Method and system for prompting replacement of efficient filter screen of air purifier

Abstract

The invention relates to the field of household appliances, and discloses an air purifier efficient filter screen replacement prompting method and system.The method comprises the steps that firstly, air adsorption data are obtained, and the concentration of pollution particles is recognized to determine a filter screen load mode; analyzing the use state of the filter screen, and performing attenuation detection in combination with historical replacement records to obtain attenuation data; calculating the service residual life according to the attenuation data, evaluating a purification index, generating a filter screen efficiency index in combination with the environment air quality, and dividing replacement levels; then configuring multi-order prompt information according to levels, determining a filter screen edge area, calculating a penetration rate and positioning a weak part; and finally, generating a local failure graph, extracting failure interference factors, constructing adaptive replacement logic and formulating a replacement prompt scheme. The filter screen utilization rate can be increased, and the purification efficiency can be guaranteed.

Description

Technical Field

[0001] The invention relates to a method and system for prompting replacement of a high-efficiency filter screen of an air purifier, and belongs to the field of household appliances. Background Art

[0002] An air purifier is a device that uses a built-in fan to drive air circulation and uses high-efficiency filters (such as HEPA filters, activated carbon filters, etc.) to adsorb or decompose pollutants such as particulate matter and formaldehyde in the air. Its purification effect is highly dependent on the performance of the filter.

[0003] At present, existing technologies mainly implement filter replacement reminders through the following two methods: one is a fixed-period reminder based on a simple timer, which does not take into account the actual pollution load differences, resulting in premature replacement or overuse of the filter when it is not saturated; the other is to rely on a single sensor (such as a pressure sensor) to detect changes in filter resistance, which is prone to misjudgment due to interference from environmental temperature and humidity. For example, in low-pollution seasons, regular reminders will cause filter waste, while in high-pollution environments, the alarm may be delayed due to sensor drift, leading to the risk of secondary pollution. In addition, traditional solutions lack the ability to learn user usage habits and cannot adapt to different scenarios (such as the different needs of newly renovated rooms and daily maintenance). Most of them do not integrate cloud data comparison functions, making it difficult to accurately evaluate the filter life. Therefore, a high-efficiency filter replacement reminder method for air purifiers is needed to improve filter utilization and ensure purification efficiency. Summary of the Invention

[0004] The present invention provides a method and system for prompting replacement of a high-efficiency filter of an air purifier, the main purpose of which is to improve the utilization rate of the filter and ensure the purification efficiency.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for prompting replacement of a high-efficiency filter of an air purifier, comprising: Acquiring air adsorption data of the air purifier during operation, identifying a concentration of pollutant particles in the air adsorption data, and determining a filter load mode corresponding to the air purifier based on the concentration of pollutant particles; analyzing the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load pattern, querying historical replacement records corresponding to the filter usage status, and performing attenuation detection on the high-efficiency filter based on the historical replacement records to obtain filter attenuation data; Based on the filter attenuation data, the remaining service life of the high-efficiency filter is calculated, a purification index corresponding to the remaining service life is evaluated, and based on the purification index combined with the current ambient air quality, a filter efficiency index corresponding to the high-efficiency filter is generated, and a filter replacement level corresponding to the filter efficiency index is classified; Based on the filter replacement level, configuring multi-stage prompt information corresponding to the air purifier, determining the filter edge area corresponding to the high-efficiency filter based on the multi-stage prompt information, calculating the filter penetration rate corresponding to the filter edge area, and locating the structural weak point corresponding to the high-efficiency filter based on the filter penetration rate; Generate a local failure map corresponding to the weak part of the structure, and extract the failure interference factor in the local failure map. Based on the failure interference factor, construct an adaptive replacement logic corresponding to the air purifier. Based on the adaptive replacement logic, formulate a replacement reminder plan corresponding to the high-efficiency filter.

[0006] Optionally, determining a filter load mode corresponding to the air purifier based on the concentration of polluted particles includes: Extracting the instantaneous concentration peak value corresponding to the pollution particle concentration; dividing the polarization adsorption field corresponding to the instantaneous concentration peak; Matching the fan speed parameter corresponding to the polarization adsorption field; Based on the fan speed parameter, adjusting the filter adsorption threshold corresponding to the air purifier; A filter load mode corresponding to the air purifier is determined according to the filter adsorption threshold.

[0007] Optionally, analyzing the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load mode includes: Analyzing the particle deposition value corresponding to the load data in the filter load mode; identifying a localized clogged area in the HEPA filter based on the particle deposition value; Calculating the airflow resistance coefficient corresponding to the high-efficiency filter according to the local blockage area; Based on the airflow resistance coefficient, correcting the actual ventilation volume corresponding to the high-efficiency filter; The filter usage status of the high-efficiency filter is evaluated based on the actual ventilation volume.

[0008] Optionally, performing attenuation detection on the high-efficiency filter based on the historical replacement record to obtain filter attenuation data includes: Performing time series analysis on the historical replacement records to obtain a filter change sequence; Matching and calibrating the filter change sequence with a standard attenuation curve to obtain attenuation deviation data; Fitting the filter attenuation curve corresponding to the attenuation deviation data; Extracting key attenuation nodes in the filter attenuation curve; Based on the key attenuation nodes, the high efficiency filter is tested for attenuation to obtain filter attenuation data.

[0009] Optionally, the calculating the remaining service life of the high-efficiency filter based on the filter attenuation data includes: The following formula is used to calculate the remaining service life of the high-efficiency filter: ; in, Indicates the remaining service life of the high-efficiency filter. Indicates the initial filtration efficiency of the filter. Indicates the current filtration efficiency, represents the filter attenuation data, Indicates the cumulative usage time of the filter. represents the critical resistance value, Indicates the current airflow resistance. represents the resistance growth rate, Indicates the load correction factor.

[0010] Optionally, the dividing the filter replacement levels corresponding to the filter efficiency index includes: Extracting the efficiency attenuation gradient value corresponding to the filter efficiency index; Based on the efficiency attenuation gradient, dividing the efficiency interval corresponding to the filter efficiency index; extracting an impurity deposition value within the performance range; Constructing a filter replacement sequence corresponding to the high-efficiency filter according to the impurity deposition value; Classify the filter replacement levels corresponding to the filter replacement sequence

[0011] Optionally, configuring multi-level prompt information corresponding to the air purifier based on the filter replacement level includes: Querying the life threshold sequence corresponding to each level in the filter replacement level; Based on the life threshold sequence, dividing the warning interval of the purifier operation status; Analyze the priority association rules corresponding to the warning interval; Removing repeated prompt nodes in the priority association rule to obtain a simplified prompt instruction; Based on the simplified prompt instruction, multi-level prompt information corresponding to the air purifier is generated.

[0012] Optionally, calculating the filter penetration rate corresponding to the filter edge area includes: The filter penetration rate corresponding to the filter edge area is calculated using the following formula: ; in, Indicates the filter penetration rate corresponding to the filter edge area, represents the average filtration efficiency corresponding to the edge area of ​​the filter, represents the regional air flow rate, Indicates the gap leakage concentration, Indicates the gap leakage flow rate, Indicates the total air intake of the filter. represents the average inlet concentration.

[0013] Optionally, locating a structural weak point corresponding to the high-efficiency filter based on the filter penetration rate includes: Analyze the filter hole defect index corresponding to the filter penetration rate; Based on the filter pore defect index, identifying the abnormal pore area corresponding to the high-efficiency filter; Analyzing the filtration and permeability characteristics corresponding to the abnormal pore area; Based on the filtration permeability characteristics, determining a candidate weak area corresponding to the high-efficiency filter; Locate the structural weak parts in the weak candidate area.

[0014] In order to solve the above problems, the present invention also provides an air purifier high-efficiency filter replacement reminder system, the system comprising: a mode determination module, configured to obtain air adsorption data during operation of the air purifier, identify the concentration of pollutant particles in the air adsorption data, and determine a filter load mode corresponding to the air purifier based on the concentration of pollutant particles; an attenuation detection module, configured to analyze a filter usage status corresponding to a high-efficiency filter in the air purifier based on the filter load mode, query a historical replacement record corresponding to the filter usage status, and perform attenuation detection on the high-efficiency filter based on the historical replacement record to obtain filter attenuation data; a level classification module, configured to calculate the remaining service life of the high-efficiency filter based on the filter attenuation data, evaluate a purification index corresponding to the remaining service life, generate a filter efficiency index corresponding to the high-efficiency filter based on the purification index combined with current ambient air quality, and classify the filter replacement level corresponding to the filter efficiency index; a location positioning module, configured to configure multi-stage prompt information corresponding to the air purifier based on the filter replacement level, determine the filter edge area corresponding to the high-efficiency filter based on the multi-stage prompt information, calculate the filter penetration rate corresponding to the filter edge area, and locate the structural weak point corresponding to the high-efficiency filter based on the filter penetration rate; A plan formulation module is used to generate a local failure map corresponding to the weak parts of the structure, and extract the failure interference factors in the local failure map. Based on the failure interference factors, an adaptive replacement logic corresponding to the air purifier is constructed, and based on the adaptive replacement logic, a replacement reminder plan corresponding to the high-efficiency filter is formulated.

[0015] Compared with the problems described in the background technology, the present invention can accurately identify the concentration of polluted particles by obtaining the air adsorption data when the air purifier is running, provide a basis for judging the filter load mode, avoid the limitations of a single timer or sensor, reduce filter waste and the risk of overuse, and lay a data foundation for dynamically adjusting replacement strategies and adapting to multiple scenarios. The present invention analyzes the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load mode, and can dynamically evaluate the degree of filter loss in combination with real-time pollution intensity (such as high, medium, and low loads), avoiding the one-sidedness of single judgment based on time or fixed parameters, improving the scientificity and reliability of filter status evaluation, and optimizing resource utilization efficiency. Furthermore, the present invention calculates the remaining service life corresponding to the high-efficiency filter based on the filter attenuation data, and can quantify the degree of degradation of key performance indicators such as filtration efficiency and resistance, combined with historical The historical attenuation law predicts the time when the filter reaches the failure threshold, maximizes the filter utilization rate while ensuring purification efficiency, and reduces the cost of use. Furthermore, the present invention configures the multi-level prompt information corresponding to the air purifier based on the filter replacement level, which can prevent users from missing high-risk filters through graded warnings, and dynamic prompts can also link the equipment automatic control system (such as reducing the prompt frequency at low levels), while reducing information interference. Ensure that key maintenance needs are not ignored, optimize user experience and equipment management efficiency, and finally, the present invention generates a local failure map corresponding to the weak part of the structure and extracts the failure interference factor in the local failure map. It can intuitively display the location of the weak point and the degree of failure with a visual image (such as color coding, marking points), quickly locate the core of the problem, facilitate efficient investigation by maintenance personnel, avoid potential failure risks in advance, and improve the overall reliability and service life of the filter. Therefore, the air purifier high-efficiency filter replacement prompt method and system provided by the embodiment of the present invention can improve the filter utilization rate and ensure purification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process for prompting replacement of a high-efficiency filter of an air purifier provided by one embodiment of the present invention; Figure 2 A schematic diagram of rate filter attenuation detection in a method for prompting replacement of a high-efficiency filter of an air purifier provided by one embodiment of the present invention; Figure 3 A schematic diagram of a module for implementing a high-efficiency filter replacement reminder system for an air purifier provided in one embodiment of the present invention.

[0017] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] The embodiments of the present application provide a method for prompting the replacement of a high-efficiency filter in an air purifier. The execution subject of the method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application. In other words, the method for prompting the replacement of a high-efficiency filter in an air purifier can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0020] Example 1: Reference Figure 1 FIG. 1 is a flow chart of a method for prompting a high-efficiency filter replacement for an air purifier according to an embodiment of the present invention. In this embodiment, the method for prompting a high-efficiency filter replacement for an air purifier includes: S1. Acquire air adsorption data of an air purifier during operation, identify a concentration of pollutant particles in the air adsorption data, and determine a filter load mode corresponding to the air purifier based on the concentration of pollutant particles.

[0021] By acquiring the air adsorption data during the operation of the air purifier, the present invention can accurately identify the concentration of polluted particles, provide a basis for judging the filter load mode, avoid the limitations of a single timer or sensor, reduce filter waste and the risk of overuse, and lay a data foundation for dynamically adjusting replacement strategies and adapting to multiple scenarios.

[0022] Among them, the air purifier refers to a device that drives air circulation through a built-in fan and uses a high-efficiency filter (such as a HEPA filter, an activated carbon filter, etc.) to adsorb or decompose particulate matter, formaldehyde and other pollutants in the air. Its purification effect depends on the performance of the filter. For example, a household air purifier can be placed in the living room or bedroom to continuously filter indoor polluted air and improve air quality. The air adsorption data refers to the data reflecting the characteristics of air pollutants and environmental conditions collected by sensors when the air purifier is running, including the concentration of polluting particles such as PM2.5, PM10, formaldehyde, and environmental parameters such as temperature and humidity. For example, the indoor PM2.5 concentration detected at a specific moment is 45μg / m 3 , formaldehyde concentration 0.06mg / m 3, temperature 22°C, humidity 55%, these data together constitute the air adsorption data. Optionally, the acquisition of air adsorption data during the operation of the air purifier can be achieved through a sensor acquisition method, such as: using PM2.5 sensors, formaldehyde sensors and other equipment to monitor the concentration of particulate matter and harmful gases in the air in real time, thereby obtaining air adsorption data.

[0023] Furthermore, by identifying the concentration of pollutant particles in the air adsorption data, the present invention can accurately determine the current environmental pollutant load level, such as clarifying the specific concentration values ​​of PM2.5 and formaldehyde; providing a core basis for dividing the filter load mode, distinguishing high, medium and low load scenarios to adapt to differentiated analysis, ensuring purification efficiency while improving resource utilization.

[0024] The particle concentration refers to the content of various types of pollutants (such as solid particulate matter and gaseous pollutant molecules) in the air per unit volume, which is used to quantify the degree of air pollution. Common indicators include the mass concentration of PM2.5 and PM10 (unit: μg / m 3 ), volume concentration of gaseous pollutants such as formaldehyde (unit: mg / m 3 ), for example, the PM2.5 concentration in the office was detected to be 60μg / m 3 (higher than the WHO annual average guidance value), formaldehyde concentration 0.12mg / m 3 (exceeding the indoor air quality standard limit), intuitively reflecting the severity of pollution in the space, and providing key data support for filter load assessment. Optionally, the identification of the concentration of polluted particles in the air adsorption data can be achieved through optical particle counting methods, such as: using a laser scattering sensor (such as a TSI particle counter) to measure the scattered light intensity of particles of different particle sizes in the air, thereby obtaining the concentration of polluted particles.

[0025] Furthermore, the present invention determines the filter load mode corresponding to the air purifier based on the concentration of the polluted particles, and can accurately divide the high, medium and low load scenarios according to the real-time concentrations of PM2.5, formaldehyde, etc., so that the filter status assessment is more in line with the actual pollution intensity, thereby improving the purification efficiency and resource utilization efficiency.

[0026] Among them, the filter load mode refers to the classification and definition of the current working intensity and pressure of the filter based on comprehensive factors such as pollution particle concentration, polarization adsorption field, fan speed parameters and filter adsorption threshold. It is mainly divided into high load, medium load and low load modes. The high load mode indicates that the filter faces a high-intensity pollutant filtration task; the low load mode indicates that the filter working pressure is relatively small. For example, when the instantaneous concentration peak is high, it is in a strong polarization adsorption field, the fan is running at high speed and the filter adsorption threshold is close to the critical value, the filter is judged to be in high load mode, and it is suggested that the filter status should be closely monitored.

[0027] As an embodiment of the present invention, determining the filter load mode corresponding to the air purifier based on the pollution particle concentration includes: extracting the instantaneous concentration peak corresponding to the pollution particle concentration; dividing the polarization adsorption field corresponding to the instantaneous concentration peak; matching the fan speed parameter corresponding to the polarization adsorption field; adjusting the filter adsorption threshold corresponding to the air purifier based on the fan speed parameter; and determining the filter load mode corresponding to the air purifier according to the filter adsorption threshold.

[0028] The instantaneous concentration peak refers to the highest value of the concentration of pollutants detected by the air purifier in a very short period of time, which reflects the instantaneous and drastic changes in the concentration of pollutants in the air. For example, in a room near a busy road, when the window is opened, the air purifier detects that the PM2.5 concentration increases from 30μg / m2 to 40μg / m3 in 1 minute. 3 Rapidly rise to 80 μg / m 3 , this 80μg / m 3 That is, the instantaneous concentration peak value of the period; the polarization adsorption field refers to the regional division of the air environment around the air purifier based on the instantaneous concentration peak value. Different areas correspond to different pollutant adsorption characteristics. When the instantaneous concentration peak value is high, a strong polarization adsorption field will be formed, and the pollutants are densely distributed and active; when the peak value is low, it is a weak polarization adsorption field. For example, when a large amount of oil smoke is generated during cooking in the kitchen, a strong polarization adsorption field is formed in the kitchen area. The air purifier needs a stronger adsorption capacity in this area to cope with high concentrations of pollutants; the fan speed parameter refers to the speed index of the fan in the air purifier. The air can be controlled by adjusting the fan speed. The flow rate affects the adsorption efficiency of the filter. The fan speed parameter corresponding to high pollution concentration is higher, which can speed up air circulation and make the filter contact pollutants faster. When the pollution concentration is low, the speed parameter is lower to save energy. For example, in a strong polarization adsorption field, adjusting the fan speed parameter to high speed can enable the air purifier to process more polluted air per minute. The filter adsorption threshold refers to the concentration limit value at which the filter can effectively adsorb pollutants. When the concentration of pollutant particles in the air exceeds this threshold, the filter needs to improve its adsorption efficiency to ensure the purification effect. For example, under normal conditions, the filter adsorption threshold is set to a PM2.5 concentration of 50μg / m 3 If the polarization adsorption field is in a high-concentration polluted environment and the fan is running at high speed, the threshold can be adjusted to 60μg / m 3 , to adapt to stronger purification needs.

[0029] Furthermore, the extraction of the instantaneous concentration peak corresponding to the pollution particle concentration can be achieved through a sliding window detection method, such as: using a dynamic time warping (DTW) algorithm to analyze time series data and identify local extreme points, thereby obtaining an instantaneous concentration peak; the division of the polarization adsorption field corresponding to the instantaneous concentration peak can be achieved through an electric field intensity clustering method, such as: spatially partitioning the particle charge characteristics based on the K-means algorithm, calculating the field intensity distribution of each region, thereby obtaining a polarization adsorption field; the matching of the fan speed parameter corresponding to the polarization adsorption field can be achieved through a fuzzy logic control method, such as: establishing a stochastic gradient descent algorithm. The attribute function library dynamically adjusts the PWM output value according to the field strength range, thereby obtaining the fan speed parameter; the adjustment of the filter adsorption threshold corresponding to the air purifier can be achieved through an adaptive PID control method, such as: based on the particle deposition rate estimated by the Kalman filter, the electrostatic adsorption voltage of the HEPA filter is corrected in real time to obtain the filter adsorption threshold; the determination of the filter load mode corresponding to the air purifier can be achieved through a decision tree classification method, such as: constructing a judgment rule tree of multi-dimensional features (wind resistance value, cumulative running time) based on the C4.5 algorithm, outputting the current load level, thereby obtaining the filter load mode.

[0030] Specifically, to further understand the relevant principles and processes of filter attenuation detection in this application, please refer to Figure 2 The filter attenuation detection diagram shown in Figure 2 This is a schematic diagram of the filter attenuation detection provided by the present invention. It should be noted that in the present invention, this schematic diagram is only used to show the connection relationship and signal flow of each key link in the filter load mode process. It can obtain harmful substance signals from the air sensor and transmit them to the MCU control unit after signal processing and A / D conversion. These data can be used to determine the filter load mode. When analyzing the filter usage status based on the filter load mode, the MCU control unit integrates relevant data, such as combining load data to determine parameters such as particulate matter deposition value, and then identifies local blockage areas, calculates the airflow resistance coefficient and corrects the actual ventilation volume to evaluate the filter usage status. In the process of querying historical replacement records and performing filter attenuation detection, the MCU control unit also plays a key role in data processing and analysis. The power circuit provides power support for the entire system to ensure the normal operation of the detection process; the motor control affects the ventilation volume and is related to the actual ventilation volume calculation and other links. Through the collaborative work of these parts, the analysis of the usage status of the high-efficiency filter and attenuation detection are realized, but it is not limited to the specific relationship analysis of each part in monitoring different actual application scenarios.

[0031] S2. Based on the filter load pattern, analyze the filter usage status corresponding to the high-efficiency filter in the air purifier, query the historical replacement record corresponding to the filter usage status, and perform attenuation detection on the high-efficiency filter based on the historical replacement record to obtain filter attenuation data.

[0032] The present invention analyzes the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load pattern, and can dynamically evaluate the degree of filter loss in combination with real-time pollution intensity (such as high, medium, and low loads), avoiding the one-sidedness of judgment based solely on time or fixed parameters, improving the scientificity and reliability of filter status evaluation, and optimizing resource utilization efficiency.

[0033] Among them, the high-efficiency filter refers to a filter component made of special materials and processes that can efficiently adsorb or decompose pollutants in the air. Common types include HEPA filters (can filter particles ≥ 0.3μm, with a filtration efficiency of more than 99.97%), activated carbon filters (adsorb formaldehyde, odor and other gaseous pollutants), photocatalyst filters (catalytically decompose harmful gases), etc. For example, the HEPA filter installed in a household air purifier can effectively intercept tiny particles such as PM2.5, pollen, and bacteria, while the activated carbon filter is used to remove pollutants such as formaldehyde and benzene left over from decoration. The two are combined to form a high-efficiency purification system, which is the core component of the air purifier to achieve high purification efficiency; the filter usage status refers to the comprehensive load data, particulate deposition, local blockage, airflow resistance and ventilation volume and other parameters, and the comprehensive evaluation results of the current performance of the high-efficiency filter, including clean status, light blockage, moderate blockage, heavy blockage and other levels. For example, when the actual ventilation volume drops to 70% of the nominal value, the resistance coefficient exceeds 1.5 and there is a large area of ​​local blockage, the filter is judged to be in a "heavy blockage" state and needs to be replaced immediately to avoid the risk of secondary pollution.

[0034] As an embodiment of the present invention, the filter usage status corresponding to the high-efficiency filter in the air purifier is analyzed based on the filter load pattern, including: parsing the particle deposition value corresponding to the load data in the filter load pattern; identifying the local blockage area in the high-efficiency filter based on the particle deposition value; calculating the airflow resistance coefficient corresponding to the high-efficiency filter based on the local blockage area; correcting the actual ventilation volume corresponding to the high-efficiency filter based on the airflow resistance coefficient; and evaluating the filter usage status of the high-efficiency filter based on the actual ventilation volume.

[0035] The particle deposition value refers to the mass or volume of solid pollutants (such as PM2.5, dust, pollen, etc.) accumulated per unit area of ​​the high-efficiency filter during the operation of the air purifier, reflecting the total amount of pollutants intercepted by the filter. For example, after running in high-load mode for 24 hours, 0.05 mg of particulate matter is deposited per square centimeter in a certain area of ​​the HEPA filter. This value can be used to quantify the degree of pollution load of the filter. The load data refers to the core parameter set that characterizes the pollution intensity and working pressure in the filter load mode, including the concentration of pollutant particles (such as PM2.5 and formaldehyde concentration), duration, fan speed, air handling capacity, etc. For example, the PM2.5 concentration is continuously greater than 75 μg / m in a certain period of time. 3 (High load threshold), fan high-speed operation, cumulative air processing volume up to 5000m 3 These data together constitute load data, which are used to analyze the actual working intensity of the filter. The localized blockage area refers to a specific area on the surface of the high-efficiency filter where the porosity decreases and airflow is blocked due to excessive particle deposition. This is usually related to uneven airflow distribution, filter structure design, or localized pollution concentration. For example, turbulent airflow easily forms particle deposition hotspots at the edge of the filter or deep in the folds. When the particle deposition value in this area exceeds the average level by 30%, it can be determined to be a localized blockage area. The airflow resistance coefficient is a dimensionless parameter that measures the degree of air flow obstruction caused by the high-efficiency filter. It is related to the filter porosity, particle deposition amount, airflow velocity, etc. For example, when the particle deposition value in the localized blockage area of ​​the filter increases by 20%, the airflow resistance coefficient increases from 0.8 to 1.2, indicating that the energy loss of air passing through the filter increases, and the fan power needs to be increased to maintain ventilation volume. The actual ventilation volume refers to the actual volume of air passing through the air purifier per unit time after taking into account the airflow resistance of the filter. The calculation formula is "theoretical ventilation volume × (1-resistance attenuation coefficient)". For example, if the theoretical ventilation volume of the model is 500m 3 / h, when the air flow resistance coefficient causes the ventilation volume to decrease by 15%, the actual ventilation volume drops to 425m 3 / h, directly affects the purification efficiency.

[0036] Furthermore, analyzing the particle deposition value corresponding to the load data in the filter load mode can be achieved through differential pressure analysis, such as using a micro-differential pressure sensor to measure the pressure difference across the filter and calculating the deposition mass in combination with the Darcy formula to obtain the particle deposition value. Identifying localized blockage areas in the HEPA filter can be achieved through infrared thermal imaging, such as using a FLIR thermal imager to detect areas of abnormal temperature distribution on the filter surface, locate the location of airflow obstruction, and thereby obtain the localized blockage area. Calculating the airflow resistance coefficient corresponding to the HEPA filter can be achieved through fluid dynamics simulation, such as establishing a porous media model based on ANSYS Fluent software and simulating pressure drop curves at different flow rates to obtain the airflow resistance coefficient. Correcting the actual ventilation volume corresponding to the HEPA filter can be achieved through a Kalman filter algorithm, such as fusing the raw data from the wind speed sensor with the resistance coefficient compensation to iteratively estimate the true flow value to obtain the actual ventilation volume. Evaluating the filter usage status of the HEPA filter can be achieved through a fuzzy comprehensive evaluation method, such as constructing a membership function matrix containing indicators such as deposition volume and resistance coefficient, and outputting a filter health score to obtain the filter usage status.

[0037] The present invention queries the historical replacement records corresponding to the usage status of the filter, and can analyze the historical replacement time, cumulative filtration volume and other data of the filter under the same status to explore the filter loss pattern, provide a horizontal comparison benchmark for the current filter attenuation detection, and improve the accuracy of the remaining life estimation and the adaptability of the replacement prompt.

[0038] Among them, the historical replacement record refers to the detailed information archive of all the replacement operations of the air purifier's high-efficiency filter, including the replacement time, the filter usage time at the time of replacement, the cumulative total amount of filtered pollutants, the filter usage status before replacement (such as the degree of blockage, ventilation volume attenuation value), the environmental parameters at that time (such as pollution concentration, usage scenario), and the triggering conditions for the user to actively replace or the system to prompt for replacement, etc. For example, if the filter is triggered to be replaced on a certain day of a certain month of a certain year because the actual ventilation volume drops to 65% of the theoretical value and the local blockage rate reaches 40%, the average PM2.5 concentration of 80μg / m during that period will be retained in the record at the same time. 3 , the usage scenario is data such as a newly renovated office, which can provide a historical reference for subsequent filter status analysis. Optionally, the query of historical replacement records corresponding to the filter usage status can be achieved through a time series database retrieval method, such as: using InfluxDB to store device operation logs, querying filter replacement event records by time range, and thus obtaining historical replacement records.

[0039] Furthermore, the present invention performs attenuation detection on the high-efficiency filter based on the historical replacement records to obtain filter attenuation data. With the help of the attenuation law of the filter under the same load mode in the historical data, the current filter performance attenuation trend can be quickly located, thereby reducing the cost of excessive use or premature replacement of the filter.

[0040] Among them, the filter attenuation data refers to the quantitative indicators obtained through attenuation detection that reflect the current degree of filter performance degradation, including filtration efficiency attenuation rate, resistance increase value, ventilation volume attenuation ratio, etc. For example, the test found that the formaldehyde adsorption capacity of the activated carbon filter decreased by 40% compared with the initial value, and the airflow resistance increased by 30Pa. These data together constitute the filter attenuation data.

[0041] As an embodiment of the present invention, the attenuation detection is performed on the high-efficiency filter based on the historical replacement records to obtain filter attenuation data, including: performing time series analysis on the historical replacement records to obtain a filter change sequence; matching and calibrating the filter change sequence with a standard attenuation curve to obtain attenuation deviation data; fitting the filter attenuation curve corresponding to the attenuation deviation data; extracting key attenuation nodes in the filter attenuation curve; and performing attenuation detection on the high-efficiency filter based on the key attenuation nodes to obtain filter attenuation data.

[0042] Among them, the filter change sequence refers to an ordered data set of filter performance indicators extracted from historical replacement records that change over time, including time series values ​​of parameters such as filtration efficiency, airflow resistance, and ventilation volume attenuation rate. For example, if the historical records of the HEPA filter show that its filtration efficiency decreases by 1% every 3 months from the initial 99.97%, and the airflow resistance increases by 5 Pa every 2 months, a performance parameter sequence that changes over time is formed; the attenuation deviation data refers to the difference between the filter change sequence and the standard attenuation curve (the theoretical attenuation trend preset based on the filter design life and ideal working conditions), reflecting the degree of deviation between the actual attenuation rate and the theoretical expectation. For example, the standard curve shows that the filtration efficiency of a filter decreases by 5% every year, while a certain filter actually decreases by 4% every six months, then the attenuation deviation data is "every six months + 1.5%" (positive deviation indicates accelerated attenuation); the filter attenuation curve refers to a personalized attenuation trend curve obtained by fitting the attenuation deviation data, which intuitively shows the actual attenuation trajectory of the filter performance over time or filtration volume. For example, combined with the historical deviation data of a certain filter (accelerated attenuation under high load), an exponential attenuation curve is fitted, showing that its filtration efficiency decreases exponentially with the cumulative filtered air volume; the key attenuation node refers to the critical point on the filter attenuation curve that marks a significant change in performance, such as the filtration efficiency falling below 95%, the airflow resistance exceeding the design threshold, the ventilation volume decaying to 80% of the theoretical value, etc., which trigger a replacement prompt. For example, when the attenuation curve shows that the filter ventilation volume drops to 75% of the theoretical value after 500 cumulative hours of operation, this time point is the key attenuation node that needs attention.

[0043] Furthermore, the time series analysis of the historical replacement records can be achieved through a time series decomposition method, such as: using the STL algorithm to separate the seasonal and trend components of the replacement records, thereby obtaining a filter change sequence; the matching and calibration of the filter change sequence with the standard attenuation curve can be achieved through a dynamic time warping method, such as: using the DTW algorithm to align the time axis of the actual observation sequence and the standard curve, thereby obtaining attenuation deviation data; the fitting of the filter attenuation curve corresponding to the attenuation deviation data can be achieved through a nonlinear regression method, such as: optimizing the parameter fitting of the exponential attenuation model based on the LM algorithm, thereby obtaining a filter attenuation curve; the extraction of key attenuation nodes in the filter attenuation curve can be achieved through a mutation point detection method, such as: applying a CUSUM control chart to identify the turning point where the slope of the curve changes significantly, thereby obtaining a key attenuation node; the attenuation detection of the high-efficiency filter can be achieved through a multi-sensor fusion method, such as: integrating real-time data from a differential pressure sensor, a particle counter, and an airflow sensor, and calculating a comprehensive attenuation score through DS evidence theory, thereby obtaining filter attenuation data.

[0044] S3. Based on the filter attenuation data, calculate the remaining service life of the high-efficiency filter, evaluate the purification index corresponding to the remaining service life, generate the filter efficiency index corresponding to the high-efficiency filter based on the purification index combined with the current ambient air quality, and divide the filter replacement level corresponding to the filter efficiency index.

[0045] The present invention calculates the remaining service life of the high-efficiency filter based on the filter attenuation data. It can quantify the degree of degradation of key performance indicators such as filtration efficiency and resistance, and combine historical attenuation laws to predict the time when the filter reaches the failure threshold. While ensuring purification efficiency, the present invention maximizes the filter utilization rate and reduces the cost of use.

[0046] Among them, the remaining service life refers to the length of time that the filter can continue to be used normally from the current moment to the moment when its performance deteriorates to the point where it cannot meet the usage requirements (such as low filtration efficiency, excessive resistance affecting ventilation, etc.), calculated by the above formula based on the current attenuation condition of the filter. The unit is usually hours, days or months.

[0047] As an embodiment of the present invention, the calculating the remaining service life of the high-efficiency filter based on the filter attenuation data includes: The following formula is used to calculate the remaining service life of the high-efficiency filter: ; in, Indicates the remaining service life of the high-efficiency filter. Indicates the initial filtration efficiency of the filter. Indicates the current filtration efficiency, represents the filter attenuation data, Indicates the cumulative usage time of the filter. represents the critical resistance value, Indicates the current airflow resistance. represents the resistance growth rate, Indicates the load correction factor.

[0048] Specifically, the initial filtration efficiency of the filter refers to the filtration capacity of the filter for specific pollutants (such as particulate matter, harmful gases, etc.) when the filter is in a new state and has not been put into use, determined and calibrated by the manufacturer according to relevant standards and test methods. It is generally expressed in percentage form. For example, the initial filtration efficiency of a HEPA filter can reach 99.97%; the current filtration efficiency refers to the actual filtration capacity of the filter for pollutants at the current moment after a period of use. Usually, the concentration of pollutants at the air inlet and outlet of the filter is detected, and the concentration is calculated according to a specific calculation method (such as , is the pollutant concentration at the air inlet, is the concentration of pollutants at the air outlet), also presented in percentage form; the cumulative use time of the filter refers to the total time the filter has been in continuous operation from the time the filter was first put into use to the current moment, and the unit is generally hours, which can be obtained through the equipment operation log record or the built-in timing device; the resistance critical value refers to an airflow resistance limit value pre-set according to the design requirements and usage specifications of the filter. When the airflow resistance of the filter reaches or exceeds this value, it will seriously affect the ventilation performance, resulting in a significant increase in equipment energy consumption, a significant decrease in air volume and other problems. At this time, the filter needs to be replaced; the current airflow resistance refers to the resistance encountered by the airflow when passing through the filter in the current use state, and the unit is Pascal (Pa). It is generally obtained by real-time measurement through pressure sensors installed before and after the filter; the The resistance growth rate refers to the average increase in airflow resistance per unit time (such as per hour or per day) during the use of the filter, and is expressed in Pascals / hour (Pa / h). It reflects the speed at which the resistance of the filter increases with the use time, and can be obtained based on statistical analysis of historical data; the load correction coefficient refers to a correction coefficient that is set by comprehensively considering the influence of load factors such as pollutant concentration and frequency of use in the actual use environment of the filter on the attenuation rate of the filter. Its numerical range is generally within a certain interval (such as 0.5-1.5). When in a high-load environment (such as high pollutant concentration and frequent use), this coefficient will shorten the calculated remaining life; in a low-load environment, the coefficient will extend the remaining life, thereby more accurately reflecting the remaining usable time of the filter under different usage conditions.

[0049] Furthermore, by evaluating the purification index corresponding to the remaining service life, the present invention can accurately grasp the changes in indicators such as filtration efficiency and resistance, and predict the decline in the purification performance of the filter in advance, so as to avoid the purification effect not meeting the standard and affecting the air quality.

[0050] The purification index refers to the quantitative parameters that measure the purification capacity and effect of the filter. It mainly includes filtration efficiency, which is the filtration ratio of pollutants, such as the filtration efficiency of PM2.5; airflow resistance, which reflects the degree of obstruction of airflow through the filter; and ventilation volume, which refers to the volume of air passing through the filter per unit time. For example, a HEPA filter has a filtration efficiency of 99%, an airflow resistance of 100Pa, and a ventilation volume of 500m 3 / h. Optionally, the evaluation of the purification index corresponding to the remaining service life can be achieved through a particle counting analysis method, such as: using a laser particle counter to monitor the PM2.5 / PM10 filtration efficiency in real time, calculating the percentage of the current purification capacity to the initial value, and thus obtaining the purification index.

[0051] Furthermore, the present invention generates a filter efficiency index corresponding to the high-efficiency filter based on the purification index combined with the current ambient air quality. The filter replacement can be planned in advance according to the index to avoid insufficient purification or waste of resources. It can also provide users and managers with an intuitive reference to assist in optimizing the air purification system operation strategy and improve the overall purification effect and efficiency.

[0052] Among them, the filter efficiency index refers to a quantitative value obtained by a specific algorithm based on the comprehensive filter purification indicators (such as filtration efficiency, airflow resistance, ventilation volume, etc.) and the current ambient air quality (pollutant concentration, pollution type, etc.), which is used to measure the ability of the filter to play a purifying role in the actual environment. For example, in a highly polluted environment, if the filter has high filtration efficiency and low resistance, the calculated efficiency index is high, indicating that its purification performance is good. Optionally, the generation of the filter efficiency index corresponding to the high-efficiency filter can be achieved through a multi-parameter weighted evaluation method, such as: establishing an evaluation system including dimensions such as filtration efficiency, wind resistance coefficient, and service life, and using the AHP hierarchical analysis method to determine the weight distribution, thereby obtaining the filter efficiency index.

[0053] Furthermore, the present invention can present the filter performance in an intuitive hierarchy (such as "normal, attention, warning, replacement") by dividing the filter replacement level corresponding to the filter efficiency index, thereby lowering the user's understanding threshold of professional indicators and quickly locating maintenance needs; by setting quantitative thresholds (such as an index ≤70 for "warning" and ≤50 for "replacement"), high-risk level filters are given priority, optimizing maintenance costs and efficiency while ensuring purification effects.

[0054] The filter replacement level refers to the maintenance level defined according to the filter replacement sequence, which is usually divided into "emergency replacement (level I), priority replacement (level II), regular replacement (level III)", etc., to facilitate resource allocation. For example, the impurity deposition value is >0.15mg / cm 2 The filter is classified as Level I (red alert) and needs to be replaced within 24 hours; 0.08~0.15mg / cm 2 Level II (yellow warning), treatment required within 1 week; <0.08 mg / cm 2 It is level III (green) and should be replaced according to the regular cycle.

[0055] As an embodiment of the present invention, the dividing of the filter replacement levels corresponding to the filter efficiency index includes: extracting the efficiency attenuation gradient value corresponding to the filter efficiency index; dividing the efficiency interval corresponding to the filter efficiency index based on the efficiency attenuation gradient value; extracting the impurity deposition value within the efficiency interval; constructing a filter replacement sequence corresponding to the high-efficiency filter based on the impurity deposition value; and dividing the filter replacement levels corresponding to the filter replacement sequence.

[0056] The efficiency attenuation gradient refers to the rate gradient of the filter efficiency index decreasing with the use time or the amount of pollutants accumulated, reflecting the speed of performance degradation. The unit is "index value / unit time" or "index value / unit amount of pollutants". For example, if the filter is under high load, the filter efficiency index will decrease every 1000m 3 For polluted air, the efficiency index drops from 100 to 95, and its attenuation gradient is -0.005 / m 3 , indicating that the greater the pollution load, the faster the efficiency declines; the efficiency range refers to the division of the filter efficiency index into several continuous ranges based on the efficiency decay gradient value, each range corresponding to a different performance state, for example, divided into "high efficiency range (≥85), medium efficiency range (60-85), and low efficiency range (<60)", corresponding to the filter's "normal operation", "needs attention", and "urgent replacement" status, respectively, to facilitate hierarchical management; the impurity deposition value refers to the mass or volume of pollutants accumulated per unit area of ​​the filter within the efficiency range, measured by weighing, image recognition and other technologies, and is directly related to efficiency decay. For example, in the low efficiency range (efficiency index <60), an activated carbon filter was detected to deposit 0.15mg of formaldehyde per square centimeter, far exceeding the designed adsorption threshold, indicating that its purification capacity has significantly decreased; the filter replacement sequence refers to a filter maintenance priority list arranged from small to large according to the impurity deposition value. The higher the deposition value, the more urgent the replacement of the filter. For example, the filters of multiple devices in the same air purification system are ranked according to the impurity deposition value A (0.2mg / cm 2 )>B(0.12mg / cm 2 )>C(0.05mg / cm 2 ), forming a replacement sequence [A→B→C], giving priority to high-load filters.

[0057] Furthermore, the extraction of the efficiency attenuation gradient value corresponding to the filter efficiency index can be achieved through a first-order difference calculation method, such as: performing a differential operation on the efficiency index sequence in a continuous time window, calculating the attenuation slope per unit time, and thus obtaining the efficiency attenuation gradient value; the division of the efficiency interval corresponding to the filter efficiency index can be achieved through a dynamic clustering method, such as: applying the DBSCAN density clustering algorithm to automatically identify the natural distribution boundary of the efficiency data, generating a multi-level efficiency interval, and thus obtaining the efficiency interval; the extraction of the impurity deposition value in the efficiency interval can be achieved through an image recognition method, such as: using the OpenCV library to process The filter microscopic image is used to quantify the coverage area of ​​the deposited particles through an edge detection algorithm, thereby obtaining the impurity deposition value; the construction of the filter replacement sequence corresponding to the high-efficiency filter can be achieved through a time series pattern mining method, such as: using the PrefixSpan algorithm to analyze the frequent sequence patterns in the historical replacement records to generate a predictive replacement sequence, thereby obtaining the filter replacement sequence; the division of the filter replacement levels corresponding to the filter replacement sequence can be achieved through a fuzzy comprehensive evaluation method, such as: establishing a membership function including indicators such as usage time and efficiency decay rate, and outputting the replacement urgency level through weighted aggregation, thereby obtaining the filter replacement level.

[0058] S4. Based on the filter replacement level, configure multi-level prompt information corresponding to the air purifier, determine the filter edge area corresponding to the high-efficiency filter based on the multi-level prompt information, calculate the filter penetration rate corresponding to the filter edge area, and locate the structural weak parts corresponding to the high-efficiency filter based on the filter penetration rate.

[0059] The present invention configures multi-level prompt information corresponding to the air purifier based on the filter replacement level, and can prevent users from missing high-risk filters through graded early warning. Dynamic prompts can also link with the equipment automatic control system (such as reducing the prompt frequency at low levels), while reducing information interference to ensure that key maintenance needs are not ignored, thereby optimizing user experience and equipment management efficiency.

[0060] Among them, the multi-level prompt information refers to the graded prompt content generated according to the simplified prompt instructions, which is conveyed to the user through the device terminal (such as display screen, APP, voice system). For example, the level I prompt is "

Red Alert

Yellow Reminder

Green Status

[0061] As an embodiment of the present invention, the multi-level prompt information corresponding to the air purifier is configured based on the filter replacement level, including: querying the life threshold sequence corresponding to each level in the filter replacement level; dividing the warning interval of the purifier operation status based on the life threshold sequence; analyzing the priority association rules corresponding to the warning interval; removing repeated prompt nodes in the priority association rules to obtain simplified prompt instructions; and generating multi-level prompt information corresponding to the air purifier based on the simplified prompt instructions.

[0062] Among them, the life threshold sequence refers to a set of critical values ​​of remaining life corresponding to the filter replacement level (such as level I, level II, and level III), which is used to mark the trigger nodes of different maintenance levels. For example, level I (emergency replacement) corresponds to a remaining life of ≤3 days, level II (priority replacement) corresponds to 3 days < remaining life ≤15 days, and level III (routine replacement) corresponds to a remaining life of >15 days, forming a stepped threshold sequence; the warning interval refers to the operating status range of the purifier divided according to the life threshold sequence, and each interval corresponds to a specific prompt strategy. For example, when the remaining life of the filter falls into the "≤3 days" interval, a level I red warning is triggered; when it falls into the "4~15 When the warning interval exceeds 15 days, a Level II yellow warning is triggered; when it exceeds 15 days, it is a Level III green prompt interval, and the prompt content and frequency are dynamically adjusted with the interval level; the priority association rule refers to defining the mapping relationship between different warning intervals and prompt information priorities to ensure that high-level replacement needs receive a higher response weight. For example, the rule sets "Level I warning requires pop-up window + voice dual prompt, triggered once an hour; Level II warning only has pop-up window prompt, triggered once a day; Level III warning displays a green icon in the device APP, synchronized once a week", avoiding information overload through priority differences; the streamlined prompt instruction refers to an efficient instruction set formed after deduplication of repeated or redundant prompt nodes in the priority association rule. For example, the repeated general prompts of "Filter needs to be replaced" at different levels are eliminated, and "Urgent! Remaining life < 3 days, replace immediately" is retained for Level I, and "Warning! Remaining life 7 days, it is recommended to replace this week" is retained for Level II to ensure that each instruction is unique and accurate.

[0063] Furthermore, the query of the life threshold sequence corresponding to each level in the filter replacement level can be implemented by a rule engine retrieval method, such as: defining a level-threshold mapping rule library in the Drools rule engine, extracting the corresponding threshold sequence through pattern matching, and thus obtaining the life threshold sequence; the division of the warning interval of the purifier operation status can be implemented by a fuzzy C-means clustering method, such as: based on the multidimensional feature space of the operating parameters, determining the optimal cluster center through iterative optimization, thereby obtaining the warning interval; the analysis of the priority association rules corresponding to the warning interval can be implemented by an Apriori algorithm, such as: mining frequent item sets in historical warning data, generating association rules with support-confidence standards, thereby obtaining priority association rules; the removal of duplicate prompt nodes in the priority association rules can be implemented by a graph theory deduplication method, such as: constructing a rule dependency graph, applying the Tarjan algorithm to identify and merge strongly connected components, thereby obtaining a streamlined prompt instruction; the generation of multi-level prompt information corresponding to the air purifier can be implemented by a state machine conversion method, such as: designing a Mealy-type finite state machine, triggering corresponding prompt strategies according to the current warning level and user operation history, thereby obtaining multi-level prompt information.

[0064] The present invention determines the filter edge area corresponding to the high-efficiency filter based on the multi-level prompt information, and can combine the local blockage data associated with high-level prompts (such as Level I warning) to quickly locate pollution concentration points in areas prone to deposition such as edge folds, thereby avoiding increased maintenance costs due to comprehensive disassembly and inspection, thereby extending the overall service life of the filter and improving purification stability.

[0065] Among them, the filter edge area refers to the surrounding areas where the high-efficiency filter contacts the air purifier frame, as well as special structural areas such as folds and joints on the filter edge itself. These areas are prone to pollutant deposition and local blockage due to factors such as uneven airflow distribution and sealing friction. For example, the edge of the HEPA filter of a household air purifier is often not tightly sealed with the casing, resulting in dust and hair carried by high-speed airflow preferentially accumulating here, causing increased local resistance and affecting the overall performance of the filter. Optionally, the determination of the filter edge area corresponding to the high-efficiency filter can be achieved through an image edge detection method, such as: applying the Canny operator to process the filter surface image, extracting the structural contour feature point set, and thus obtaining the filter edge area.

[0066] Furthermore, the present invention can accurately evaluate the degree of pollutant leakage caused by sealing defects or blockages at the edge by calculating the filter penetration rate corresponding to the edge area of ​​the filter. For example, when the penetration rate reaches 8%, it can be determined that the edge purification has failed and timely maintenance is required; by analyzing the difference in penetration rate between the edge and the main area (for example, the edge penetration rate is 4 percentage points higher than the center), the structural weak points can be quickly located, providing data support for filter design optimization or installation process improvement.

[0067] Among them, the filter penetration rate refers to the proportion of pollutants that are not effectively filtered by the edge area of ​​the filter and directly pass through this area under specific operating conditions, to the total amount of pollutants entering the filter. It is presented in decimal form. The lower the value, the better the purification effect of the edge area of ​​the filter. For example, a penetration rate of 5% means that 5% of the pollutants are not effectively filtered.

[0068] As an embodiment of the present invention, the calculating the filter penetration rate corresponding to the filter edge area includes: The filter penetration rate corresponding to the filter edge area is calculated using the following formula: ; in, Indicates the filter penetration rate corresponding to the filter edge area, represents the average filtration efficiency corresponding to the edge area of ​​the filter, represents the regional air flow rate, Indicates the gap leakage concentration, Indicates the gap leakage flow rate, Indicates the total air intake of the filter. represents the average inlet concentration.

[0069] In detail, the average filtration efficiency refers to the average level of the filter edge area's ability to filter pollutants within a certain period of time, expressed as a percentage. It comprehensively reflects the ability of the filter in the edge area to intercept and adsorb pollutants. For example, if the average filtration efficiency of the edge area is 80%, it means that theoretically 80% of the pollutants entering the area can be filtered out. The regional airflow rate refers to the volume of air passing through the filter edge area per unit time (usually per hour), expressed in cubic meters per hour (m3 / h). 3 / h), which reflects the flow rate of air in the edge area. The flow rate will affect the contact time between pollutants and the filter and the filtering effect. For example, the regional air flow rate is 100m 3 / h; the gap leakage concentration refers to the concentration of pollutants that leak directly from the gaps between the filter and the equipment frame without being filtered by the filter, and the unit is micrograms per cubic meter (μg / m 3 ), the higher the concentration, the more pollutants leak from the gap. For example, the gap leakage concentration is 50μg / m 3 The gap leakage flow rate refers to the volume of air leaking out through the gap at the edge of the filter per unit time (per hour), and the unit is cubic meters per hour (m 3 / h), which reflects the rate of air leakage at the gap. The larger the leakage flow, the easier it is to cause pollutant leakage. For example, the gap leakage flow is 5m 3 / h; The total air intake of the filter refers to the total volume of air entering the entire filter per unit time (per hour), and the unit is cubic meters per hour (m 3 / h), is an important parameter when the equipment is running, which is usually calibrated by the equipment manufacturer. For example, the total air intake of the filter is 500m 3 / h; The inlet average concentration refers to the average concentration of pollutants entering the filter within a certain period of time (such as 1 hour), and the unit is micrograms per cubic meter (μg / m 3 ), which is obtained by taking the average value of multiple measurements of the inlet pollutant concentration during this period, and is used to measure the pollution load level entering the filter. For example, the average inlet concentration is 100μg / m 3 .

[0070] Furthermore, the present invention locates the structural weak parts corresponding to the high-efficiency filter based on the filter penetration rate, and can quickly lock the poor sealing or filtration failure points through the high penetration rate area. It can dynamically monitor the changes in weak parts according to the penetration rate, and give early warning of potential faults to ensure stable and reliable operation of the air purification system.

[0071] Among them, the structural weak part refers to the specific location in the weak candidate area where there is actually a structural defect, which causes the filtering performance of the filter to be significantly reduced. It can be a damaged filter material, a place where the splicing gap is too large, etc. For example, if a small damage is found in the filter material in the weak candidate area, pollutants can easily penetrate from here. This damaged point is the structural weak part.

[0072] As an embodiment of the present invention, locating the structural weak parts corresponding to the high-efficiency filter based on the filter penetration rate includes: analyzing the filter pore defect index corresponding to the filter penetration rate; identifying the abnormal pore area corresponding to the high-efficiency filter based on the filter pore defect index; analyzing the filtration permeability characteristics corresponding to the abnormal pore area; determining the weak candidate area corresponding to the high-efficiency filter based on the filtration permeability characteristics; and locating the structural weak parts in the weak candidate area.

[0073] The pore defect index is a numerical indicator used to quantify the degree of pore defect in a filter. It comprehensively considers factors such as pore size deviation, shape irregularity, and clogging. For example, if the normal pore size is 0.3 μm, and the average pore size in a region deviates by 0.05 μm and a certain proportion of irregularly shaped pores are present, the pore defect index for that region is calculated to be 0.6 (ranging from 0 to 1, with higher values ​​indicating more severe defects). The abnormal pore area is defined as a region on a filter where pore characteristics differ significantly from the normal state. This can manifest as abnormally increased or decreased pore size or severe pore clogging. For example, if a localized area of ​​the filter is heavily clogged with dust, resulting in a porosity far below normal, this region is considered an abnormal pore area. The filter permeability characteristics are properties that reflect the ease and regularity with which pollutants pass through the filter pores, including pollutant penetration rate and penetration volume. For example, if the PM2.5 penetration rate of a filter is 10 μg / m3 per hour at a specific wind speed, the filter may have a PM2.5 penetration rate of 10 μg / m3 per hour. 2 The infiltration volume is related to factors such as wind speed and pollutant concentration, which reflects the filtration and infiltration characteristics of the filter under these conditions; the weak candidate areas refer to areas that may have structural weaknesses and are preliminarily screened out based on the abnormal pore areas and their filtration and infiltration characteristics. These areas are more prone to pollutant penetration during the filtration process due to abnormal pores. For example, after analysis, it was determined that two areas of the filter had abnormal pores and poor infiltration characteristics, and these two areas became weak candidate areas.

[0074] Furthermore, the analysis of the filter pore defect index corresponding to the filter mesh penetration rate can be achieved through a microscopic image analysis method, such as: using a scanning electron microscope to obtain a filter mesh microstructure image, and calculating the pore size distribution variation coefficient through the OpenCV library to obtain the filter pore defect index; the identification of the abnormal pore area corresponding to the high-efficiency filter mesh can be achieved through an X-ray tomography method, such as: using industrial CT equipment for three-dimensional imaging, combining the regional growth algorithm to mark the density abnormal area, and thus obtaining the abnormal pore area; the analysis of the filtration permeability characteristics corresponding to the abnormal pore area can be achieved through a computational fluid dynamics simulation method, such as: in COMSOL A porous medium model is established in Multiphysics to simulate the local flow velocity distribution under different pressure differences, thereby obtaining the filtration permeability characteristics; the determination of the weak candidate area corresponding to the high-efficiency filter can be achieved through a thermal stress analysis method, such as: simulating the stress concentration area under temperature cycle through the ANSYS thermodynamic module, identifying the material fatigue risk point, and thus obtaining the weak candidate area; the positioning of the structural weak parts in the weak candidate area can be achieved through an acoustic emission detection method, such as: arranging a piezoelectric sensor array, analyzing the time-frequency characteristics of the filter vibration signal through wavelet transform, and accurately locating the microcrack position, thereby obtaining the structural weak parts.

[0075] S5. Generate a local failure map corresponding to the weak part of the structure, and extract the failure interference factor in the local failure map. Based on the failure interference factor, construct an adaptive replacement logic corresponding to the air purifier. Based on the adaptive replacement logic, formulate a replacement reminder plan corresponding to the high-efficiency filter.

[0076] By generating a local failure map corresponding to the weak parts of the structure and extracting the failure interference factors in the local failure map, the present invention can intuitively display the location of the weak points and the degree of failure with a visual image (such as color coding and marking points), quickly locate the core of the problem, facilitate efficient troubleshooting by maintenance personnel, avoid potential failure risks in advance, and improve the overall reliability and service life of the filter.

[0077] Among them, the local failure map refers to a schematic diagram that graphically presents the failure of weak parts of the high-efficiency filter structure. It uses different colors, symbols or textures to intuitively display the location, range and failure degree of the weak parts. For example, the red area represents the part where the filter is severely damaged, and the yellow area represents the area where the filter holes are more clogged. The distribution of the failed parts can be clearly seen on the map, which is convenient for the staff to quickly locate the problem; the failure interference factor refers to various factors that lead to the failure of the weak parts of the high-efficiency filter structure, including physical factors (such as filter material wear, pore blockage), chemical factors (such as filter material corrosion), etc. For example, if the filter is in a high-concentration acidic gas environment for a long time, the filter material will be chemically corroded, and the acidic gas concentration will increase. It is an interference factor that causes failure; for example, due to long-term high-speed scouring of airflow, the filter material in a certain part of the filter screen is severely worn, and the airflow velocity is a related interference factor. Optionally, the generation of the local failure map corresponding to the weak part of the structure can be achieved by the finite element stress cloud map method, such as: meshing the weak part in ABAQUS software, and visualizing the high stress area through the VonMises stress cloud map to obtain the local failure map; the extraction of the failure interference factor in the local failure map can be achieved by image texture analysis method, such as: applying the Gabor filter group to extract the texture features of the failure area, and obtaining the key interference features through principal component analysis dimensionality reduction, thereby obtaining the failure interference factor.

[0078] Furthermore, based on the failure interference factor, the present invention constructs an adaptive replacement logic corresponding to the air purifier, which can dynamically adjust the filter replacement strategy according to the key influencing factors monitored in real time (such as corrosive gas concentration and airflow scouring intensity), avoid the blindness of fixed-period replacement, and improve the accuracy and timeliness of maintenance.

[0079] Among them, the adaptive replacement logic refers to an intelligent mechanism of the air purifier that dynamically adjusts the filter replacement strategy based on the real-time monitored filter failure interference factors (such as pollutant concentration, filter material wear degree, ambient temperature and humidity, etc.). The preset algorithm comprehensively evaluates the influence of factors and automatically matches the optimal replacement time. For example, when it is detected that the filter in an industrial environment has been corroded by acidic gas, causing the filtration efficiency to drop to 70% and the resistance to exceed 80% of the critical value, the system triggers an "emergency replacement" instruction instead of replacing it according to a fixed 3-month cycle to achieve "on-demand maintenance". Optionally, the construction of the adaptive replacement logic corresponding to the air purifier can be achieved through reinforcement learning methods, such as: using the Q-learning algorithm to establish a state-action value function, and dynamically optimizing the replacement decision strategy based on real-time performance data, thereby obtaining an adaptive replacement logic.

[0080] Furthermore, based on the adaptive replacement logic, the present invention formulates a replacement reminder plan corresponding to the high-efficiency filter, which can dynamically generate differentiated reminder content according to the real-time failure factor, avoid the lag or redundancy of fixed-cycle reminders, optimize the full-scene maintenance experience and reduce the purification efficiency loss caused by maintenance delays.

[0081] Among them, the replacement reminder plan refers to a filter maintenance reminder strategy generated according to the adaptive replacement logic. By integrating real-time failure interference factor data (such as filtration efficiency, resistance, environmental parameters, etc.), a systematic plan including reminder timing, content, and form is formulated. For example, the replacement reminder plan for a household air purifier can be set as follows: when the filter resistance exceeds 150% of the initial value and the PM2.5 penetration rate is greater than 8%, an orange warning message "Filter efficiency drops to 65%, it is recommended to replace it within 7 days" can be pushed through the APP, and the remaining life countdown can be displayed simultaneously on the device display to guide users to maintain it in time. Optionally, the formulation of the replacement reminder plan corresponding to the high-efficiency filter can be achieved through a multi-objective decision-making method, such as: applying the TOPSIS algorithm to comprehensively consider indicators such as filter life, purification efficiency and user usage habits to generate the optimal reminder strategy, thereby obtaining a replacement reminder plan.

[0082] Compared with the problems described in the background technology, the present invention can accurately identify the concentration of polluted particles by obtaining the air adsorption data when the air purifier is running, provide a basis for judging the filter load mode, avoid the limitations of a single timer or sensor, reduce filter waste and the risk of overuse, and lay a data foundation for dynamically adjusting replacement strategies and adapting to multiple scenarios. The present invention analyzes the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load mode, and can dynamically evaluate the degree of filter loss in combination with real-time pollution intensity (such as high, medium, and low loads), avoiding the one-sidedness of single judgment based on time or fixed parameters, improving the scientificity and reliability of filter status evaluation, and optimizing resource utilization efficiency. Furthermore, the present invention calculates the remaining service life corresponding to the high-efficiency filter based on the filter attenuation data, and can quantify the degree of degradation of key performance indicators such as filtration efficiency and resistance, combined with historical The historical attenuation law predicts the time when the filter reaches the failure threshold, maximizes the filter utilization rate while ensuring purification efficiency, and reduces the cost of use. Furthermore, the present invention configures the multi-level prompt information corresponding to the air purifier based on the filter replacement level, which can prevent users from missing high-risk filters through graded warnings, and dynamic prompts can also link the equipment automatic control system (such as reducing the prompt frequency at low levels), while reducing information interference. Ensure that key maintenance needs are not ignored, optimize user experience and equipment management efficiency, and finally, the present invention generates a local failure map corresponding to the weak part of the structure and extracts the failure interference factor in the local failure map. It can intuitively display the location of the weak point and the degree of failure with a visual image (such as color coding, marking points), quickly locate the core of the problem, facilitate efficient investigation by maintenance personnel, avoid potential failure risks in advance, and improve the overall reliability and service life of the filter. Therefore, the air purifier high-efficiency filter replacement prompt method and system provided by the embodiment of the present invention can improve the filter utilization rate and ensure purification efficiency.

[0083] Example 2: like Figure 3 1 is a functional module diagram of a high-efficiency filter replacement reminder system for an air purifier according to the present invention.

[0084] The air purifier high-efficiency filter replacement reminder system 200 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the air purifier high-efficiency filter replacement reminder system may include a mode determination module 201, an attenuation detection module 202, a level classification module 203, a location location module 204, and a solution formulation module 205. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0085] In the embodiment of the present invention, the functions of each module / unit are as follows: The mode determination module 201 is configured to obtain air adsorption data during operation of the air purifier, identify the concentration of pollutant particles in the air adsorption data, and determine a filter load mode corresponding to the air purifier based on the concentration of pollutant particles; The attenuation detection module 202 is configured to analyze the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load mode, query the historical replacement records corresponding to the filter usage status, and perform attenuation detection on the high-efficiency filter based on the historical replacement records to obtain filter attenuation data; The level classification module 203 is configured to calculate the remaining service life of the high-efficiency filter based on the filter attenuation data, evaluate a purification index corresponding to the remaining service life, generate a filter efficiency index corresponding to the high-efficiency filter based on the purification index combined with the current ambient air quality, and classify the filter replacement level corresponding to the filter efficiency index; The location location module 204 is configured to configure multi-stage prompt information corresponding to the air purifier based on the filter replacement level, determine the filter edge area corresponding to the high-efficiency filter based on the multi-stage prompt information, calculate the filter penetration rate corresponding to the filter edge area, and locate the structural weak point corresponding to the high-efficiency filter based on the filter penetration rate; The plan formulation module 205 is used to generate a local failure map corresponding to the weak part of the structure, and extract the failure interference factor in the local failure map, based on the failure interference factor, construct the adaptive replacement logic corresponding to the air purifier, and based on the adaptive replacement logic, formulate a replacement reminder plan corresponding to the high-efficiency filter.

[0086] In detail, each module in the air purifier high efficiency filter replacement reminder system 200 described in the embodiment of the present invention adopts the same method as above when in use. Figure 1 The technical means described in the invention are the same as the method for prompting the replacement of the high-efficiency filter of an air purifier and can produce the same technical effects, so they will not be repeated here.

[0087] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for prompting replacement of a high-efficiency filter of an air purifier, characterized in that: The method comprises: Acquiring air adsorption data of the air purifier during operation, identifying a concentration of pollutant particles in the air adsorption data, and determining a filter load mode corresponding to the air purifier based on the concentration of pollutant particles; analyzing the filter usage status corresponding to the high-efficiency filter in the air purifier based on the filter load pattern, querying historical replacement records corresponding to the filter usage status, and performing attenuation detection on the high-efficiency filter based on the historical replacement records to obtain filter attenuation data; Based on the filter attenuation data, the remaining service life of the high-efficiency filter is calculated, a purification index corresponding to the remaining service life is evaluated, and based on the purification index combined with the current ambient air quality, a filter efficiency index corresponding to the high-efficiency filter is generated, and a filter replacement level corresponding to the filter efficiency index is classified; Based on the filter replacement level, configuring multi-stage prompt information corresponding to the air purifier, determining the filter edge area corresponding to the high-efficiency filter based on the multi-stage prompt information, calculating the filter penetration rate corresponding to the filter edge area, and locating the structural weak point corresponding to the high-efficiency filter based on the filter penetration rate; Generate a local failure map corresponding to the weak part of the structure, and extract the failure interference factor in the local failure map. Based on the failure interference factor, construct an adaptive replacement logic corresponding to the air purifier. Based on the adaptive replacement logic, formulate a replacement reminder plan corresponding to the high-efficiency filter.

2. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, characterized in that: The determining, based on the concentration of polluted particles, a filter load mode corresponding to the air purifier includes: Extracting the instantaneous concentration peak value corresponding to the pollution particle concentration; dividing the polarization adsorption field corresponding to the instantaneous concentration peak; Matching the fan speed parameter corresponding to the polarization adsorption field; Based on the fan speed parameter, adjusting the filter adsorption threshold corresponding to the air purifier; A filter load mode corresponding to the air purifier is determined according to the filter adsorption threshold.

3. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, characterized in that: The analyzing, based on the filter load mode, the filter usage status corresponding to the high-efficiency filter in the air purifier, includes: Analyzing the particle deposition value corresponding to the load data in the filter load mode; identifying a localized clogged area in the HEPA filter based on the particle deposition value; Calculating the airflow resistance coefficient corresponding to the high-efficiency filter according to the local blockage area; Based on the airflow resistance coefficient, correcting the actual ventilation volume corresponding to the high-efficiency filter; The filter usage status of the high-efficiency filter is evaluated based on the actual ventilation volume.

4. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, wherein: The attenuation detection of the high-efficiency filter based on the historical replacement record to obtain filter attenuation data includes: Performing time series analysis on the historical replacement records to obtain a filter change sequence; Matching and calibrating the filter change sequence with a standard attenuation curve to obtain attenuation deviation data; Fitting the filter attenuation curve corresponding to the attenuation deviation data; Extracting key attenuation nodes in the filter attenuation curve; Based on the key attenuation nodes, the high-efficiency filter is subjected to attenuation detection to obtain filter attenuation data.

5. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, characterized in that: The calculating the remaining service life of the high-efficiency filter based on the filter attenuation data includes: The following formula is used to calculate the remaining service life of the high-efficiency filter: ； in, Indicates the remaining service life of the high-efficiency filter. Indicates the initial filtration efficiency of the filter. Indicates the current filtration efficiency, represents the filter attenuation data, Indicates the cumulative usage time of the filter. represents the critical resistance value, Indicates the current airflow resistance. represents the resistance growth rate, Indicates the load correction factor.

6. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, wherein: The filter replacement level corresponding to the filter efficiency index includes: Extracting the efficiency attenuation gradient value corresponding to the filter efficiency index; Based on the efficiency attenuation gradient, dividing the efficiency interval corresponding to the filter efficiency index; extracting an impurity deposition value within the performance range; Constructing a filter replacement sequence corresponding to the high-efficiency filter according to the impurity deposition value; The filter replacement sequence is divided into filter replacement levels.

7. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, characterized in that: The configuring of multi-level prompt information corresponding to the air purifier based on the filter replacement level includes: Querying the life threshold sequence corresponding to each level in the filter replacement level; Based on the life threshold sequence, dividing the warning interval of the purifier operation status; Analyze the priority association rules corresponding to the warning interval; Removing repeated prompt nodes in the priority association rule to obtain a simplified prompt instruction; Based on the simplified prompt instruction, multi-level prompt information corresponding to the air purifier is generated.

8. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, wherein: The calculating the filter penetration rate corresponding to the filter edge area includes: The filter penetration rate corresponding to the filter edge area is calculated using the following formula: ； in, Indicates the filter penetration rate corresponding to the filter edge area, represents the average filtration efficiency corresponding to the edge area of ​​the filter, represents the regional air flow rate, Indicates the gap leakage concentration, Indicates the gap leakage flow rate, Indicates the total air intake of the filter. represents the average inlet concentration.

9. The method for prompting replacement of a high-efficiency filter of an air purifier according to claim 1, wherein: The method of locating the structural weak points corresponding to the high-efficiency filter based on the filter penetration rate includes: Analyze the filter hole defect index corresponding to the filter penetration rate; Based on the filter pore defect index, identifying the abnormal pore area corresponding to the high-efficiency filter; Analyzing the filtration and permeability characteristics corresponding to the abnormal pore area; Based on the filtration permeability characteristics, determining a candidate weak area corresponding to the high-efficiency filter; Locate the structural weak parts in the weak candidate area.

10. An air purifier high efficiency filter replacement reminder system, characterized in that: The system comprises: a mode determination module, configured to obtain air adsorption data during operation of the air purifier, identify the concentration of pollutant particles in the air adsorption data, and determine a filter load mode corresponding to the air purifier based on the concentration of pollutant particles; an attenuation detection module, configured to analyze a filter usage status corresponding to a high-efficiency filter in the air purifier based on the filter load mode, query a historical replacement record corresponding to the filter usage status, and perform attenuation detection on the high-efficiency filter based on the historical replacement record to obtain filter attenuation data; a level classification module, configured to calculate the remaining service life of the high-efficiency filter based on the filter attenuation data, evaluate a purification index corresponding to the remaining service life, generate a filter efficiency index corresponding to the high-efficiency filter based on the purification index combined with current ambient air quality, and classify the filter replacement level corresponding to the filter efficiency index; a location positioning module, configured to configure multi-stage prompt information corresponding to the air purifier based on the filter replacement level, determine the filter edge area corresponding to the high-efficiency filter based on the multi-stage prompt information, calculate the filter penetration rate corresponding to the filter edge area, and locate the structural weak point corresponding to the high-efficiency filter based on the filter penetration rate; A plan formulation module is used to generate a local failure map corresponding to the weak parts of the structure, and extract the failure interference factors in the local failure map. Based on the failure interference factors, an adaptive replacement logic corresponding to the air purifier is constructed, and based on the adaptive replacement logic, a replacement reminder plan corresponding to the high-efficiency filter is formulated.

Images