Intelligent filter element service life monitoring method and system based on Internet of Things

Abstract

The invention provides an intelligent filter element service life monitoring method and system based on the Internet of Things, and relates to the technical field of filter element monitoring. Determining the performance attenuation of the filter element caused by pollutant accumulation according to all the degradation distribution characteristics; determining the pore permeation deviation in the filter element performance attenuation information by measuring the interference variable and combining the historical operation data of the filter element in the cloud server, and dynamically correcting the permeation net life of the filter element pores through the pore permeation deviation to obtain a life prediction index of the remaining service life of the filter element; and setting a pore alarm threshold value of the residual service life of the filter element according to the performance attenuation and the service life prediction index, and pushing monitoring information to a user terminal. According to the invention, full-process monitoring can be carried out on the performance attenuation and life prediction of the filter element in an intelligent monitoring scene of the Internet of Things, so that the accuracy of prediction of the remaining service life of the filter element is improved.

Description

Technical Field

[0001] This application relates to the field of filter cartridge monitoring technology, and more specifically, to an intelligent filter cartridge life monitoring method and system based on the Internet of Things. Background Technology

[0002] Filter cartridge monitoring refers to the process of real-time sensing, data collection, analysis, and evaluation of the working status of filter cartridges during operation. It typically involves multiple stages, including sensor deployment, parameter monitoring, data processing, and status assessment. In practical applications such as industrial filtration and water treatment, filter cartridge monitoring not only requires timely detection of performance changes but also accurate prediction of remaining lifespan. The Internet of Things (IoT) has been introduced into the field of filter cartridge monitoring, simultaneously linking with user terminals to push alarm information, significantly improving the real-time performance and accuracy of monitoring, and providing assurance for preventative maintenance of filter cartridges.

[0003] However, existing IoT-based smart filter life monitoring technologies lack a mechanism for integrating and processing multi-dimensional filter operating parameters and accurately correcting for environmental interference. Furthermore, life prediction does not incorporate dynamic degradation distribution characteristics and pore permeation deviations, resulting in incomplete performance degradation calculations and static distortion of life prediction indicators. This leads to unreasonable alarm threshold settings, hindering accurate prediction of remaining filter life and the timely delivery of effective monitoring information. Therefore, how to conduct full-process monitoring of filter performance degradation and life prediction in IoT smart monitoring scenarios to improve the accuracy of remaining filter life prediction is a challenge facing the industry. Summary of the Invention

[0004] This application provides an IoT-based intelligent filter life monitoring method and system, which can monitor the performance degradation and life prediction of filter elements throughout the entire process in IoT intelligent monitoring scenarios, thereby improving the accuracy of filter element remaining life prediction.

[0005] In a first aspect, this application provides a smart filter life monitoring method based on the Internet of Things, the filter life monitoring method comprising the following steps: Environmental pollutant monitoring sensors are deployed in the filter system to collect filter operating parameters in real time during the filter operation process; The filter element's operating parameters are fused to obtain a performance degradation index for the filter element's ability to filter pollutants. The degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted from the performance degradation index. Then, the amount of performance degradation caused by pollutant accumulation is determined by all degradation distribution characteristics. The measurement interference of the monitoring sensors in the working environment of the filter element is determined. The measurement interference is combined with the historical operating data of the filter element in the cloud server to determine the pore permeation deviation in the filter element performance degradation information. Then, the pore permeation deviation is used to dynamically correct the net permeation life of the filter element pores to obtain the life prediction index of the remaining service life of the filter element. Based on the performance degradation and the life prediction index, a pore alarm threshold for the remaining lifespan of the filter element is set. The lifespan of the filter element is monitored according to the pore alarm threshold, and monitoring information is pushed to the user terminal.

[0006] In this embodiment, the monitoring sensors include a pressure sensor, a flow sensor, and a particulate matter monitoring sensor.

[0007] In this embodiment, the filter element's operating parameters are fused to obtain the filter element's performance degradation index for pollutant filtration, specifically including: The performance fusion value of the filter element's pollutant filtration performance is determined based on the filter element's operating parameters. The performance deviation of the filter element's pollutant filtration performance is determined by the performance fusion value and the environmental impact curve of the filter element's working environment. The performance degradation index of the filter element's ability to filter pollutants is determined based on the performance offset.

[0008] In this embodiment, determining the performance degradation of the filter element due to contaminant accumulation based on all degradation distribution characteristics specifically includes: Determine the performance degradation curve of the filter element due to contaminant accumulation based on all degradation distribution characteristics; Extract the performance degradation characteristics of the filter element caused by contaminant accumulation from the filter element performance degradation curve; The amount of performance degradation caused by contaminant accumulation is determined based on the filter element performance degradation characteristics.

[0009] In this embodiment, determining the measurement interference of the monitoring sensor in the filter element's working environment specifically includes: Extract the correlation features between environmental parameters and sensor readings from historical monitoring data of the filter element's working environment; The deviation between the sensor's reference reading and the current actual reading under standard conditions is determined based on the aforementioned correlation characteristics. The measurement interference of the monitoring sensor in the filter element's working environment is determined based on the deviation between the reference reading under the standard environment and the current actual reading.

[0010] In this embodiment, the historical operating data of the filter element refers to the collection of relevant data on the filter element's past operation throughout its entire lifecycle, stored in the cloud.

[0011] In this embodiment, the net permeation life of the filter element pores is dynamically corrected by the pore permeation deviation to obtain the life prediction index of the remaining service life of the filter element, specifically including: The net permeation life of the filter element pores is determined based on the historical operating data of the filter element. The net permeation life of the filter element pores is compensated by the pore permeation deviation to obtain the attenuation linear deviation corresponding to the remaining service life of the filter element. The remaining service life of the filter element is predicted by the attenuation linear deviation.

[0012] In this embodiment, setting the pore alarm threshold for the remaining service life of the filter element based on the performance degradation and the life prediction index specifically includes: The basic alarm level for filter element pores is determined based on the aforementioned performance degradation. The state offset factor of the filter element pores is determined based on the life prediction index. The pore alarm threshold for the remaining service life of the filter element is set by the basic alarm level and the state offset factor.

[0013] In this embodiment, the net permeability lifetime refers to the theoretical remaining service life without considering real-time pore permeability deviation.

[0014] Secondly, this application provides an IoT-based intelligent filter life monitoring system for executing an IoT-based intelligent filter life monitoring method, the filter life monitoring system comprising: The parameter acquisition module is used to deploy environmental pollutant monitoring sensors in the filter system to collect filter operating parameters in real time during the filter operation process; The fusion processing module is used to fuse the working parameters of the filter element to obtain the performance degradation index of the filter element's ability to filter pollutants. From the performance degradation index, the degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted respectively. Then, the amount of performance degradation of the filter element caused by pollutant accumulation is determined by all degradation distribution characteristics. The dynamic correction module is used to determine the measurement interference of the monitoring sensors in the working environment of the filter element. By combining the measurement interference with the historical operating data of the filter element in the cloud server, the pore permeation deviation in the filter element performance degradation information is determined. Then, the pore permeation deviation is used to dynamically correct the net permeation life of the filter element pores to obtain the life prediction index of the remaining service life of the filter element. The life monitoring module is used to set a pore alarm threshold for the remaining service life of the filter element based on the performance degradation amount and the life prediction index, monitor the life of the filter element according to the pore alarm threshold, and push monitoring information to the user terminal.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: Environmental pollutant monitoring sensors are deployed in the filter cartridge system to collect filter cartridge operating parameters in real time during operation. These parameters are then fused to obtain a performance degradation index for the filter cartridge's pollutant filtration performance. Degradation distribution characteristics of the filter cartridge in the initial cleaning stage and the current operating stage are extracted from this index. The performance degradation caused by pollutant accumulation is then determined based on all degradation distribution characteristics. Measurement interference from the monitoring sensors in the filter cartridge's operating environment is determined. This interference, combined with historical operating data of the filter cartridge in a cloud server, determines the pore permeation deviation in the filter cartridge's performance degradation information. The pore permeation deviation is then used to dynamically correct the net permeation life of the filter cartridge pores, resulting in a lifespan prediction index for the remaining service life of the filter cartridge. A pore alarm threshold for the remaining service life of the filter cartridge is set based on the performance degradation and the lifespan prediction index. The filter cartridge lifespan is monitored according to this pore alarm threshold, and monitoring information is pushed to the user terminal.

[0016] Therefore, this application can overcome the lag of traditional offline monitoring and achieve dynamic perception of the filter element's operating status; by acquiring multi-dimensional, all-time basic data, it effectively solves the problem of data collection being partial and lagging, leading to analytical distortion; by fusing and processing the filter element's operating parameters and extracting the degradation distribution characteristics at different stages to determine the performance degradation amount, it avoids the limitations of single-parameter analysis, accurately captures subtle degradation trends in filter element performance, and achieves the quantification and early identification of performance degradation; by determining the measurement interference amount and combining it with historical data to calculate the pore permeation deviation, it dynamically corrects the net permeation life to obtain the life prediction index, eliminating prediction deviations caused by environmental interference and individual differences, and improving the accuracy and personalized adaptability of remaining life prediction; based on the performance degradation amount and life prediction index, it sets pore alarm thresholds and pushes monitoring information, achieving scientific quantification and dynamic adaptation of alarm thresholds, and solving the problems of false alarms, missed alarms, or resource waste caused by unreasonable alarm thresholds.

[0017] In summary, the technical solution adopted in this application can monitor the performance degradation and lifespan prediction of filter elements throughout the entire process in IoT intelligent monitoring scenarios, thereby improving the accuracy of predicting the remaining lifespan of filter elements. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of an IoT-based smart filter life monitoring method provided in this application; Figure 2 This is a flowchart illustrating the process for determining degradation distribution characteristics provided in this application; Figure 3 This is a flowchart illustrating the determination of pore permeability deviation provided in this application; Figure 4 This is a module structure diagram of an IoT-based intelligent filter life monitoring system provided in this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides an IoT-based intelligent filter life monitoring method and system. The core of the method involves deploying environmental pollutant monitoring sensors within the filter system to collect filter operating parameters in real time. These parameters are then fused to obtain a performance degradation index for the filter's pollutant filtration performance. Degradation distribution characteristics of the filter in the initial cleaning stage and the current operating stage are extracted from these performance degradation indicators. The amount of performance degradation due to pollutant accumulation is then determined using all degradation distribution characteristics. The measurement interference of the monitoring sensors in the filter's operating environment is determined. This measurement interference, combined with historical filter operating data from a cloud server, determines the pore permeation deviation in the filter performance degradation information. The pore permeation deviation is then used to dynamically correct the net permeation life of the filter pores, resulting in a life prediction index for the remaining service life of the filter. A pore alarm threshold for the remaining service life of the filter is set based on the performance degradation and the life prediction index. The filter life is monitored according to the pore alarm threshold, and monitoring information is pushed to the user terminal.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of an IoT-based smart filter life monitoring method according to this embodiment of the present application. The filter life monitoring method includes the following steps: In step S1, environmental pollutant monitoring sensors are deployed in the filter system to collect filter operating parameters in real time during the filter operation process.

[0023] In practical implementation, when deploying environmental pollutant monitoring sensors in the filter cartridge system, the core monitoring parameters must first be determined based on the type of filter cartridge: inlet and outlet pressure difference, filtration flow rate, and filtration efficiency. When selecting sensors, industrial-grade sensors should be prioritized to ensure stable operation within the pressure and temperature range of the filter cartridge's operation, and a protection rating of IP65 or higher to adapt to humid / dusty environments. Precise placement is crucial: differential pressure sensors should be symmetrically installed at the inlet and outlet flanges of the filter cartridge to avoid pressure fluctuations caused by pipe bends; flow sensors should be connected in series in the upstream main pipeline of the filter cartridge to ensure a full measurement cross-section; environmental sensors should be placed close to the filter cartridge housing to capture local temperature and humidity in real time. During installation, anti-vibration brackets should be used for fixation, and the interfaces should be sealed. A shielded cable should be connected to a local data acquisition terminal (such as a PLC or edge computing gateway). The terminal reads the sensor data in real time at a frequency of 1–5 Hz, using the read data as the filter cartridge's operating parameters during operation; further details are omitted here.

[0024] It should be noted that, in this application, the filter element operating parameters refer to the key indicators of the filter element's operating status, including inlet and outlet pressure difference, filtration flow rate, filtration efficiency, and medium temperature and humidity; the monitoring sensors include pressure sensors, flow sensors, and particulate matter monitoring sensors.

[0025] In step S2, the working parameters of the filter element are fused to obtain the performance degradation index of the filter element's ability to filter pollutants. The degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted from the performance degradation index. Then, the performance degradation of the filter element due to pollutant accumulation is determined by all the degradation distribution characteristics.

[0026] In this embodiment, the performance degradation index of the filter element's pollutant filtration performance can be obtained by fusing the filter element's operating parameters using the following steps: The performance fusion value of the filter element's pollutant filtration performance is determined based on the filter element's operating parameters. The performance deviation of the filter element's pollutant filtration performance is determined by the performance fusion value and the environmental impact curve of the filter element's working environment. The performance degradation index of the filter element's ability to filter pollutants is determined based on the performance offset.

[0027] In practice, the process begins by collecting historical operating parameters of the same model of filter cartridges from cloud storage and real-time data collection. This includes parameters directly related to filtration performance, such as inlet / outlet pressure difference, filtration flow rate, filtration efficiency, and contaminant retention. Each parameter is then converted to a unified evaluation scale. By statistically analyzing the frequency of each parameter's impact in filter cartridge failure cases under the same operating conditions, and combining this with industry technical personnel's assessments of parameter importance, the importance percentage of each parameter is determined. Next, the actual values ​​of each parameter are multiplied by their corresponding importance percentages and summed. By comparing the calculation results of multiple groups of filter cartridges under the same operating conditions and eliminating outliers, the final performance fusion value is obtained. Then, environmental parameters such as temperature, humidity, and media pH are selected from historical cloud data, along with corresponding performance fusion value data under different operating conditions. These environmental parameters are grouped according to their variation gradients. The difference between each group's performance fusion value and the corresponding performance value under ideal environmental conditions (standard environmental conditions under common operating conditions) is calculated. A trend curve is plotted based on the distribution trend of each group's data points, and the curve shape is adjusted to ensure that most data points conform to the curve. Substituting the current performance fusion value into the curve, the performance difference under the current environment is calculated. After repeatedly verifying the stability of the difference through multiple sets of environmental data from the same period, it is determined as the performance offset. Finally, the period during which the performance fusion value fluctuation is within a reasonable range after the filter element is put into use is extracted. The average performance fusion value of this period is used as the initial benchmark value, and the rationality of the benchmark value is verified by comparing the initial operating data of multiple sets of brand-new filter elements of the same model. Subtracting the performance offset from the current performance fusion value yields the actual filtration performance value after eliminating environmental interference. The ratio of the actual filtration performance value to the benchmark value is calculated. If the ratio is less than 1, the performance degradation index is obtained by subtracting the ratio from 1.

[0028] It should be noted that in this application, the performance fusion value refers to the quantitative value of the basic operating state of the filter element; the environmental impact curve refers to the curve that quantifies the deviation of the filter element performance caused by environmental parameters such as temperature and humidity; the performance offset refers to the quantitative value that quantifies the deviation of the actual performance of the filter element from the ideal state caused by environmental factors; and the performance degradation index refers to the core quantitative index of the degree of performance degradation of the filter element itself.

[0029] Preferably, in this embodiment, the degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted from the performance degradation indicators, respectively, with reference to... Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining degradation distribution characteristics in some embodiments of this application. In this embodiment, the determination of degradation distribution characteristics can be achieved using the following steps: In step S21, the initial stable stage window and the current operating stage window of the filter element performance are defined based on the complete life cycle data of the filter element; In step S22, the first degradation distribution data of the initial clean phase is extracted from the initial stabilization phase window; In step S23, the second degradation distribution data of the initial clean phase is extracted from the current operating phase window; In step S24, the first degradation distribution data and the second degradation distribution data are compared and screened with the performance degradation index to obtain the degradation distribution characteristics of the filter element in the initial cleaning stage and the current operation stage.

[0030] In practice, the process begins by retrieving complete lifecycle data of the same model of filter element from cloud storage, with samples covering operational records under different working conditions. Using the fluctuation range of performance degradation indicators as a stability criterion, the fluctuation of indicators during the initial operation period of multiple groups of brand-new filter elements is statistically analyzed to determine a reasonable fluctuation range, and its effectiveness is verified through industrial experiments. The time period within this range after the filter element is put into use is selected and defined as the initial stabilization phase window. Using the current time as the endpoint, the most recent period reflecting the current performance status is extracted as the current operational phase window, and its rationality is verified by comparing the analysis results of different time period lengths. Next, performance degradation indicator data within the time range corresponding to the initial stabilization phase window is exported from the local data acquisition terminal or cloud storage. The data source is real-time records collected at a fixed frequency within this period. The exported data is deduplicated, removing duplicate records with the same values, and then sorted and organized according to the chronological order of data acquisition. Completeness is verified by statistically analyzing the missing rate. If the missing rate exceeds a reasonable range, backup data under the same working conditions is retrieved to supplement the data, ultimately forming the first degradation distribution data for the initial cleaning phase. Then, through the local data acquisition gateway, real-time data on performance degradation indicators within the time range corresponding to the current operating stage is extracted. The data source is recent continuous monitoring records. The fluctuation range of indicators during normal operation of the filter element under the same conditions is compared to identify and eliminate abnormal data exceeding this range, avoiding data distortion caused by sudden interference. The processed valid data is organized and archived in chronological order of acquisition. Cross-validation with environmental parameter records from the same period ensures that the data accurately reflects the current operating status, forming a second degradation distribution data set. Finally, statistical analysis is performed on the first and second degradation distribution data sets respectively, calculating key statistical results such as the average level, fluctuation degree, and trend of the two sets of data. Referring to relevant industry standards for filter element performance evaluation, a reasonable range of values ​​for performance degradation indicators is determined, and the statistical results of the two sets of data are compared with this range. Statistical results within the reasonable range that significantly reflect the degradation differences between the two stages are selected. The effectiveness of these characteristics is verified through multiple sets of measured data from filter elements with different degrees of degradation, ultimately determining the degradation distribution characteristics of the initial cleanliness stage and the current operating stage, without further limitations.

[0031] It should be noted that, in this application, complete lifecycle data refers to the working parameters and performance index data of the filter element throughout the entire process from its initial use to its failure and disposal; the initial stable phase window refers to the time interval during which the filter element is first put into use and its performance is in a stable state; the current operating phase window refers to the time interval during which the filter element is currently in actual operation; the first degradation distribution data refers to the original dataset of all performance degradation indicators within the initial stable phase window; the second degradation distribution data refers to the original dataset of all performance degradation indicators within the current operating phase window; and the degradation distribution characteristics refer to the core quantitative characteristics of the performance degradation pattern of the filter element at different stages.

[0032] In this embodiment, determining the amount of performance degradation of the filter element due to contaminant accumulation by using all degradation distribution characteristics can be achieved through the following steps: Determine the performance degradation curve of the filter element due to contaminant accumulation based on all degradation distribution characteristics; Extract the performance degradation characteristics of the filter element caused by contaminant accumulation from the filter element performance degradation curve; The amount of performance degradation caused by contaminant accumulation is determined based on the filter element performance degradation characteristics.

[0033] In practice, the process begins by collecting all degradation distribution characteristics from the initial clean-up phase and the current operating phase, including quantitative data such as average levels, fluctuations, and trends, and labeling the collection time points for each characteristic. Sample data is derived from historical operating records of the same type of filter cartridge under different pollutant concentrations, ensuring data coverage of scenarios with varying degrees of buildup. Using time as the independent variable and the quantitative values ​​of degradation distribution characteristics as the dependent variable, each point is mapped onto a coordinate system, connecting the data points to form a preliminary curve. By comparing the fit between multiple sets of curves and the actual pollutant buildup, the curve shape is adjusted to ensure most data points align with the trend, ultimately yielding the performance degradation curve. Next, the generated performance degradation curve is segmented, dividing the curve into multiple continuous segments according to time intervals, and calculating the slope of each segment to reflect the degradation rate during that period. Points where the curve slope abruptly changes are identified to determine the time points where accelerated pollutant buildup leads to increased degradation. The difference in the vertical axis between the starting point of the curve in the initial clean-up phase and the ending point of the curve in the current operating phase is calculated to obtain the basic degradation magnitude caused by pollutant buildup. Industrial experiments are used to verify the correlation between these parameters and the actual amount of pollutant buildup, and parameters with strong correlations are selected and integrated into performance degradation characteristics. Finally, the average level of degradation distribution characteristics in the initial clean phase was used as the baseline value. This baseline value was verified for its rationality by comparing it with initial data from multiple sets of brand-new filter cartridges of the same model. Combining the basic degradation amplitude extracted from the performance degradation characteristics with the correction ratio corresponding to different contaminant accumulation rates (determined through historical data statistical analysis), the correlation values ​​between the baseline value and the basic degradation amplitude and correction ratio were calculated. The calculated results were compared and verified with the degradation amount corresponding to the known amount of contaminant accumulation under experimental conditions. Parameters were adjusted to make the results more consistent with reality, ultimately yielding a quantified performance degradation amount.

[0034] It should be noted that, in this application, the filter element performance degradation curve refers to a curve that shows the trend of filter element performance degradation with the duration of use, with time as the horizontal axis and the quantitative value of degradation distribution characteristics as the vertical axis; the filter element performance degradation characteristics refer to key parameters that quantify the filter element degradation rate and degradation magnitude; and the performance degradation amount refers to the specific value that quantifies the degree of performance decline of the filter element from the initial clean stage to the current operating stage.

[0035] In step S3, the measurement interference of the monitoring sensor in the working environment of the filter element is determined. The measurement interference is combined with the historical operating data of the filter element in the cloud server to determine the pore permeation deviation in the filter element performance degradation information. Then, the pore permeation deviation is used to dynamically correct the net permeation life of the filter element pores to obtain the life prediction index of the remaining service life of the filter element.

[0036] In this embodiment, determining the measurement interference of the monitoring sensor in the filter element's working environment can be achieved through the following steps: Extract the correlation features between environmental parameters and sensor readings from historical monitoring data of the filter element's working environment; The deviation between the sensor's reference reading and the current actual reading under standard conditions is determined based on the aforementioned correlation characteristics. The measurement interference of the monitoring sensor in the filter element's working environment is determined based on the deviation between the reference reading under the standard environment and the current actual reading.

[0037] In practice, the process begins with retrieving historical monitoring data from the cloud for the same model of sensor. The sample includes environmental parameters (temperature, humidity, electromagnetic intensity, etc.) under different operating conditions and corresponding sensor readings at different time points. The data is grouped according to the range of environmental parameter changes, and the average change in sensor readings within each group is statistically analyzed to observe the response trend of readings when environmental parameters increase or decrease. By comparing the consistency of readings under multiple groups of the same environmental parameters, environmental parameters that significantly affect the readings are identified, and their correlation with reading changes is summarized. After verifying the stability of this correlation through multiple sets of experimental data, it is determined as a correlation feature. Next, standard environmental parameters (industry-standard stable operating conditions) are defined. Based on the correlation feature, the theoretical readings that the sensor should have under this standard environment are deduced. This is verified by comparing and verifying multiple sets of measured data from the same model of sensor under the standard environment to determine the baseline reading. Real-time acquisition of actual readings under the current operating environment is performed, and the actual readings are subtracted from the baseline readings to obtain a preliminary difference. The stability of the difference is verified by repeatedly acquiring the current environmental readings and calculating the difference. After eliminating abnormal fluctuations, the final deviation is determined. Finally, multiple sets of deviation data are acquired through continuous acquisition, and the concentrated distribution range of these data is statistically analyzed. Referring to the measurement accuracy standards of the sensors, abnormal deviation values ​​exceeding the reasonable error range are eliminated, and the average value of the remaining effective deviation values ​​is calculated. If multiple environmental parameters interfere, the corresponding deviation values ​​are weighted and integrated according to the influence weight of each parameter in the correlation features. By comparing and verifying with known interference quantities in the experimental environment, the weights are adjusted to ensure that the results are consistent with reality, and finally determined as the measurement interference quantity.

[0038] It should be noted that, in this application, the correlation feature between environmental parameters and sensor readings refers to the core feature that reflects the correspondence between changes in filter element working environment parameters and fluctuations in sensor readings; the deviation between the reference reading and the current actual reading refers to the numerical value that quantifies the difference between the sensor reading in the current actual environment and the reference reading in the standard environment; and the measurement interference refers to the numerical value that quantifies the degree of interference caused by the filter element working environment to the measurement results of the monitoring sensor.

[0039] Preferably, in this embodiment, the pore permeation deviation in the filter element performance degradation information is determined by combining the measured interference amount with the historical operating data of the filter element in the cloud server, with reference to... Figure 3As shown in the figure, this is a schematic flowchart of determining pore permeability deviation in some embodiments of this application. In this embodiment, determining pore permeability deviation can be achieved by the following steps: In step S31, the historical operating data of the filter element is obtained from the cloud server; In step S32, the measured interference amount is corrected and filtered with the historical operating data of the filter element to obtain the filter element performance degradation information; In step S33, the pore permeability index of the filter element pores is determined based on the filter element performance degradation information; In step S34, the pore permeability deviation in the filter element performance degradation information is determined by the pore permeability index.

[0040] In practice, the process begins by connecting to a cloud server via a standardized data interface to initiate a data acquisition request. The filtering criteria are clearly defined as operational records of the same model and operating conditions as the current filter element. A complete dataset covering filter element operating parameters, performance indicators, environmental parameters, and sensor readings is downloaded, sourced from long-term monitoring archives under different usage scenarios. The downloaded data is deduplicated, removing duplicate entries. Completeness is verified by statistically analyzing the missing rate; if the missing rate exceeds the limit, backup data is retrieved. After cross-checking to ensure data consistency, the data is stored on a local analysis terminal. Next, performance data corresponding to the current measured interference level in the environmental scenario is extracted from the compiled historical operating data of the filter element, establishing a correspondence between interference level and performance data. The original performance data of the current filter element is substituted into this correspondence, and the original data is adjusted using the measured interference level, removing data whose interference exceeds a reasonable range. Valid data is retained and integrated chronologically. This is verified by comparing the data with filter element data from those with known degradation states under the same operating conditions, ensuring that the integrated data accurately reflects the filter element's own degradation, ultimately forming filter element performance degradation information. Then, key parameters related to pore permeability are extracted from the filter element performance degradation information, including pore flow rate, media permeation volume, and pore blockage-related data. The frequency of each parameter's impact on permeability in filter element failure cases is statistically analyzed, and the importance percentage of each parameter is determined by combining the assessment opinions of industry technicians. The actual values ​​of each parameter are multiplied by their corresponding percentages and summed to obtain preliminary quantitative results. These results are verified by comparing with pore permeability measured under experimental conditions, and the parameter percentages are adjusted to better reflect reality, ultimately determining the pore permeability index. Finally, multiple sets of pore permeability indices for the same model of brand-new filter elements in their initial state are extracted from historical filter element operating data. Their average values ​​are calculated and verified through industrial testing to determine the ideal benchmark value. The current pore permeability index is compared with this ideal benchmark value, and the difference is calculated. If the difference is positive, a secondary verification is needed to check for measurement errors; if negative, its absolute value is taken as the preliminary deviation value. This is verified by comparing with the measured deviations of filter elements with different degradation levels to ensure that the results accurately reflect the degree of deviation in pore permeability, ultimately determining the pore permeability deviation.

[0041] It should be noted that, in this application, the filter element historical operation data refers to the collection of filter element operation data throughout its entire life cycle stored in the cloud; the filter element performance degradation information refers to the data reflecting the decline in filter element performance over time after being corrected and filtered by measurement interference; the pore permeability index refers to the parameter that quantifies the filter element pores' ability to permeate media; and the pore permeability deviation refers to the numerical value that quantifies the difference between the current pore permeability index of the filter element and the permeability index under ideal conditions.

[0042] In this embodiment, the life prediction index of the remaining service life of the filter element is obtained by dynamically correcting the net permeation life of the filter element pores through the pore permeation deviation using the following steps: The net permeation life of the filter element pores is determined based on the historical operating data of the filter element. The net permeation life of the filter element pores is compensated by the pore permeation deviation to obtain the attenuation linear deviation corresponding to the remaining service life of the filter element. The remaining service life of the filter element is predicted by the attenuation linear deviation.

[0043] In practice, the process begins by retrieving historical operating data from the cloud for the same model and operating conditions as the current filter cartridge. This data covers the complete cycle of the filter cartridge's lifespan, from brand new to its penetration capacity declining to industry-standard levels. Using time as the horizontal axis and pore penetration-related performance data as the vertical axis, performance values ​​at each time point are marked and connected to form a performance degradation trend line. Based on the trend line's changing patterns, the time span between the current filter cartridge's pore penetration performance value and its standard failure value is calculated. This calculation is cross-validated using periodic data from multiple filter cartridges operating under the same conditions to ensure its reasonableness, ultimately determining the net penetration lifespan. Next, the differences between the actual and theoretical net penetration lifespan of the filter cartridges corresponding to different pore penetration deviations in the historical cloud data are statistically analyzed. The correlation between the deviation magnitude and the lifespan compensation amount is summarized, and the validity of this correlation is verified through simulations in an experimental environment. The current pore penetration deviation is then substituted into this correlation to calculate the corresponding lifespan compensation amount. Combining this with the slope of the net penetration lifespan degradation trend, the lifespan compensation amount is converted into a linear deviation value. The stability of this deviation value is verified using multiple sets of real-time data, ultimately determining it as the linear degradation deviation. Finally, based on the net permeation life as the baseline value, preliminary adjustments are made according to the positive or negative attribute of the linear deviation of the attenuation: if the deviation is positive, it indicates that the actual life is shorter than the theoretical value, and the deviation is subtracted from the baseline value; if the deviation is negative, it indicates that the actual life is longer than the theoretical value, and the deviation is added to the baseline value. Then, by collecting real-time operating load data of the filter element, the ratio of the actual load to the rated load is calculated as the load coefficient. The preliminary adjustment result is multiplied by the load coefficient for fine-tuning. The results are verified by comparing with the measured remaining life of the filter element under the same operating conditions to ensure that the results are consistent with reality, and are ultimately determined as the life prediction index.

[0044] It should be noted that in this application, net permeation life refers to the theoretical remaining service life without considering real-time pore permeation deviation; the remaining service life of the filter element refers to the effective operating time of the filter element from its current state until it can no longer meet the filtration requirements; attenuation linear deviation refers to the deviation value of the linear deviation between the theoretical life and the actual life; and the life prediction index refers to the index that quantifies the actual remaining service life of the filter element.

[0045] In step S4, a pore alarm threshold for the remaining service life of the filter element is set based on the performance degradation amount and the life prediction index. The filter element life is monitored according to the pore alarm threshold, and monitoring information is pushed to the user terminal.

[0046] In this embodiment, setting the pore alarm threshold for the remaining service life of the filter element based on the performance degradation amount and the life prediction index can be achieved through the following steps: The basic alarm level for filter element pores is determined based on the aforementioned performance degradation. The state offset factor of the filter element pores is determined based on the life prediction index. The pore alarm threshold for the remaining service life of the filter element is set by the basic alarm level and the state offset factor.

[0047] In practice, the process begins by retrieving fault case data and corresponding performance degradation records of the same model of filter element under different application scenarios, and statistically analyzing the probability of filter element failure within different degradation ranges. Combining industry-standard safety practices for filter element maintenance and operational cost control requirements, three continuous intervals are defined to distinguish between mild, moderate, and severe degradation. Multiple experiments simulate the operating states of filter elements under different degradation levels to verify the rationality of the interval division, ensuring that each interval accurately corresponds to the actual safe operating risk of the filter element. Finally, the basic alarm level is determined based on the current interval of the filter element's performance degradation. Next, the rated service life data of the same model of filter element stored in the cloud is extracted, and the differences in actual operating risk corresponding to the ratio of different historical lifespan prediction indicators to the rated service life are statistically analyzed. The correlation between the ratio and the alarm threshold adjustment range is summarized; for example, when the ratio is too small (actual lifespan is too short), the threshold adjustment range needs to be increased to issue an earlier alarm, while when the ratio is too large, the adjustment range should be appropriately decreased. The adaptability of this pattern is verified through multiple sets of concurrently operating filter element data to ensure that the adjustment range accurately matches the actual lifespan state, ultimately obtaining the current filter element's state offset factor. Finally, an initial threshold is set for each basic alarm level. The initial threshold is determined based on the critical value of the performance degradation range corresponding to that level and verified by industry maintenance standards. The initial threshold is calculated with (1 + state offset factor) to obtain the corrected threshold. If the state offset factor is positive, the threshold trigger point is increased to issue an early alarm, allowing time for maintenance; if it is negative, the threshold is appropriately reduced to avoid excessive alarms. The corrected threshold is compared and verified with measured failure data of filter elements under multiple sets of different operating conditions. The parameters are adjusted to ensure that the threshold can accurately trigger alarms without false alarms or missed alarms. The final threshold is determined as the pore alarm threshold, which will not be elaborated here.

[0048] It should be noted that in this application, the basic alarm level refers to the initial alarm level of the severity of pore performance degradation; the state deviation factor refers to the degree of deviation between the actual remaining life of the filter element and the expected life; and the pore alarm threshold refers to the critical value that triggers the filter element life monitoring alarm.

[0049] In addition, in specific implementation, monitoring the filter cartridge lifespan based on the aforementioned pore alarm threshold and pushing monitoring information to the user terminal can be achieved in the following way: First, in the real-time monitoring phase, the system collects the current performance degradation and lifespan prediction indicators of the filter cartridge every 5 minutes and compares them with the set pore alarm threshold in real time. If the current performance degradation reaches the first-level alarm threshold (e.g., 30%), it is determined as a mild warning; if it reaches the second-level threshold (e.g., 60%), it is determined as a moderate warning; and if it reaches the third-level threshold (e.g., 80%), it is determined as an emergency warning. Then, corresponding monitoring information is generated according to the warning level: a mild warning includes the current degradation rate, the estimated remaining lifespan, and daily maintenance suggestions; a moderate warning adds a reminder to prepare a spare filter cartridge; and an emergency warning clearly indicates that immediate replacement is required. Finally, after the information is generated, it is pushed to the user terminal (mobile APP, industrial control platform) through a preset communication protocol (e.g., MQTT), while recording the push time and content. After receiving the information, the terminal reports a read status, and the system stores the complete interaction record, forming a closed-loop management from monitoring to push.

[0050] Therefore, this application can overcome the lag of traditional offline monitoring and achieve dynamic perception of the filter element's operating status; by acquiring multi-dimensional, all-time basic data, it effectively solves the problem of data collection being partial and lagging, leading to analytical distortion; by fusing and processing the filter element's operating parameters and extracting the degradation distribution characteristics at different stages to determine the performance degradation amount, it avoids the limitations of single-parameter analysis, accurately captures subtle degradation trends in filter element performance, and achieves the quantification and early identification of performance degradation; by determining the measurement interference amount and combining it with historical data to calculate the pore permeation deviation, it dynamically corrects the net permeation life to obtain the life prediction index, eliminating prediction deviations caused by environmental interference and individual differences, and improving the accuracy and personalized adaptability of remaining life prediction; based on the performance degradation amount and life prediction index, it sets pore alarm thresholds and pushes monitoring information, achieving scientific quantification and dynamic adaptation of alarm thresholds, and solving the problems of false alarms, missed alarms, or resource waste caused by unreasonable alarm thresholds.

[0051] In summary, the technical solution adopted in this application can monitor the performance degradation and lifespan prediction of filter elements throughout the entire process in IoT intelligent monitoring scenarios, thereby improving the accuracy of predicting the remaining lifespan of filter elements.

[0052] Example 2: This application provides an IoT-based intelligent filter life monitoring system, referencing... Figure 4 As shown in the figure, this is a modular structure diagram of an IoT-based intelligent filter life monitoring system according to this embodiment of the present application. The filter life monitoring system includes: The parameter acquisition module 100 is used to deploy environmental pollutant monitoring sensors in the filter system to collect filter operating parameters in real time during the filter operation process; The fusion processing module 200 is used to fuse the working parameters of the filter element to obtain the performance degradation index of the filter element's ability to filter pollutants. The degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted from the performance degradation index. Then, the performance degradation caused by the accumulation of pollutants is determined by all the degradation distribution characteristics. The dynamic correction module 300 is used to determine the measurement interference of the monitoring sensor in the working environment of the filter element, and to determine the pore permeation deviation in the filter element performance degradation information by combining the measurement interference with the historical operating data of the filter element in the cloud server. Then, the net permeation life of the filter element pores is dynamically corrected by the pore permeation deviation to obtain the life prediction index of the remaining service life of the filter element. The life monitoring module 400 is used to set a pore alarm threshold for the remaining service life of the filter element based on the performance degradation amount and the life prediction index, monitor the life of the filter element according to the pore alarm threshold, and push monitoring information to the user terminal.

[0053] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0055] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things, characterized in that, The filter cartridge life monitoring method includes the following steps: Environmental pollutant monitoring sensors are deployed in the filter system to collect filter operating parameters in real time during the filter operation process; The filter element's operating parameters are fused to obtain a performance degradation index for the filter element's ability to filter pollutants. The degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted from the performance degradation index. Then, the amount of performance degradation caused by pollutant accumulation is determined by all degradation distribution characteristics. The measurement interference of the monitoring sensors in the working environment of the filter element is determined. The measurement interference is combined with the historical operating data of the filter element in the cloud server to determine the pore permeation deviation in the filter element performance degradation information. Then, the pore permeation deviation is used to dynamically correct the net permeation life of the filter element pores to obtain the life prediction index of the remaining service life of the filter element. Based on the performance degradation and the life prediction index, a pore alarm threshold for the remaining lifespan of the filter element is set. The lifespan of the filter element is monitored according to the pore alarm threshold, and monitoring information is pushed to the user terminal.

2. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The monitoring sensors include pressure sensors, flow sensors, and particulate matter monitoring sensors.

3. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The filter element's operating parameters are fused to obtain performance degradation indicators for its ability to filter pollutants. These indicators specifically include: The performance fusion value of the filter element's pollutant filtration performance is determined based on the filter element's operating parameters. The performance deviation of the filter element's pollutant filtration performance is determined by the performance fusion value and the environmental impact curve of the filter element's working environment. The performance degradation index of the filter element's ability to filter pollutants is determined based on the performance offset.

4. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The specific amount of performance degradation of the filter element due to contaminant accumulation is determined by identifying all degradation distribution characteristics, including: Determine the performance degradation curve of the filter element due to contaminant accumulation based on all degradation distribution characteristics; Extract the performance degradation characteristics of the filter element caused by contaminant accumulation from the filter element performance degradation curve; The amount of performance degradation caused by contaminant accumulation is determined based on the filter element performance degradation characteristics.

5. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, Determining the measurement interference of the monitoring sensors in the filter element's working environment specifically includes: Extract the correlation features between environmental parameters and sensor readings from historical monitoring data of the filter element's working environment; The deviation between the sensor's reference reading and the current actual reading under standard conditions is determined based on the aforementioned correlation characteristics. The measurement interference of the monitoring sensor in the filter element's working environment is determined based on the deviation between the reference reading under the standard environment and the current actual reading.

6. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The aforementioned filter cartridge historical operation data refers to the collection of relevant data on the filter cartridge's past operation throughout its entire lifecycle, stored in the cloud.

7. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The net permeation life of the filter element is dynamically corrected by the pore permeation deviation, and the life prediction index of the remaining service life of the filter element is obtained, specifically including: The net permeation life of the filter element pores is determined based on the historical operating data of the filter element. The net permeation life of the filter element pores is compensated by the pore permeation deviation to obtain the attenuation linear deviation corresponding to the remaining service life of the filter element. The remaining service life of the filter element is predicted by the attenuation linear deviation.

8. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, Setting the pore alarm threshold for the remaining service life of the filter element based on the performance degradation and the life prediction index specifically includes: The basic alarm level for filter element pores is determined based on the aforementioned performance degradation. The state offset factor of the filter element pores is determined based on the life prediction index. The pore alarm threshold for the remaining service life of the filter element is set by the basic alarm level and the state offset factor.

9. The method for monitoring the lifespan of an intelligent filter cartridge based on the Internet of Things as described in claim 1, characterized in that, The net permeability lifetime refers to the theoretical remaining service life without taking into account real-time pore permeability deviation.

10. An IoT-based intelligent filter life monitoring system, used to execute the IoT-based intelligent filter life monitoring method as described in any one of claims 1 to 9, characterized in that, The filter cartridge life monitoring system includes: The parameter acquisition module is used to deploy environmental pollutant monitoring sensors in the filter system to collect filter operating parameters in real time during the filter operation process; The fusion processing module is used to fuse the working parameters of the filter element to obtain the performance degradation index of the filter element's ability to filter pollutants. From the performance degradation index, the degradation distribution characteristics of the filter element in the initial cleaning stage and the current operating stage are extracted respectively. Then, the amount of performance degradation of the filter element caused by pollutant accumulation is determined by all degradation distribution characteristics. The dynamic correction module is used to determine the measurement interference of the monitoring sensors in the working environment of the filter element. By combining the measurement interference with the historical operating data of the filter element in the cloud server, the pore permeation deviation in the filter element performance degradation information is determined. Then, the pore permeation deviation is used to dynamically correct the net permeation life of the filter element pores to obtain the life prediction index of the remaining service life of the filter element. The life monitoring module is used to set a pore alarm threshold for the remaining service life of the filter element based on the performance degradation amount and the life prediction index, monitor the life of the filter element according to the pore alarm threshold, and push monitoring information to the user terminal.

Images