unit time under standard operating conditions, set to 500 grams per hour in the factory workshop scenario. Dividing the cumulative sum by the standard load value yields an equivalent usage time of 10 hours. The equivalent usage time converts the operating time under different load intensities to a unified benchmark. For example, one hour of operation under a high load of 1 kg / h is equivalent to two hours of operation under a standard load of 500 kg / h. This conversion makes the lifespan consumption under different operating conditions comparable. The rated lifespan of the filter element is then read from memory, set to 1000 hours in a factory workshop scenario based on the filter element model. Dividing the equivalent usage time by the rated lifespan of the filter element yields the current clogging rate, which in the above example is 10 divided by 1000 equals 1%. The controller then determines the benchmark filtration efficiency based on the current clogging rate. The initial filtration efficiency and efficiency decay curve data of the filter element are read from memory. The initial filtration efficiency is set to 99.9%, and the efficiency decay curve records the efficiency retention coefficient corresponding to different clogging rates. The efficiency retention coefficient represents the proportion of efficiency maintained by the filter element relative to its initial state; this curve is obtained based on experimental testing of the filter element material. When the clogging rate is 1%, the efficiency retention coefficient is 0.995. The controller multiplies the initial filtration efficiency by the efficiency retention coefficient to obtain the benchmark filtration efficiency of 99.9 multiplied by 0.995, which calculates to 99.4%. The baseline filtration efficiency reflects the natural decline in filtration capacity of the filter cartridge due to clogging accumulation during its current usage phase. This value serves as a benchmark for evaluating filter cartridge performance. The ratio of the current load value to the standard load value is then calculated. With a current load of 831 grams per hour and a standard load of 500 grams per hour, the ratio is 1.66. This ratio indicates how many times the current load exceeds the standard load; a high load accelerates filter cartridge saturation and reduces its actual filtration efficiency. The load correction curve, which describes the efficiency reduction factor at different load multiples, is read from memory. When the load multiple is 1.66, the corresponding efficiency reduction factor is 0.6. Multiplying the baseline filtration efficiency by the efficiency reduction factor yields the current filtration efficiency of 99.4 multiplied by 0.6, which calculates to 59.6%.The current filtration efficiency reflects the filter element's true performance under current high-load conditions. The controller then identifies localized clogging areas based on differential pressure distribution data. It reads the differential pressure values ​​at nine measuring points on the filter element, calculating an average differential pressure of 400 Pa. Comparing the differential pressure at each measuring point with the average differential pressure, a localized clogging area is marked when the differential pressure at any measuring point exceeds 1.3 times the average differential pressure. This threshold is set based on engineering experience, indicating an abnormally high localized differential pressure. For example, the differential pressure at measuring point number three is 550 Pa, exceeding the average by 1.375 times, and is therefore marked as a localized clogging area. Further, the system identifies the measuring point with the fastest rate of differential pressure increase from historical differential pressure trend data as a priority clogging area. For example, the recent rate of differential pressure increase at measuring point number one is 10 Pa per hour, higher than other measuring points, and is marked as a priority clogging area. The identification of localized and priority clogging allows the system to understand the non-uniform distribution of the filter element's internal state. The system then reads the minimum allowable threshold for filtration efficiency from memory, setting it to 50% in a factory workshop scenario. The difference between the current filtration efficiency and the minimum threshold is calculated. With the current filtration efficiency at 59.6%, the efficiency margin is 9.6 percentage points. The efficiency decay rate is calculated based on the current load value and the efficiency decay curve. Specifically, the hourly efficiency decrease rate corresponding to the current load multiple is found in the decay curve. When the load multiple is 1.66, the corresponding decay rate is 0.5 percentage points per hour. Dividing the efficiency margin by the decay rate yields the remaining usable time: 9.6 divided by 0.5, which is approximately 19 hours. Subsequently, a filter cartridge life parameter data structure is generated. This structure includes four fields: current clogging rate of 1%, remaining usable time of 19 hours, third measuring point area of ​​local clogging region, and first measuring point area of ​​priority clogging region. The filter cartridge life parameters comprehensively describe the health status and expected lifespan of the filter cartridge, providing a complete status assessment basis for operation adjustment and maintenance decisions.

[0026] Secondly, the system reads a preset safe concentration threshold configuration table from memory. This table stores the corresponding concentration limits according to pollutant type. The preset safe concentration threshold refers to the upper limit of pollutant concentration to ensure a safe working environment. In factory workshop scenarios, it is set according to national occupational health standards. For example, the PM10 threshold is 150 micrograms per cubic meter, and the volatile organic compound threshold is 0.5 milligrams per cubic meter. The controller compares the equivalent pollutant concentration of each type of pollutant with the corresponding threshold one by one. When the concentration of any pollutant exceeds the threshold, it is marked as a pollution exceeding the standard state; otherwise, it is marked as a normal state. For example, if the PM10 concentration is 185 micrograms per cubic meter, exceeding the threshold, the state determination result is pollution exceeding the standard. Subsequently, the filter element status level is determined based on the current clogging rate and remaining usable time in the filter element life parameters. By reading the clogging rate threshold and time threshold from memory, the clogging rate threshold is divided into three levels: below 30% is a healthy state, 30% to 70% is a warning state, and above 70% is a critical state. The time threshold is divided into: more than 48 hours is a sufficient state, and less than 48 hours is an emergency state. The 48-hour setting takes into account the preparation cycle for maintenance personnel to purchase and replace spare parts. The controller, after comprehensively assessing the current blockage rate (1%) as healthy but the remaining 19 hours as urgent, assigns a warning level. This status determination and level classification allows the system to differentiate between two dimensions: the degree of environmental pollution and the equipment's own status. Based on the status determination result and the filter's status level, it queries a pre-set operational parameter decision table. This table stores the corresponding target ventilation volume and target filtration frequency, indexed by status combinations. The target ventilation volume refers to the airflow required to achieve the purification effect, and the target filtration frequency refers to the number of times air is circulated and filtered per unit time. In a factory workshop scenario, the decision table is set as follows: when pollution exceeds the standard and the filter is healthy, increase the ventilation volume to 3,000 cubic meters per hour and the filtration frequency to three times per hour; when pollution is normal but the filter is under warning, reduce the ventilation volume to 1,500 cubic meters per hour and the filtration frequency to twice per hour. The controller, based on the current pollution exceeding the standard and the filter under warning status, determines the target ventilation volume as 2,500 cubic meters per hour and the target filtration frequency as 2.5 times per hour. These two parameters are then packaged to generate the target operational parameters. This mechanism achieves a dynamic balance between environmental demands and equipment capacity, increasing purification efforts when pollution is severe and appropriately reducing the load when the equipment is nearing the end of its lifespan.

[0027] Next, the system reads preset fan characteristic curve data from memory, which describes the correspondence between fan speed and output ventilation volume. Based on the target ventilation volume, a precise speed value is calculated using linear interpolation on the characteristic curve. For example, if the target ventilation volume is 2500 cubic meters per hour, it is found that 1000 rpm corresponds to 2400 cubic meters per hour, and 1100 rpm corresponds to 2700 cubic meters per hour. The interpolation yields a target fan speed of 1033 rpm. The controller then performs compensation correction based on the current clogging rate. Compensation correction refers to the adjustment amount by increasing the fan speed to offset the increased air resistance caused by filter clogging. By reading the compensation coefficient table from memory, a compensation coefficient of 1.005 corresponds to a clogging rate of 1%. The target fan speed is then multiplied by the compensation coefficient to obtain a corrected target fan speed of 1038 rpm. This correction mechanism proactively compensates for the impact of clogging, preventing the actual ventilation volume from falling below the target value. Finally, the internal circulation ratio of the purification equipment is calculated based on the target filtration frequency. The internal circulation ratio refers to the percentage of airflow that returns from the filter outlet to the inlet for re-filtration, relative to the total processed airflow. It is calculated by subtracting one from the target filtration count and then dividing by the target filtration count. For example, if the target filtration count is 2.5, the internal circulation ratio is 1.5 divided by 2.5, resulting in 60%. The controller then calculates the target opening angle of the internal circulation valve based on this ratio. The internal circulation valve is a regulating valve installed at the connection between the filter outlet and inlet ducts. By reading the valve opening versus flow rate curve from memory, the controller finds the opening angle corresponding to 60% flow rate, thus determining the target opening angle of the internal circulation valve to be 54 degrees. The internal circulation mechanism allows the system to increase filtration intensity without increasing the external airflow. Furthermore, the system reads the location distribution information of the priority clogging area from the filter life parameters; in a factory workshop scenario, the priority clogging area is the first measuring point area. The corresponding inlet valve opening angle is adjusted based on the location of the priority clogging area. The inlet valve is an independent regulating valve installed on the inlet duct of each filter area. The adjustment strategy involves reducing the opening of the inlet valves in the priority blockage area to decrease the load on that area, while increasing the opening of other areas to maintain a constant total ventilation volume. This is achieved by reading the current opening of the inlet valves in each area from memory; assuming the current opening of area 1 is 60 degrees and the other eight areas are all at 55 degrees. Then, the flow characteristic parameters of the valves in each area are read from memory. The valve opening in area 1 is reduced by 10 to 50 degrees. Based on the valve characteristics, the flow reduction for that area is calculated. This reduction is then evenly distributed to the other eight areas to calculate the required increase in flow for each area. Finally, based on the valve characteristics of each area, the corresponding opening increase is determined, resulting in an increase of 1.25 to 56.25 degrees in the valve openings of the other eight areas. This differentiated inlet control allows the system to balance the lifespan of the filter cartridges across different areas.

[0028] Finally, the warning level is determined by querying a preset tiered threshold table based on the current blockage rate and remaining available time. The tiered threshold table divides warnings into three levels: Level 1 is a blockage rate below 50% with more than 72 hours remaining; Level 2 is a blockage rate between 50% and 70% or 24 to 72 hours remaining; and Level 3 is a blockage rate above 70% or less than 24 hours remaining. A Level 3 alarm is triggered when the current blockage rate is 1% but the remaining time is 19 hours. A warning message containing the current blockage rate, predicted remaining available time, and filtration efficiency information is generated and displayed on the screen. Tiered warnings allow managers to schedule maintenance plans based on urgency. Furthermore, when the warning level reaches Level 3, a higher warning threshold is triggered, automatically initiating the intelligent filter recommendation process. The system reads the user's historical replacement records and commonly used filter models from the database. Historical replacement records include the date, model, and duration of each replacement within the past twelve months. For example, the history might show that the user replaced filters five times in a year, using type A four times and type B once. By reading that the current filter cartridge specification is Type A, the system filters the filter cartridge database for compatible candidate models. Matching criteria include identical size specifications, consistent interface standards, and a filtration level no lower than the original model. The resulting candidate models are Type A, Type A upgraded version, and Type D. These candidate models are then sorted based on the user's historical preferences, generating a recommended solution message containing the names, specifications, estimated prices, and inventory status of the three candidate models. The recommended solution is then sent to the user's mobile terminal via a ZigBee wireless communication module. This intelligent recommendation process provides personalized recommendations based on historical behavior, improving the efficiency of purchasing decisions.

[0029] In this embodiment of the invention, environmental parameter data of the space to be purified and operating status data of the purification equipment are collected, and the spatiotemporal variation characteristics of pollutant concentration are extracted to generate environmental characteristic data. Based on the ventilation volume and environmental characteristic data in the operating status data, the mass flow rate of each pollutant through the filter element is calculated, and the mass flow rate is weighted and corrected using a preset load coefficient to obtain the current load value. By accumulating the load history data, pressure difference distribution data, and the current load value, the filter element lifespan parameter is obtained. Based on the filter element lifespan parameter and environmental parameter data, the target operating parameters are determined, and the corresponding fans and valves of the purification equipment are adjusted accordingly. Because this method achieves precise control through multi-dimensional environmental perception and dynamic load assessment, it can adaptively adjust the operating parameters according to changes in pollutant concentration and the actual state of the filter element, maximizing the filter element lifespan while ensuring the purification effect, thereby improving the working efficiency of the air purification system and the utilization rate of filter element resources.

[0030] Please see Figure 2 Another embodiment of the air purification filter control method based on environmental perception in this application includes: 201. Collect environmental parameter data of the space to be purified and working status data of the purification equipment, and extract the spatiotemporal variation values ​​of pollutant concentration in the environmental parameter data to generate environmental characteristic data; 202. Based on the ventilation volume in the working status data and the environmental characteristic data, calculate the mass flow rate of each pollutant passing through the filter element; In this embodiment, steps 201-202 are similar to steps 101-102 in the first embodiment, and will not be described again here.

[0031] 203. Determine the pollution concentration range of various particulate pollutants in the environmental characteristic data, and determine the corresponding synergy coefficient for each pollution concentration range based on a preset synergy coefficient comparison table; In this embodiment, equivalent pollutant concentration values ​​for various particulate pollutants are extracted from environmental characteristic data, and pollution concentration intervals are divided according to pre-set concentration thresholds. Pollution concentration intervals refer to segmenting pollutant concentrations into levels, with each interval corresponding to a different degree of pollution severity. In a factory workshop scenario, for PM10, the controller divides the concentration into three intervals: a low concentration interval (0 to 100 micrograms per cubic meter), a medium concentration interval (100 to 300 micrograms per cubic meter), and a high concentration interval (above 300 micrograms per cubic meter). Assuming the current equivalent pollutant concentration of PM10 is 250 micrograms per cubic meter, it is determined to belong to the medium concentration interval. The same interval determination is performed for other particulate pollutants such as PM2.5. Subsequently, a pre-set synergy coefficient lookup table is read from memory. This lookup table stores the corresponding synergy coefficient values ​​according to the combination of concentration intervals for different particulate pollutants. The synergy coefficient refers to the intensity of the load superposition caused by the interaction between particles when multiple particulate pollutants coexist; a value greater than one indicates that coexistence exacerbates filter clogging. The lookup table is organized as follows: each record contains a PM10 concentration range identifier, a PM2.5 concentration range identifier, and a corresponding synergy coefficient value. For example, the table stores a record like "PM10 medium concentration range - PM2.5 medium concentration range - synergy coefficient 1.2". This value is based on actual testing, which found that when both pollutants are in the medium concentration range, the filter clogging rate is 20% higher than the sum of the rates when treated individually. The controller matches the corresponding combination in the lookup table based on the current concentration range of each particulate pollutant and reads the synergy coefficient value. The synergy coefficient reflects the true characteristics of a multi-pollutant environment in a factory workshop. Large dust particles form a skeletal structure on the filter surface, while fine particles fill the gaps within. The synergy between these two factors leads to rapid pore clogging. This physical process is quantitatively characterized by the synergy coefficient, ensuring that the load calculation conforms to the actual clogging mechanism in a multi-pollutant mixed environment.

[0032] 204. Calculate the humidity difference between the air humidity and the preset humidity threshold in the environmental feature data, and perform a linear transformation on the humidity difference to obtain a humidity correction factor; In this embodiment, the current air humidity value is extracted from environmental characteristic data and compared with a preset humidity threshold read from memory. The preset humidity threshold is set to 60% relative humidity in a factory workshop scenario, corresponding to the standard operating humidity of the filter material. The humidity difference is obtained by subtracting the preset humidity threshold from the current humidity; for example, if the current humidity is 75%, the humidity difference is 15%. A linear transformation is then performed on the humidity difference to obtain a humidity correction factor. The specific operation of the linear transformation is: dividing the humidity difference by a preset humidity sensitivity coefficient and then adding one. The humidity sensitivity coefficient is set to 50%, which represents the multiple by which the filter load increases for every 50% increase in humidity. The value is based on experimental calibration of the moisture absorption characteristics of the filter material. In the above example, dividing the humidity difference of 15% by 50% yields 0.3, and adding one gives a humidity correction factor of 1.3, indicating that the filter load under the current humidity condition is 30% higher than at standard humidity. A humidity correction factor greater than one indicates increased load due to high humidity, and less than one indicates reduced load due to low humidity. In high humidity environments, particulate matter absorbs moisture and expands, increasing the contact area with the filter element. At the same time, moisture softens the filter element fibers, reducing their mechanical strength. Both factors combined make the filter element more prone to clogging. The humidity correction factor quantifies this humidity effect as a load correction parameter.

[0033] 205. Multiply the mass flow rate of particulate pollutants by the corresponding load factor and synergy factor, and multiply the mass flow rate of gaseous pollutants by the corresponding load factor, and sum the mass flow rates after humidity correction to obtain the current load value. In this embodiment, different correction calculations are performed for particulate pollutants and gaseous pollutants. For particulate pollutants, the corrected mass flow rate is obtained by multiplying the mass flow rate by the load factor, then by the synergy factor, and finally by the humidity correction factor. For example, if the PM10 mass flow rate is 277.5 g / h, the load factor is 1, the synergy factor is 1.2, and the humidity correction factor is 1.3, then the corrected mass flow rate is 277.5 multiplied by 1, 1.2, and 1.3, which equals 433.08 g / h. For gaseous pollutants, since gas molecules do not have a synergistic blockage effect between particles, only the mass flow rate is multiplied by the load factor and the humidity correction factor, without multiplying by the synergy factor. For example, if the volatile organic compound mass flow rate is 50 g / h, the load factor is 1.2, and the humidity correction factor is 1.3, the corrected mass flow rate is 78 g / h. The controller sums up the corrected mass flow rates of all pollutants to obtain the current load value. Assuming that the workshop also has PM2.5, which is corrected to 320 g / h, the total is the current load value of 831.08 g / h. This calculation process employs a differentiated correction strategy for different types of pollutants, considering co-clogging for particulate matter while excluding the effect for gaseous substances, so that the current load value accurately reflects the true working intensity of the filter element in a multi-pollutant, variable humidity environment.

[0034] 206. Accumulate and calculate the load history data, differential pressure distribution data, and current load value in the working status data to obtain the filter life parameter. Based on the filter life parameter and the environmental parameter data, determine the target operating parameters and adjust the corresponding fan and valve of the purification equipment.

[0035] In this embodiment, step 206 is similar to step 104 in the first embodiment, and will not be described again here.

[0036] In this embodiment, environmental parameter data of the space to be purified and operating status data of the purification equipment are collected, and the spatiotemporal variation characteristics of pollutant concentration are extracted to generate environmental characteristic data. Based on the ventilation volume and environmental characteristic data in the operating status data, the mass flow rate of each pollutant through the filter element is calculated, and the mass flow rate is weighted and corrected using a preset load coefficient to obtain the current load value. By accumulating the load history data, pressure difference distribution data, and the current load value, the filter element lifespan parameter is obtained. Based on the filter element lifespan parameter and environmental parameter data, the target operating parameters are determined, and the corresponding fans and valves of the purification equipment are adjusted accordingly. Because this method achieves precise control through multi-dimensional environmental perception and dynamic load assessment, it can adaptively adjust the operating parameters according to changes in pollutant concentration and the actual state of the filter element, maximizing the filter element lifespan while ensuring the purification effect, thereby improving the working efficiency of the air purification system and the utilization rate of filter element resources.

[0037] The above describes the air purification filter control method based on environmental perception in the embodiments of the present invention. The following describes the air purification filter control system based on environmental perception in the embodiments of the present invention. Please refer to [link / reference]. Figure 3 One embodiment of the air purification filter control system based on environmental perception in this invention includes: The feature generation unit 301 is used to collect environmental parameter data of the space to be purified and working status data of the purification equipment, and extract the spatiotemporal variation values ​​of pollutant concentration in the environmental parameter data to generate environmental feature data. The flow calculation unit 302 is used to calculate the mass flow rate of each pollutant through the filter element based on the ventilation volume in the working status data and the environmental characteristic data. The load assessment unit 303 is used to perform load weighting correction on the mass flow rate of the filter element based on a preset load coefficient to obtain the current load value; The control and adjustment unit 304 is used to accumulate and calculate the load history data, differential pressure distribution data and current load value in the working status data to obtain filter life parameters, and based on the filter life parameters and environmental parameter data, determine the target operating parameters and adjust the fans and valves corresponding to the purification equipment.

[0038] In this embodiment of the invention, environmental parameter data of the space to be purified and operating status data of the purification equipment are collected, and the spatiotemporal variation characteristics of pollutant concentration are extracted to generate environmental characteristic data. Based on the ventilation volume and environmental characteristic data in the operating status data, the mass flow rate of each pollutant through the filter element is calculated, and the mass flow rate is weighted and corrected using a preset load coefficient to obtain the current load value. By accumulating the load history data, pressure difference distribution data, and the current load value, the filter element lifespan parameter is obtained. Based on the filter element lifespan parameter and environmental parameter data, the target operating parameters are determined, and the corresponding fans and valves of the purification equipment are adjusted accordingly. Because this method achieves precise control through multi-dimensional environmental perception and dynamic load assessment, it can adaptively adjust the operating parameters according to changes in pollutant concentration and the actual state of the filter element, maximizing the filter element lifespan while ensuring the purification effect, thereby improving the working efficiency of the air purification system and the utilization rate of filter element resources.

[0039] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system or system / unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0040] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An environment-sensing-based air purification filter cartridge control method, characterized by, The air purification filter element control method based on environmental perception comprises: Collecting environmental parameter data of a space to be purified and working state data of a purification device, and extracting time and space variation values of pollutant concentrations in the environmental parameter data to generate environmental feature data; Based on the ventilation volume in the working state data and the environmental feature data, the mass flow rate of each pollutant through the filter element is calculated; Based on a preset load coefficient, the mass flow rate is subjected to load weighting correction of the filter element to obtain a current load value; The load history data and pressure difference distribution data in the working state data and the current load value are cumulatively calculated to obtain a filter element life parameter, and based on the filter element life parameter and the environmental parameter data, a target operating parameter is determined to adjust the corresponding fan and valve of the purification device.

2. The environment perception based air purification cartridge control method of claim 1, wherein, The extraction of the time and space variation values of the pollutant concentrations in the environmental parameter data to generate the environmental feature data comprises: The concentration difference values of the pollutant concentrations in the environmental parameter data at the current time and the previous time are calculated, and the concentration difference values are divided by the time difference between the current time and the previous time to obtain the time variation rate; Based on a plurality of environmental perception nodes deployed at different positions in the space to be purified, the spatial mean and spatial standard deviation of the pollutant concentrations in the environmental parameter data of the nodes at different positions are calculated; Based on the time variation rate, the spatial mean, the spatial standard deviation and the environmental parameter data, the environmental feature data is generated.

3. The environment perception based air purification cartridge control method of claim 2, wherein, The working state data comprises a current fan speed and a filter element pressure difference, and the calculation of the mass flow rate of each pollutant through the filter element based on the ventilation volume in the working state data and the environmental feature data comprises: The rated ventilation volume corresponding to the current fan speed is determined, and the pressure difference correction coefficient is determined according to the ratio of the filter element pressure difference to a preset rated pressure difference; The rated ventilation volume is multiplied by the pressure difference correction coefficient to obtain the actual ventilation volume, and the pollutant concentrations of each environmental perception node are weighted and averaged based on the spatial distance of each environmental perception node to obtain an equivalent pollutant concentration; The equivalent pollutant concentration is multiplied by the actual ventilation volume to obtain the mass flow rate of each pollutant through the filter element.

4. The environment perception based air purification cartridge control method of claim 1, wherein, The load weighting correction of the mass flow rate of the filter element based on the preset load coefficient to obtain the current load value comprises: The pollution concentration intervals of each type of particulate pollutant in the environmental feature data are determined, and the corresponding synergy coefficients of each pollution concentration interval are determined based on a preset synergy coefficient reference table; The humidity difference value of the air humidity in the environmental feature data and a preset humidity threshold value is calculated, and the humidity difference value is subjected to linear transformation to obtain a humidity correction factor; The mass flow rate of each type of particulate pollutant is multiplied by the corresponding load coefficient and synergy coefficient, and the mass flow rate of each type of gaseous pollutant is multiplied by the corresponding load coefficient, and the sum of the humidity-corrected mass flow rates of each type is summed to obtain the current load value.

5. The environment perception based air purification cartridge control method of claim 3, wherein, The cumulative calculation of the load history data and pressure difference distribution data in the working state data and the current load value to obtain the filter element life parameter comprises: The equivalent use time length is obtained by multiplying and accumulating the historical load value of each period and the corresponding working time length in the load history data in the working state data; The ratio of the equivalent use time length to the rated service life of the filter element is calculated to obtain a current clogging rate, and a reference filtration efficiency is determined according to the current clogging rate and a preset efficiency decay coefficient; The reference filtration efficiency is corrected according to the ratio of the current load value to a standard load value to obtain a current filtration efficiency, and a local clogging area and a corresponding priority clogging area of the filter element are identified based on differential pressure distribution data; Based on the current filtration efficiency, the remaining available time of the filter element is calculated, and a filter element service life parameter is generated based on the remaining available time, the local clogging area and the priority clogging area.

6. The environment perception based air purification cartridge control method of claim 5, wherein, The determination of the target operating parameter based on the filter element service life parameter and the environmental parameter data includes: Determine whether the equivalent pollutant concentration is a pollution exceeding standard state based on a preset safety concentration threshold to obtain a state determination result; Determine the filter element state level corresponding to the filter element service life parameter based on preset clogging rate threshold and time threshold; According to the state determination result and the filter element state level, determine the target air volume and target filtration frequency of the purification equipment to generate the target operating parameter.

7. The environment perception based air purification cartridge control method of claim 6, wherein, The adjustment of the fan and valve corresponding to the purification equipment includes: Determine the target fan speed according to the target air volume and the preset fan characteristic curve, and compensate and correct the target fan speed according to the current clogging rate to obtain the corrected target fan speed; According to the target filtration frequency, the internal circulation ratio of the purification equipment is calculated, and the target opening angle of the internal circulation valve is calculated according to the internal circulation ratio; Based on the position distribution information of the priority clogging area, the opening angle of the air inlet valve corresponding to the filter element area is adjusted.

8. An environment-sensing-based air purification filter cartridge control system, characterized by, The air purification filter element control system based on environmental perception includes: A feature generation unit is configured to collect environmental parameter data of a space to be purified and working state data of a purification equipment, and extract the spatio-temporal variation value of the pollutant concentration in the environmental parameter data to generate environmental feature data; A flow calculation unit is configured to calculate the mass flow of each pollutant through the filter element based on the air volume in the working state data and the environmental feature data; A load evaluation unit is configured to perform load weighting correction on the mass flow based on a preset load coefficient to obtain a current load value; A control adjustment unit is configured to perform cumulative calculation on the load history data, differential pressure distribution data and the current load value in the working state data to obtain a filter element service life parameter, and determine a target operating parameter based on the filter element service life parameter and the environmental parameter data, and adjust the fan and valve corresponding to the purification equipment.

Images