Intelligent filter bag design method and system based on artificial intelligence

Abstract

The invention relates to the technical field of filter bag design, and discloses a filter bag intelligent design method and system based on artificial intelligence. The method comprises the following steps: dynamically capturing pollutant particles to obtain a pollutant characteristic digital fingerprint database; a multi-dimensional material performance matrix is obtained through material microcosmic permeability measurement; performing wrinkle parameter modeling based on the matrix to obtain a self-balancing wrinkle structure parameter group; according to the optimized material layer configuration, forming a multi-layer composite filtering structure configuration table; performing a simulation test to obtain a full-condition performance curve set; and finally, accurately converting into a producible filter bag design scheme. Based on complex indoor air pollutant characteristics and variable environmental conditions, accurate optimization of filtering materials and structural parameters is achieved, the service life of the filtering bag is accurately predicted, meanwhile, it is ensured that the design scheme can be efficiently converted into actual production, and therefore the filtering efficiency, the service life and the adaptability of the filtering bag are improved.

Description

Technical Field

[0001] This application relates to the technical field of filter bag design, and particularly to an intelligent design method and system for filter bags based on artificial intelligence. Background Art

[0002] Most of the existing filter bag design methods rely on traditional empirical design and repeated experiments, lacking systematicness and precision. Designers usually make simple improvements or parameter adjustments based on existing products and rely on physical production and laboratory tests to verify the design effects. This method is not only time-consuming and laborious but also difficult to cope with the complex and changeable air pollution environment. In the traditional design process, the selection of filter materials is mostly based on a single performance index, such as the filtration efficiency for specific particulate matter or the initial pressure drop, and rarely considers the comprehensive performance of the materials under different environmental conditions. At the same time, the determination of the structural design parameters of the filter bag, such as the pleat angle, depth, and density, often relies on the personal experience of designers and lacks scientific optimization methods. In addition, there are also significant limitations in the prediction of the filter bag life in the existing technology, and it is impossible to accurately evaluate the impact of different environmental factors on the attenuation of filtration performance, resulting in a large difference between the actual service life and the design expectation.

[0003] However, the traditional design method has obvious deficiencies and cannot effectively cope with the increasingly complex indoor air pollution environment. First, the types of indoor air pollutants are diverse, including PM2.5 particulate matter, formaldehyde, VOCs, etc., and their physical and chemical properties and distribution laws are complex and changeable. It is difficult for traditional empirical design to optimize precisely for this complex pollution environment. Second, there are complex interaction relationships between the filter material and the structural parameters, and traditional methods cannot comprehensively consider the coupling effects of these factors, resulting in unstable or low-efficiency performance of the designed filter bag. Moreover, environmental factors such as temperature and humidity have a significant impact on the performance of filter materials, and the existing technology lacks systematic analysis and prediction capabilities for these effects, making it difficult to guarantee the performance of the filter bag in the actual use environment. Finally, the traditional design-manufacturing process lacks an effective data feedback and optimization mechanism and cannot accurately adjust the design according to the actual production situation, resulting in low conversion efficiency from design to production. Summary of the Invention

[0004] This application provides an intelligent design method and system for filter bags based on artificial intelligence, which is used to achieve precise optimization of filter materials and structural parameters based on the characteristics of complex indoor air pollutants and variable environmental conditions, accurately predict the service life of the filter bag, and ensure that the design scheme can be efficiently transformed into actual production, thereby improving the filtration efficiency, service life, and adaptability of the filter bag.

[0005] In a first aspect, the present application provides an intelligent design method for filter bags based on artificial intelligence. The intelligent design method for filter bags based on artificial intelligence includes: collecting multi-dimensional data on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library; accurately quantifying the porosity, active site distribution, and surface charge of the filter material using a material micro-permeability measuring instrument according to the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material property matrix; performing parametric modeling and airflow distribution calculation on the pleat angle, depth, and density of the filter bag based on the multi-dimensional material property matrix to obtain a self-balanced pleat structure parameter set; optimizing and adjusting the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced pleat structure parameter set to obtain a multi-layer composite filter structure configuration table; simulating and testing the filtration efficiency and service life of the filter bag in a high-humidity and high-concentration pollutant environment using the multi-layer composite filter structure configuration table to obtain a full-condition performance curve set; and accurately converting and verifying the filter bag material formula, structural dimensions, and production process parameters based on the full-condition performance curve set to obtain a filter bag design scheme that can be directly used for production.

[0006] In a second aspect, the present application provides an intelligent design system for filter bags based on artificial intelligence. The intelligent design system for filter bags based on artificial intelligence includes:

[0007] A collection module for collecting multi-dimensional data on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library;

[0008] A quantification module for accurately quantifying the porosity, active site distribution, and surface charge of the filter material using a material micro-permeability measuring instrument according to the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material property matrix;

[0009] A calculation module for performing parametric modeling and airflow distribution calculation on the pleat angle, depth, and density of the filter bag based on the multi-dimensional material property matrix to obtain a self-balanced pleat structure parameter set;

[0010] An adjustment module for optimizing and adjusting the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced pleat structure parameter set to obtain a multi-layer composite filter structure configuration table;

[0011] A test module for simulating and testing the filtration efficiency and service life of the filter bag in a high-humidity and high-concentration pollutant environment using the multi-layer composite filter structure configuration table to obtain a full-condition performance curve set;

[0012] A verification module, configured to accurately convert and verify the filter bag material formula, structural dimensions, and production process parameters according to the full-condition performance curve set, so as to obtain a filter bag design solution that can be directly used for production.

[0013] A third aspect of the present invention provides a computer device, including: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor invokes the instructions in the memory to cause the computer device to execute the above-mentioned artificial intelligence-based intelligent design method for filter bags.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium, in which instructions are stored, and when the instructions are run on a computer, the computer is caused to execute the above-mentioned artificial intelligence-based intelligent design method for filter bags.

[0015] In the technical solution provided by this application, multi-dimensional data collection of indoor air pollutants is carried out through a pollutant particle dynamic capture device, and an accurate digital fingerprint library of pollutant characteristics is established. This fingerprint library contains key information such as the particle size distribution and adsorption characteristics of pollutants, providing an accurate data basis for subsequent designs and solving the problem of insufficient understanding of pollutant characteristics in traditional designs. Secondly, a precise quantification of the filter material is carried out using a material micro-permeability measuring instrument to generate a multi-dimensional material performance matrix. This matrix comprehensively characterizes the characteristics of the material such as porosity, active site distribution, and surface charge, enabling designers to more accurately select filter materials suitable for specific pollutants. Furthermore, parametric modeling and air flow distribution calculations based on the multi-dimensional material performance matrix generate a set of self-balancing fold structure parameters. By optimizing parameters such as the fold angle, depth, and density through artificial intelligence algorithms, the optimal design of the filter bag structure is achieved, significantly improving the filtration efficiency and service life. In addition, the combination order, thickness ratio, and contact interface of different material layers of the filter bag are optimized and adjusted to form a multi-layer composite filter structure configuration table, giving full play to the synergistic effect of each material layer and enhancing the overall performance of the filtration system. It is particularly worth mentioning that this solution applies artificial intelligence algorithms for virtual testing and life prediction. By simulating the performance of the filter bag in an environment with high humidity and high-concentration pollutants, a set of full-condition performance curves is generated, accurately predicting the performance and service life of the product under various environmental conditions and avoiding the limitations of relying on physical testing in traditional methods. Finally, through precise conversion and verification based on the set of full-condition performance curves, a filter bag design solution that can be directly used for production is generated, achieving seamless connection from design to production and improving the design conversion efficiency and product consistency. The application of artificial intelligence algorithms in this invention, especially the deep learning and optimization algorithms in the links of pollutant data fusion processing, material performance prediction, structural parameter optimization, and life prediction, greatly improves the intelligence level and accuracy of the design process, making the filter bag design no longer rely on experience and trial-and-error, but on precise data and scientific calculations, achieving personalized and precise design for complex indoor air pollution environments, thereby significantly improving the filtration efficiency, service life, and environmental adaptability of the filter bag. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of an embodiment of the intelligent design method of a filter bag based on artificial intelligence in the embodiments of this application;

[0018] Figure 2 Schematic diagram of an embodiment of an intelligent design system for filter bags based on artificial intelligence in an embodiment of the present application;

[0019] Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. Detailed implementation manners

[0020] The embodiments of the present application provide an intelligent design method and system for filter bags based on artificial intelligence. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and the above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order different from that shown or described here. In addition, the term "comprising" or "having" and any deformation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 An embodiment of the intelligent design method for filter bags based on artificial intelligence in the embodiments of the present application includes:

[0022] Step S101: Collect multi-dimensional data on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library;

[0023] Step S102: Use a material microscopic permeability measuring instrument to accurately quantify the porosity, active site distribution, and surface charge of the filter material according to the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material property matrix;

[0024] Step S103: Perform parametric modeling and airflow distribution calculation on the pleat angle, depth, and density of the filter bag based on the multi-dimensional material property matrix to obtain a self-balancing pleat structure parameter group;

[0025] Step S104: Optimize and adjust the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balancing pleat structure parameter group to obtain a multi-layer composite filter structure configuration table;

[0026] Step S105: Use the multi-layer composite filter structure configuration table to simulate and test the filtration efficiency and service life of the filter bag in an environment with high humidity and high-concentration pollutants to obtain a full-condition performance curve set;

[0027] Step S106: Based on the full operating condition performance curve set, accurately convert and verify the filter bag material formula, structural dimensions, and production process parameters to obtain a filter bag design solution that can be directly used for production.

[0028] It can be understood that the execution subject of this application can be an intelligent filter bag design system based on artificial intelligence, or a terminal or a server. Specifically, it is not limited here. In this embodiment of the application, the server is used as the execution subject for illustration.

[0029] Specifically, a high-precision light scattering sensor is used to monitor the PM2.5 particle concentration in real time. This sensor is based on the Mie scattering principle. When a laser beam irradiates the particulate matter in the air, scattered light is generated. The sensor detects the intensity of the scattered light and converts it into an electrical signal, and calculates the particulate matter concentration through an algorithm. At the same time, a gas chromatograph analyzer measures the concentration gradient of gaseous pollutants such as formaldehyde and VOC. The gas chromatograph analyzer separates the mixed gas through a chromatographic column, and then the detector identifies and quantifies the concentration of different pollutants. The electrostatic adsorption test plate is used to quantitatively record the surface adhesion of pollutants under different temperature and humidity conditions. A specific voltage is applied to the surface of the test plate, and the adsorption rate and intensity of pollutants are recorded. The data fusion processor performs correlation analysis on these three types of data, generates a spatio-temporal distribution feature map of pollutants through timestamp alignment and spatial interpolation algorithms, and the feature extraction unit applies the principal component analysis algorithm to extract key pollutant characteristic parameters and establish a pollutant behavior pattern library. Finally, through cross-validation and normalization processing, a pollutant characteristic digital fingerprint library is formed. This fingerprint library contains multi-dimensional information such as pollutant particle size, concentration, and adsorption characteristics.

[0030] When accurately quantifying according to the pollutant characteristic digital fingerprint library using a material micro-permeability measuring instrument, the specific surface area of the filter material is measured by the nitrogen adsorption method. The nitrogen adsorption method is based on the BET theory, and measures the amount of nitrogen adsorbed on the material surface under low-temperature conditions, so as to calculate the specific surface area and pore size distribution of the material. The electron microscopy scanning technology magnifies the surface morphology of the filter material at a high magnification to obtain a microscopic structure diagram of the material surface with a resolution up to the nanometer level, showing the fiber arrangement, pore distribution, and surface roughness on the material surface. The thermogravimetric analyzer tests the adsorption capacity of the filter material under different temperature conditions, and calculates the adsorption thermodynamic characteristics of the material by recording the mass change of the material during the temperature change process. The material pore size distribution curve and the surface microscopic structure diagram are fused through image recognition algorithms and three-dimensional reconstruction technologies to establish a three-dimensional pore network topological structure of the material. The fluorescence labeling method binds specific fluorescent dyes to the active sites of the material, and observes and quantifies the spatial distribution of the active sites under a fluorescence microscope. The correlation analysis algorithm combines the spatial distribution map of the active sites and the adsorption thermodynamic characteristic map to construct a capture efficiency prediction model, and finally generates a multi-dimensional material performance matrix.

[0031] When parametrically modeling the filter bag folds based on the multi-dimensional material property matrix, the geometric parameter generator first discretizes the fold structure, decomposing the continuous fold form into a finite number of grid points to form a fold unit grid point set. Physical parameters in the multi-dimensional material property matrix, such as elastic modulus, porosity, surface energy, etc., are mapped onto the grid points to construct a digital fold material model. The flow field boundary conditions include the inlet flow rate, outlet pressure, and no-slip condition on the sidewalls. Through finite element analysis, the pressure drop and air flow flux distributions of each fold unit are calculated. The pressure imbalance region adjusts the fold angle parameter through the gradient descent algorithm to generate an angle optimization data table. The response surface analysis method combines the fold depth variable to establish a mathematical relationship between depth and density, forming a fold geometry coupling relationship diagram. Finally, the parameters are continuously adjusted through the iterative optimization algorithm until the air flow distribution uniformity reaches the preset threshold, generating a self-balanced fold structure parameter set.

[0032] When optimizing and adjusting different material layers of the filter bag according to the self-balanced fold structure parameter set, the material compatibility analyzer first measures the interfacial force between candidate filter materials and obtains the material interface bonding strength data through tensile tests and shear tests. The capture ability complementarity evaluation is based on the data in the pollutant characteristic digital fingerprint library, calculates the capture efficiency of different materials for various pollutants, and forms a material complementarity score table. The exhaustive analysis algorithm systematically evaluates the permutation and combination schemes of different material layers and generates a material sorting scheme library through the calculation of the directional filtration coefficient. The interlayer pressure drop coordination calculation uses the fluid mechanics model to determine the optimal thickness ratio of each layer of material and constructs a thickness ratio relationship matrix. The interfacial stress analysis identifies the stress concentration problem at the contact points between material layers and generates an interface optimization strategy table by adjusting the contact mode. All these analysis results are finally integrated to form a multi-layer composite filter structure configuration table.

[0033] When conducting simulation tests using the multi-layer composite filter structure configuration table, the environmental parameter control box sets the temperature (15 - 40 °C), humidity (30 - 90%), and pollutant concentration (10 - 1000 μg / m 3Different combinations are used to construct a multi-dimensional test condition matrix. The digital twin prototype constructs a virtual model based on the parameters in the multi-layer composite filtration structure configuration table, loads environmental conditions in computational fluid dynamics software, conducts virtual wind tunnel tests, and obtains initial filtration resistance data. The accelerated aging process simulates the pollutant accumulation process during long-term use through a mathematical model, calculates the capture saturation curve, and plots the attenuation graph of filtration efficiency over time. The humidity response strain analysis studies the moisture absorption and deformation characteristics of materials under different humidity conditions and constructs a humidity response strain diagram. The life prediction analysis combines the initial filtration resistance and efficiency decay data to evaluate the impact of high-concentration pollutants on the material saturation time and generates a life prediction data set. The boundary condition screening and performance interpolation calculations process the prediction data through statistical methods to form a set of full-condition performance curves covering various working conditions. When performing precise conversion and verification based on the set of full-condition performance curves, the material formula parser performs reverse analysis on the indicators in the performance curves to determine the material composition ratio relationship and generates a material formula list. The availability assessment checks the availability of formula items in the existing supply chain, matches the supplier resource library, and forms a material procurement parameter table. The key structural dimension data is extracted from the multi-layer composite filtration structure configuration table and the set of full-condition performance curves to construct a manufacturing dimension specification card. The process adaptability analysis converts the design parameters into specific production equipment operation parameters to form a process flow instruction set. The small-batch trial production collects deviation data in actual production, establishes a process correction factor table, which is used to fine-tune the material formula and manufacturing dimensions, and finally integrates to form a filter bag design scheme that can be directly used for production.

[0034] For example, when the capture device detects that the average diameter of PM2.5 particles in a certain indoor environment is 0.8 microns and the concentration is 75 μg / m 3 , the formaldehyde concentration is 0.12 mg / m 3 , the VOC concentration is 1.5 mg / m 3 , and the electrostatic adsorption test records that the pollutant adhesion is 2.3 mN / cm at 45% humidity 2 , these data are fused to form a pollutant spatio-temporal distribution feature map. The measurement of the material's micro-permeability shows that a certain filter material has a porosity of 78%, a specific surface area of 850 m 2 / g, and an active site density of 3.2×1014 per cm 2 . The parametric modeling calculates that the optimal pleat angle is 22°, the depth is 15 mm, and the density is 4.2 pleats / cm for the most uniform air flow distribution. The multi-layer composite filtration structure adopts a three-layer design of electrostatic fiber, activated carbon fiber, and HEPA fiber, with a thickness ratio of 2:3:5, and the interface uses a hot pressing process. The simulation test shows that at 80% humidity and 250 μg / m 3At the pollutant concentration, it takes 1,200 hours for the filtration efficiency to drop from the initial 99.5% to 90%. These data are converted into specific material formulas and production process parameters through reverse analysis, and finally a filter bag design scheme that can be actually applied is formed.

[0035] In the embodiment of the present application, multi-dimensional data of indoor air pollutants are collected through a pollutant particle dynamic capture device, and an accurate digital fingerprint library of pollutant characteristics is established. This fingerprint library contains key information such as the particle size distribution and adsorption characteristics of pollutants, providing an accurate data basis for subsequent designs and solving the problem of insufficient understanding of pollutant characteristics in traditional designs. Secondly, a precise quantification of the filter material is carried out using a material micro-permeability measuring instrument to generate a multi-dimensional material performance matrix. This matrix comprehensively characterizes the porosity, active site distribution, surface charge and other characteristics of the material, enabling designers to more accurately select filter materials suitable for specific pollutants. Furthermore, parametric modeling and air flow distribution calculations based on the multi-dimensional material performance matrix generate a self-balancing pleat structure parameter group. By optimizing parameters such as pleat angle, depth and density through artificial intelligence algorithms, the optimal design of the filter bag structure is achieved, significantly improving the filtration efficiency and service life. In addition, the combination order, thickness ratio and contact interface of different material layers of the filter bag are optimized and adjusted to form a multi-layer composite filter structure configuration table, giving full play to the synergistic effect of each material layer and enhancing the overall performance of the filtration system. It is particularly worth mentioning that this solution applies artificial intelligence algorithms for virtual testing and life prediction. By simulating the performance of the filter bag in an environment with high humidity and high-concentration pollutants, a set of full-condition performance curves is generated, accurately predicting the performance and service life of the product under various environmental conditions and avoiding the limitations of relying on physical testing in traditional methods. Finally, through precise conversion and verification based on the set of full-condition performance curves, a filter bag design scheme that can be directly used for production is generated, achieving seamless connection from design to production and improving the design conversion efficiency and product consistency. The application of artificial intelligence algorithms in the present invention, especially the deep learning and optimization algorithms in the links of pollutant data fusion processing, material performance prediction, structural parameter optimization and life prediction, greatly improves the intelligent level and accuracy of the design process, making the filter bag design no longer rely on experience and trial and error, but based on accurate data and scientific calculations, realizing personalized and precise design for complex indoor air pollution environments, thus significantly improving the filtration efficiency, service life and environmental adaptability of the filter bag.

[0036] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0037] (1) Real-time concentration monitoring of PM2.5 particles in indoor air is carried out through a high-precision light scattering sensor to obtain a particle size distribution histogram;

[0038] (2) Use a gas chromatograph analyzer to measure the concentration gradients of indoor formaldehyde and VOC gaseous pollutants, and form a pollutant concentration change curve;

[0039] (3) Use an electrostatic adsorption test plate to quantitatively record the surface adhesion of different pollutants under various temperature and humidity conditions, and construct a pollutant adhesion characteristic data set;

[0040] (4) Based on the obtained particle size distribution histogram, pollutant concentration change curve and pollutant adhesion characteristic data set, conduct multi-source data correlation analysis through a data fusion processor to generate a pollutant spatio-temporal distribution characteristic map;

[0041] (5) Import the generated pollutant spatio-temporal distribution characteristic map into the feature extraction unit, extract key pollutant feature parameters, and establish a pollutant behavior pattern library;

[0042] (6) According to the established pollutant behavior pattern library and historical environmental condition data, conduct cross-validation and normalization processing to form a pollutant characteristic digital fingerprint library.

[0043] Specifically, a high-precision light scattering sensor is used to monitor the real-time concentration of PM2.5 particles in indoor air and obtain a particle size distribution histogram. The high-precision light scattering sensor is a detection device based on the principle of light scattering. When a laser beam irradiates suspended particles in the air, the particles will scatter light, and the sensor captures this scattered light and converts the optical signal into an electrical signal through a photoelectric conversion element. The signal processing circuit amplifies and filters the electrical signal, and then calculates the size and concentration of the particles through Mie scattering theory. The sensor collects data in real time, samples 60 times per second, and after continuously monitoring for 30 minutes, groups and statistically analyzes the 180,000 collected data points according to the particle diameter size to form a particle size distribution histogram. The horizontal axis of this histogram represents the particle diameter range (usually divided into 50 intervals from 0.1μm to 10μm), and the vertical axis represents the number or concentration of particles in each interval. A gas chromatograph analyzer is used to measure the concentration gradient of indoor formaldehyde and VOC gaseous pollutants and form a pollutant concentration change curve. The gas chromatograph analyzer is an instrument for separating and detecting the components of complex mixed gases. Its working principle is to utilize the difference in the distribution coefficients of different compounds between the stationary phase and the mobile phase to separate the components in the mixture in the chromatographic column. This analyzer is equipped with a special chromatographic column and a hydrogen flame ionization detector, which can detect formaldehyde and VOC concentrations at the ppb (one in a billion) level. When performing concentration gradient measurement, the analyzer collects samples at different positions in the room (usually selecting 9 measurement points to form a three-dimensional space grid) at preset time intervals (once every 10 minutes) and continuously measures for 3 hours, obtaining a total of 162 concentration data points. These data are arranged in a time series, and a continuous pollutant concentration change curve is generated through an interpolation algorithm. The horizontal axis of the curve is time, and the vertical axis is the pollutant concentration.

[0044] Meanwhile, an electrostatic adsorption test board is used to quantitatively record the surface adhesion of different pollutants under various temperature and humidity conditions, and a pollutant adhesion characteristic data set is constructed. The electrostatic adsorption test board is a device dedicated to measuring the adsorption characteristics of microparticles, consisting of a metal plate with a controllable charge on the surface, a microelectronic force sensor, and an environmental parameter control system. During the test, the control system sets specific temperature (15°C to 40°C, at intervals of 5°C) and humidity (30% to 90%, at intervals of 10%) combinations, forming a total of 42 different environmental conditions. Under each environmental condition, different voltages (0V to 5000V, at intervals of 500V) are applied to the surface of the test board to measure the adhesion of different types of pollutants (PM2.5, formaldehyde condensate, VOC condensate). The microelectronic force sensor records the force changes during the adsorption and desorption processes of the pollutants, calculates the surface adhesion value, and finally obtains a pollutant adhesion characteristic data set containing 42×11×3 = 1386 data points.

[0045] Based on the obtained particle size distribution histogram, pollutant concentration change curve, and pollutant adhesion characteristic dataset, multi-source data correlation analysis is carried out through a data fusion processor to generate a pollutant spatio-temporal distribution feature map. The data fusion processor is a computing device dedicated to processing multi-source heterogeneous data, and uses the Kalman filtering algorithm to synchronize and align time series data. First, timestamp alignment is performed to synchronize the three types of data according to the acquisition time; then spatial registration is carried out to map the data collected at different positions into a unified three-dimensional space coordinate system; then data standardization is performed to eliminate the differences brought by different dimensions; finally, the correlation relationship between data is extracted through a tensor decomposition algorithm, and a continuous pollutant spatio-temporal distribution feature map is generated using a spatial interpolation method. This feature map is a four-dimensional data volume, with three dimensions representing spatial coordinates and one dimension representing time. Each spatio-temporal point contains multi-dimensional information such as pollutant concentration, particle size distribution, and adhesion characteristics.

[0046] Import the generated pollutant spatio-temporal distribution feature map into the feature extraction unit to extract key pollutant feature parameters and establish a pollutant behavior pattern library. The feature extraction unit is a data processing module designed based on deep learning algorithms, and uses a convolutional neural network to analyze the spatio-temporal distribution feature map. This unit first performs dimensionality reduction on the four-dimensional data volume, extracts the main variation features through principal component analysis; then applies the non-negative matrix factorization algorithm to decompose the complex pollutant distribution pattern into a linear combination of several basic patterns; then uses a clustering algorithm to classify similar pollutant behavior patterns to form typical pollutant behavior categories; finally, the association rule mining algorithm is used to discover the association rules between environmental conditions and pollutant behavior. After this series of processes, key feature parameters including diffusion rate, sedimentation coefficient, adsorption saturation, etc. are extracted from the massive data, and a pollutant behavior pattern library containing typical pollutant behavior patterns is established.

[0047] According to the established pollutant behavior pattern library and historical environmental condition data, cross-validation and normalization processing are carried out to form a pollutant characteristic digital fingerprint library. Cross-validation is a statistical method for evaluating the generalization ability of a model, and the performance of the model is evaluated by dividing the dataset into training sets and validation sets and repeating training and validation multiple times. In this step, the K-fold cross-validation method is used, and the data in the pollutant behavior pattern library is randomly divided into 10 parts. Each time, 9 parts are used to train the model, and the remaining 1 part is used to verify the prediction accuracy of the model. This is repeated 10 times and the average result is taken. Normalization processing is a process of converting data with different dimensions and different distributions to a unified scale. The Z-score normalization method is used to process each feature parameter so that its mean is 0 and the standard deviation is 1. After cross-validation, stable and reliable pollutant behavior patterns are selected, and the data format and scale are unified through normalization processing. Finally, a pollutant characteristic digital fingerprint library containing multi-dimensional information such as pollutant particle size characteristics, concentration distribution characteristics, adsorption characteristics, and diffusion characteristics is formed.

[0048] For example, in an office environment, a high-precision light scattering sensor continuously monitors for 30 minutes. The PM2.5 particle data collected shows that most particles are concentrated in the range of 0.5 μm to 2.5 μm, forming a unimodal distribution histogram skewed to the right. The gas chromatograph analyzer performs gradient measurements at 9 measurement points for 3 hours and finds that the formaldehyde concentration fluctuates between 0.08 mg / m 3 and 0.15 mg / m 3 and shows obvious periodic changes over time, which is highly correlated with the operating cycle of the indoor air conditioner. The electrostatic adsorption test board tests under different temperature and humidity combinations and finds that when the humidity increases from 30% to 70%, the surface adhesion of PM2.5 particles increases by 2.8 times, while the temperature has a relatively small impact. The data fusion processor performs correlation analysis on these three groups of data and finds that the southwestern corner of the office is the area with the highest pollutant concentration, and the peak value is reached 15 minutes after the air conditioner is started. The feature extraction unit extracts key parameters such as the pollutant diffusion rate of 3.2 cm / min and the sedimentation coefficient of 0.018 min-1 from the spatio-temporal distribution feature map. Through 10-fold cross-validation and Z-score normalization processing, these feature parameters are compared with historical data, and it is confirmed that the pollutants in this environment mainly come from the release of office equipment, forming a digital fingerprint of pollutant characteristics with specific features. These digital fingerprint data directly guide the subsequent selection of filter materials and the design of the filter bag structure, enabling the finally designed filter bag to specifically filter the main pollutants in this environment.

[0049] In a specific embodiment, the process of performing step S102 may specifically include the following steps:

[0050] (1) Measure the specific surface area of the filter material by the nitrogen adsorption method and record the material pore size distribution curve;

[0051] (2) Use electron microscopy scanning technology to perform high-magnification imaging on the surface morphology of the filter material to obtain the material surface microstructure diagram;

[0052] (3) Use a thermogravimetric analyzer to quantitatively test the adsorption capacity of the filter material under different temperature conditions to form an adsorption thermodynamic characteristic diagram;

[0053] (4) Fuse the material pore size distribution curve and the material surface microstructure diagram to establish a three-dimensional pore network topological structure of the material;

[0054] (5) Locate and measure the density of active sites in the three-dimensional pore network topological structure of the material by fluorescence labeling method to construct a spatial distribution diagram of active sites;

[0055] (6) Combine the spatial distribution map of active sites with the adsorption thermodynamic characteristic map, and construct a prediction model for the capture efficiency of the material through correlation analysis to generate a multi-dimensional material property matrix.

[0056] Specifically, the specific surface area of the filter material is measured by the nitrogen adsorption method, and the pore size distribution curve of the material is recorded. The nitrogen adsorption method is a classic method for measuring the specific surface area and pore structure of porous materials. Based on the BET theory (Brunauer-Emmett-Teller theory), this theory describes the process of gas molecules forming multi-layer adsorption on the solid surface. During the measurement, the filter material sample is placed in the sample tube. After degassing to remove surface impurities and moisture, a nitrogen adsorption-desorption experiment is carried out at the liquid nitrogen temperature (-196 °C). The test instrument automatically controls the change of nitrogen pressure, records the amount of nitrogen adsorbed by the material at different relative pressures, and plots the adsorption-desorption isotherm. The pore size distribution curve of the material is calculated by the BJH method (Barrett-Joyner-Halenda method). The horizontal axis of this curve represents the pore size (usually several discrete points in the range of 1-100 nanometers), and the vertical axis represents the pore volume or pore area distribution corresponding to the pore size. At the same time, the specific surface area of the material is calculated. The specific surface area refers to the total surface area per unit mass of the material, with the unit of square meters per gram (m 2 / g).

[0057] The surface morphology of the filter material is magnified at a high magnification by electron microscopy scanning technology to obtain a microscopic structure diagram of the material surface. Electron microscopy scanning technology uses signals such as secondary electrons and backscattered electrons generated by the interaction between the electron beam and the sample surface, which are collected by a detector and converted into image signals to achieve the observation of the sample surface morphology. In the analysis of filter materials, first, the sample is cut into an appropriate size, fixed on the sample stage with conductive tape, and treated by sputtering gold or carbon to enhance conductivity. Then the sample is placed in the vacuum chamber of the scanning electron microscope, and the electron beam is scanned on the sample surface by controlling the electron beam acceleration voltage (usually 5 - 20 kV) and the focusing system. The secondary electron detector collects the signals, and a microscopic structure diagram of the material surface is formed through the image processing system. Usually, multiple images are collected for each sample at different magnification ratios (from 100 times to 100,000 times) to comprehensively understand the structural characteristics of the material from macroscopic to microscopic, including fiber distribution, surface roughness, pore morphology and other information. Subsequently, a thermogravimetric analyzer is used to quantitatively test the adsorption capacity of the filter material under different temperature conditions to form an adsorption thermodynamic characteristic diagram. A thermogravimetric analyzer is an instrument that accurately measures the mass change of a sample during the temperature change process and is used to study the thermal stability, adsorption - desorption behavior and reaction kinetics of materials. During the test, the filter material sample is placed on a precision balance, and in a specific atmosphere (usually nitrogen or air), it is heated according to a preset program (from room temperature to 500 °C, with a heating rate of 10 °C / min). At the same time, the relationship curve between the sample mass change and temperature, that is, the thermogravimetric curve (TG curve), is continuously recorded. For the study of the adsorption characteristics of filter materials, first, the sample is treated at a high temperature to remove moisture and volatile substances, then cooled to room temperature, and a gas containing the pollutant to be measured (such as formaldehyde or VOC) is introduced, and the increased adsorption mass of the material at different temperatures is recorded. Through data processing, the adsorption capacity at different temperatures is calculated, and an adsorption thermodynamic characteristic diagram is drawn, which reflects the dependence of the material's adsorption ability for specific pollutants on temperature.

[0058] Fuse the pore size distribution curve of the material with the microscopic surface structure diagram of the material to establish a three-dimensional pore network topological structure of the material. Data fusion is a process of comprehensively processing data from different sources and with different properties to form more complete information. In this method, first, digital processing is performed on the electron microscope images, including image enhancement, noise removal, and edge detection, to extract features such as the fiber orientation and pore distribution on the material surface. Then, image segmentation algorithms are used to identify and label different structural units, such as fibers, intersections, and pores. At the same time, the statistical data in the pore size distribution curve is spatially mapped with the image information, and through the structure reconstruction algorithm, the two-dimensional surface information is extended to a three-dimensional network structure. Specifically, when implementing, the Markov random field model is used to describe the spatial correlation of the pores inside the material, combined with the Monte Carlo simulation method, to reconstruct the three-dimensional structure based on the two-dimensional slice information. The finally formed three-dimensional pore network topological structure of the material is a digital model containing the pore position, size, connectivity, and spatial distribution, which can intuitively display the internal structural features of the material.

[0059] Locate and measure the density of the active sites in the three-dimensional pore network topological structure of the material by fluorescence labeling method to construct a spatial distribution map of the active sites. The fluorescence labeling method is a technique that uses specific fluorescent dyes or fluorescent markers to specifically bind to the target substance and observes and analyzes the distribution of the target substance under a fluorescence microscope. In the analysis of filter materials, first, a fluorescent dye that can specifically bind to the active sites of the material (such as functional groups like hydroxyl, carboxyl, amino, etc.) is selected, and the material sample is immersed in the dye solution to make the fluorescent molecules bind to the active sites. After washing to remove the unbound dye, three-dimensional scanning imaging is performed under a confocal fluorescence microscope. The instrument scans the sample layer by layer, records the fluorescence signal intensity and distribution of each layer, and forms a three-dimensional fluorescence intensity data set. Through image processing software, quantitative analysis of the fluorescence intensity is carried out to calculate the density (the number of active sites per unit volume or unit mass of the material) and distribution uniformity of the active sites. Combining with the three-dimensional pore network topological structure obtained previously, the active site information is mapped onto the three-dimensional structure to construct a spatial distribution map of the active sites, accurately characterizing the position and concentration gradient of the active sites in the material space.

[0060] Combine the spatial distribution map of active sites with the adsorption thermodynamic property map, and construct a prediction model for the capture efficiency of materials through correlation analysis to generate a multi-dimensional material performance matrix. Correlation analysis is a statistical method for studying the mutual relationship between variables. In this method, first calculate the correlation coefficients between the active site density, distribution characteristics and the adsorption capacity of the material under different conditions, and identify the parameter pairs with significant correlations. Then use the multiple regression analysis method to establish the mathematical relationship between the active site characteristic parameters and the adsorption performance, and construct a prediction model. This model can predict the capture efficiency of different pollutants based on the structural characteristics and active site distribution of the material. Based on this model, systematically evaluate the performance of the material under different working conditions (temperature, humidity, pollutant concentration, etc.) to generate a multi-dimensional material performance matrix. This matrix is a high-dimensional data structure, each dimension corresponds to a performance parameter or a working condition variable, and the matrix element value represents the performance index of the material under specific conditions, such as capture efficiency, adsorption capacity, pressure drop, etc.

[0061] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0062] (1) Discretize the initial geometric form of the folded structure through a geometric parameter generator to form a set of grid points of folded units;

[0063] (2) Map the material physical parameters in the multi-dimensional material performance matrix onto the set of grid points of folded units to construct a digital folded material model;

[0064] (3) Apply flow field boundary conditions to the digital folded material model, and determine the air flow flux distribution of each folded unit through segmented pressure drop calculation;

[0065] (4) Identify the pressure imbalance area based on the air flow flux distribution, and perform gradient adjustment on the folded angle parameter to generate an angle optimization data table;

[0066] (5) Combine the angle optimization data table with the folded depth variable, and determine the depth-density relationship curve through response surface analysis to form a folded geometry coupling relationship diagram;

[0067] (6) Perform air flow uniformity evaluation and parameter iterative optimization according to the folded geometry coupling relationship diagram to generate a self-balanced folded structure parameter group.

[0068] Specifically, the initial geometric form of the pleated structure is discretized by a geometric parameter generator to form a set of grid points of pleat units. The geometric parameter generator is a computational tool dedicated to generating digital models of complex geometric structures. For the pleated structure of the filter bag, parametric modeling technology is used to convert the continuous pleated form into a discrete mathematical representation. Discretization is the process of dividing a continuum into a finite number of discrete elements, facilitating subsequent numerical calculations and analyses. In specific implementation, first, a geometric description equation of the pleated structure is established, defining the basic shape characteristics of the pleats, including parameters such as pleat angle, pleat depth, and pleat spacing. Then, finite element mesh generation technology is used to perform mesh dissection on the pleated structure, dividing the continuous pleats into thousands of small elements to form a set of grid points of pleat units. The density of the grid points is dynamically adjusted according to the calculation accuracy requirements, usually with a higher grid density at geometrically sharp changes such as pleat corners. Each grid point records three-dimensional spatial coordinates and local geometric feature parameters such as curvature and normal vector information.

[0069] The material physical parameters in the multi-dimensional material property matrix are mapped onto the set of grid points of pleat units to construct a digital pleated material model. The multi-dimensional material property matrix contains various physical property parameters of the filter material, such as porosity, permeability, elastic modulus, surface charge density, etc. Parameter mapping is the process of associating these material properties with spatial positions, assigning corresponding material characteristic values to each grid point. The mapping process uses a spatial interpolation algorithm to calculate the exact parameter values at microscopic grid points based on the distribution characteristics of the material at the macroscopic scale. For inhomogeneous materials, hierarchical mapping technology is used to assign the characteristics of different material layers to the grid points in the corresponding regions. The digital pleated material model is a computational model that combines geometric structure and material physical properties. Each grid point contains both position information and a complete set of material property parameters.

[0070] After the digital pleated material model is established, flow field boundary conditions need to be applied to it, and the air flow rate distribution of each pleat unit is determined through segmented pressure drop calculations. The flow field boundary conditions include inlet flow rate, outlet pressure, and no-slip conditions on the sidewalls, etc. The segmented pressure drop calculation is based on an extended form of Darcy's formula to calculate the pressure gradient under different material regions and geometric structures. The specific calculation formula is:

[0071]

[0072] where, ΔP f is the pressure drop (Pa) of the f-th pleat unit, μ is the fluid viscosity (Pa·s), L f is the effective length (m) of the fluid passing through this unit, V f is the flow velocity (m / s) within this unit, k f is the permeability (m 2 ) of this unit, and ρ is the fluid density (kg / m3 ), C f is the resistance coefficient related to the structure (dimensionless). By solving this system of equations, the pressure drop values and the corresponding air flow fluxes (Q f ) distribution of each corrugated unit are calculated. The relationship between the air flow flux, the pressure drop, and the permeability is:

[0073]

[0074] where Q f is the volume flow rate of air passing through the f-th corrugated unit (m 3 / s), and A f is the cross-sectional area of this unit (m 2 ).

[0075] Based on the air flow flux distribution, the pressure imbalance regions are identified, the corrugation angle parameters are adjusted gradientually, and an angle optimization data table is generated. The pressure imbalance regions refer to the parts where the air flow flux distribution is uneven, usually manifested as the air flow flux being too large in some corrugated units while too small in other units. In the identification process, first, the average air flow flux (\bar{Q}) of the entire filter bag is calculated, and then the air flow flux deviation of each unit is calculated:

[0076]

[0077] When δ f exceeds the set threshold (usually 15%), this unit is marked as a pressure imbalance region. For these regions, the gradient descent algorithm is used to adjust the corrugation angle parameters. The adjustment process follows the following formula:

[0078]

[0079] where θ new and θ old are the corrugation angles (degrees) after and before adjustment respectively, η is the learning rate (a parameter controlling the adjustment step size), is the gradient of the air flow uniformity objective function with respect to the angle. The objective function is usually defined as the sum of the squares of the air flow flux deviations of each unit:

[0080]

[0081] where N is the total number of corrugated units. Through multiple iterative calculations, the corrugation angles are gradually optimized until the air flow flux distribution reaches the expected uniformity. After each iteration, the angle parameters and the corresponding air flow uniformity indicators are recorded in the angle optimization data table.

[0082] Combine the angle optimization data table with the pleat depth variable, determine the depth-density relationship curve through response surface analysis, and form a pleat geometry coupling relationship diagram. Response surface analysis is a statistical method for studying how multiple independent variables affect a dependent variable, and it describes this complex relationship by constructing a mathematical model. In the design of filter bags, the pleat angle and depth are taken as independent variables, and the filtration efficiency and pressure drop are taken as dependent variables. By designing a series of experimental points with different combinations of angles and depths, the response values of each point are obtained. Then, the polynomial regression method is used to fit the response surface equation to analyze how the pleat depth affects the optimal pleat density. The relationship between depth and density usually exhibits non-linear characteristics, and response surface analysis can find the pleat density values that can achieve the best filtration performance at different depths. The formed pleat geometry coupling relationship diagram is a graphical representation that intuitively shows the interdependence between pleat geometry parameters. The horizontal axis represents the pleat depth, the vertical axis represents the optimal pleat density, and each point on the curve corresponds to a set of optimized pleat geometry parameters. According to the pleat geometry coupling relationship diagram, the air flow uniformity evaluation and parameter iterative optimization are carried out to generate a self-balancing pleat structure parameter group. The air flow uniformity evaluation is a quantitative analysis of the air flow distribution uniformity in the filter bag under given geometric parameters, and usually the coefficient of variation (the ratio of the standard deviation of the air flow rate to the average value) is used as the evaluation index. The parameter iterative optimization is a cyclic optimization process. By continuously adjusting the pleat angle, depth, and density parameters, the parameter combination that can achieve the best air flow uniformity and filtration efficiency is found. The specific optimization process uses genetic algorithms or particle swarm optimization algorithms, sets the fitness function as the weighted sum of air flow uniformity and filtration efficiency, and finally obtains the global optimal solution through multi-generation evolution or iterative calculation. The self-balancing pleat structure parameter group is a set of geometric parameter sets that can make the filter bag achieve automatic air flow distribution balance and maximize filtration efficiency in the working state, including key parameters such as the optimal pleat angle, depth, and density, providing direct guidance for the subsequent structural design and manufacturing of the filter bag.

[0083] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0084] (1) Quantitatively measure the interfacial force between candidate filter materials through a material compatibility analyzer to obtain material interface bonding strength data;

[0085] (2) Evaluate the capture ability complementarity of candidate filter materials, calculate the material combination capture spectrum based on the pollutant data in the pollutant characteristic digital fingerprint library, and form a material complementarity scoring table;

[0086] (3) Exhaustively analyze the arrangement and combination schemes of different material layers according to the material complementarity scoring table, and generate a material sorting scheme library through the calculation of the directional filtration coefficient;

[0087] (4) Combine the material sorting scheme library with the self-balancing fold structure parameter group, and determine the optimal thickness ratio of each layer of material through coordinated calculation of the pressure drop between layers to construct a thickness ratio relationship matrix;

[0088] (5) Use the thickness ratio relationship matrix and the material interface bonding strength data for cross-analysis, identify the interface stress concentration points, adjust the interlayer contact mode of the materials, and generate an interface optimization strategy table;

[0089] (6) Integrate the interface optimization strategy table with the material sorting scheme library and the thickness ratio relationship matrix to form a multi-layer composite filter structure configuration table.

[0090] Specifically, quantitatively measure the interfacial forces between candidate filter materials through a material compatibility analyzer to obtain material interface bonding strength data. A material compatibility analyzer is a precision instrument dedicated to measuring the interfacial bonding characteristics between different materials. Through tensile tests, shear tests, and peel tests, etc., comprehensively evaluate the material interface bonding strength. During the measurement process, the two materials to be tested are subjected to hot pressing or bonding treatment according to preset conditions (such as temperature, pressure, and time) to form a composite interface, and then the bonding strength test is carried out in a standard test environment. The tensile test applies a tensile force perpendicular to the interface direction to measure the maximum stress required for interface separation; the shear test applies a force parallel to the interface direction to measure the maximum shear stress required for interface slip; the peel test simulates the gradual separation process in actual use and measures the energy required for interface separation per unit width. The test results are comprehensively formed into material interface bonding strength data, which includes the interface strength values, interface failure modes, and durability evaluations of different material combinations under various bonding conditions. Evaluate the complementarity degree of the capture capabilities of candidate filter materials, calculate the capture spectra of material combinations based on the pollutant data in the pollutant characteristic digital fingerprint library, and form a material complementarity score table. The evaluation of the complementarity degree of capture capabilities is a process of analyzing the capture mechanisms and efficiency differences of different filter materials for various pollutants to find complementary combinations. The pollutant characteristic digital fingerprint library contains multi-dimensional information such as the particle size distribution, chemical characteristics, and adsorption behavior of pollutants. By comparing these data with the capture characteristics of various filter materials, calculate the capture efficiency of the material for specific pollutants. The calculation formula for the capture spectrum of the material combination is:

[0091] CE ab,p =1-(1-CE a,p )·(1-CE b,p )

[0092] where CE ab,p represents the capture efficiency of the combination of material a and material b for pollutant p, CE a,p and CE b,prespectively represent the capture efficiency of pollutant p when using material a and material b alone. For each possible combination of materials, calculate its comprehensive capture ability for all target pollutants to form a complementarity score, and the calculation formula is:

[0093]

[0094] Among them, CIS ab is the complementarity score of material a and material b, P is the total number of pollutant types, w p is the weight coefficient of pollutant p (determined according to its harm degree or importance). The third factor is used to quantify the difference degree of the capture ability of the two materials. The greater the difference, the stronger the complementarity. By comparing the complementarity scores of different material combinations, select the combination with the highest score to form a material complementarity score table.

[0095] Based on the material complementarity score table, conduct an exhaustive analysis of the permutation and combination schemes of different material layers, and generate a material sorting scheme library through the calculation of the directional filtration coefficient. Exhaustive analysis is a process of systematically evaluating all possible arrangements of material layers. For each permutation and combination, calculate its directional filtration coefficient (DFC), which takes into account the influence of the air flow direction on the filtration efficiency. The calculation formula of DFC is:

[0096]

[0097] Among them, {a1, a2,..., a L} represents a specific material arrangement order, L is the number of material layers, CE al,p is the basic capture efficiency of the l-th layer of material for pollutant p, is the directional adjustment factor, and its value range is between 0.6 - 1.4, which is used to adjust the influence of the air flow direction on the capture efficiency. Different materials have different sensitivities to the air flow direction. For example, the electrostatic fiber may have higher efficiency when the air flow passes through in the positive direction, while the activated carbon adsorption material is less affected by the direction. By calculating the DFC values of all possible permutations and combinations and sorting them from high to low scores, a material sorting scheme library is formed.

[0098] Combine the material sorting scheme library with the self-balancing fold structure parameter group, and determine the optimal thickness ratio of each layer of material through the interlayer pressure drop coordination calculation to construct a thickness ratio relationship matrix. The interlayer pressure drop coordination calculation is based on the inherent resistance characteristics of each layer of material and the principle of minimizing the overall pressure drop to solve the optimal thickness distribution. The total pressure drop calculation formula is:

[0099]

[0100] Among them, ΔP total is the total pressure drop (Pa), ΔP l is the pressure drop of the l-th layer of material, Rl is the resistance coefficient per unit thickness of the l-th layer of material (Pa·s / m 2 ), v is the air flow velocity (m / s), and t l is the thickness of the l-th layer of material (m). Under the total thickness constraint condition, combined with various fold structure parameters (angle, depth, density), the optimal thickness ratio under different working conditions is calculated to form a thickness ratio relationship matrix. The rows of this matrix represent different combinations of fold structure parameters, the columns represent the thickness ratios of each layer of material, and the matrix element values are specific thickness ratios.

[0101] Cross-analysis is carried out using the thickness ratio relationship matrix and the material interface bonding strength data to identify the interface stress concentration points, adjust the material interlayer contact method, and generate an interface optimization strategy table. The identification of stress concentration points is based on finite element analysis to simulate the stress distribution generated when air flows through the multi-layer composite filter material. For each interface, the uniformity index and the maximum stress value of the stress distribution are calculated and compared with the interface bonding strength data to identify the positions where the stress level exceeds the bonding strength safety threshold. For the identified stress concentration points, analyze the formation reasons and design optimization strategies, including adjusting the material contact method (point contact, line contact or surface contact), adding a transition layer, adjusting the hot pressing parameters, etc. The effect of each strategy is verified by secondary finite element analysis, and the scheme with the best stress reduction effect is selected to form an interface optimization strategy table. The rows of this table represent different interface positions, the columns represent different optimization strategies, and the table content is the stress reduction effect and operation parameters of each strategy.

[0102] Integrate the interface optimization strategy table with the material sorting scheme library and the thickness ratio relationship matrix to form a multi-layer composite filter structure configuration table. The integration process uses a multi-criteria decision-making method, comprehensively considering factors such as filtration efficiency, pressure drop, structural stability, and manufacturing feasibility. The multi-layer composite filter structure configuration table is a complete technical specification document that details the key parameters such as the material composition, layer structure, thickness ratio, and interface treatment process of the filter bag.

[0103] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0104] (1) Set the temperature, humidity, and pollutant concentration in a hierarchical combination through the environmental parameter control box to construct a multi-dimensional test working condition matrix;

[0105] (2) Convert the structural parameters in the multi-layer composite filter structure configuration table into a digital twin prototype, load the environmental conditions in the multi-dimensional test working condition matrix, and conduct virtual wind tunnel tests to obtain the initial filtration resistance data;

[0106] (3) Apply accelerated aging treatment to the digital twin prototype, determine the capture saturation curve through the calculation of the pollutant accumulation amount, and draw the filtration efficiency decay map;

[0107] (4) Analyze the hygroscopic deformation characteristics of the filter material under different humidity conditions based on the filtration efficiency decay map, and construct a humidity-responsive strain map;

[0108] (5) Combine the humidity-responsive strain map with the initial filtration resistance data, analyze the influence of high-concentration pollutants on the saturation time of the material, and generate a life prediction data set;

[0109] (6) Conduct boundary condition screening and performance interpolation calculation on the life prediction data set to form a full-condition performance curve set.

[0110] Specifically, a multi-dimensional test condition matrix is constructed by setting the temperature, humidity, and pollutant concentration in a hierarchical combination through an environmental parameter control box. The environmental parameter control box is a closed test device capable of precisely controlling environmental conditions, used to simulate the performance of filter bags under various working environments. The hierarchical combination setting means discretizing parameters such as temperature, humidity, and pollutant concentration according to preset intervals, and then performing orthogonal combination to form a test condition matrix. During specific implementation, the temperature is usually divided into 5 levels (such as 15°C, 20°C, 25°C, 30°C, 35°C), the humidity is divided into 4 levels (such as 30%, 50%, 70%, 90%), and the pollutant concentration is divided into 3 levels (such as low, medium, high, corresponding to different numerical ranges). Through the combination of these parameters, a multi-dimensional test condition matrix with 5×4×3 = 60 working condition points is constructed. Each working condition point represents a specific combination of environmental conditions for subsequent virtual testing. The construction of the multi-dimensional test condition matrix adopts the orthogonal experimental design method, which can not only comprehensively cover various possible working conditions but also reduce unnecessary repeated testing and improve testing efficiency. The structural parameters in the multi-layer composite filter structure configuration table are converted into a digital twin prototype, and the environmental conditions in the multi-dimensional test condition matrix are loaded for virtual wind tunnel testing to obtain the initial filter resistance data. The digital twin prototype refers to a virtual model created in a computer environment that is consistent with the structure and performance of the physical filter bag. The conversion process first imports the parameters in the multi-layer composite filter structure configuration table, such as material types, layer thickness ratios, and pleat geometric parameters, into computer-aided design (CAD) software to construct a three-dimensional geometric model; then maps the physical property parameters (such as permeability, porosity, surface charge, etc.) of each material layer onto the geometric model to form a complete digital twin prototype. Virtual wind tunnel testing is to use computational fluid dynamics (CFD) software to simulate and analyze the flow and filtration performance of the digital twin prototype under different environmental conditions. During testing, the environmental conditions in the multi-dimensional test condition matrix are input as boundary conditions into the CFD model, the inlet flow velocity is set as the standard test flow velocity (usually 0.1 m / s), the outlet is at atmospheric pressure, and then the Navier-Stokes equations are solved to calculate the flow field distribution and pressure field distribution. The initial filter resistance data refers to the pressure drop of the filter bag in the initial stage of use (when not affected by the accumulation of contaminated particles), obtained by calculating the average pressure difference between the inlet and the outlet. Virtual wind tunnel testing is performed on 60 working condition points respectively to obtain an initial filter resistance data matrix, and each element in the matrix corresponds to the initial pressure drop value under a specific environmental condition.

[0111] Apply accelerated aging treatment to the digital twin prototype, determine the capture saturation curve through the calculation of pollutant accumulation, and plot the filtration efficiency decay map. The accelerated aging treatment is a calculation method to simulate the impact of pollutant accumulation on the performance during the long-term use of the filter bag. By increasing the virtual time step and pollutant concentration, the simulation period is shortened. During the treatment process, based on the previous CFD model, a pollutant particle trajectory tracking and deposition simulation module is added to calculate the capture process and accumulation of particles in the filter material. The calculation of pollutant accumulation adopts the Lagrangian-Euler hybrid method. First, the flow field is calculated (Euler method), and then the movement trajectories of a large number of representative particles are tracked in this flow field (Lagrangian method), and the positions and quantities of the captured particles are recorded. This process is carried out sequentially according to the virtual time step, and the permeability and porosity of the material are updated after each time step to reflect the change in material performance caused by pollutant accumulation. The capture saturation curve is a curve that describes the relationship between the mass of pollutants accumulated in the filter material over time and the change in its capture efficiency. The horizontal axis is the accumulated pollutant mass (or equivalent service time), and the vertical axis is the filtration efficiency. The filtration efficiency decay map is a set of capture saturation curves plotted under different environmental conditions, visually showing how environmental factors affect the service life and performance decay rate of the filter bag.

[0112] Based on the filtration efficiency decay map, analyze the moisture absorption and deformation characteristics of the filter material under different humidity conditions, and construct a humidity response strain map. The moisture absorption and deformation characteristics refer to the properties of the filter material that deform (such as expansion, contraction, distortion, etc.) after absorbing moisture in the air. This kind of deformation will affect the structural stability and filtration performance of the filter material. The analysis process first extracts the performance data under different humidity conditions from the filtration efficiency decay map, and then combines the moisture absorption performance parameters of the material (such as moisture absorption coefficient, saturated moisture content, etc.) to calculate the expansion rate or contraction rate of the material under each humidity condition. The humidity response strain map is a chart that describes the relationship between the strain (deformation ratio) of the filter material and the environmental humidity, usually plotted as multiple curves, and each curve represents the humidity-strain relationship at a specific temperature. The construction process adopts the multivariate regression analysis method, comprehensively considering the influence of temperature, humidity, and pollutant accumulation on the material deformation, establishing a mathematical model and plotting the corresponding curve graph. This chart has important reference value for predicting the structural changes and performance fluctuations of the filter bag in a high-humidity environment.

[0113] The humidity response strain diagram is combined with the initial filter resistance data to analyze the impact of high-concentration pollutants on the material saturation time and generate a life prediction data set. The deformation of the filter material caused by humidity changes will directly affect its filtration resistance and capture efficiency. Coupled with the rapid accumulation of high-concentration pollutants, the two together determine the service life of the filter bag. The analysis process first establishes a comprehensive evaluation model to convert the deformation data in the humidity response strain diagram into a resistance change factor, which is multiplied by the initial filter resistance data to obtain the actual resistance value after considering the humidity effect. Then, combined with the pollutant accumulation rate in the capture saturation curve (proportional to the concentration), the time required for the filter material to reach a saturated state (usually defined as the filtration efficiency drops to 80% of the initial value or the pressure drop increases to twice the initial value) is calculated, that is, the saturation time of the material. For each operating point in the multidimensional test operating condition matrix, the corresponding saturation time is calculated to form a life prediction data set. This data set is a multidimensional array that records the expected service life of the filter bag under different combinations of temperature, humidity and pollutant concentration.

[0114] The life prediction data set is subjected to boundary condition screening and performance interpolation calculation to form a full-condition performance curve set. Boundary condition screening is to select representative extreme condition points from the multidimensional test condition matrix. These points are usually located at the boundary or turning point of the parameter space and can reflect the main characteristics of the performance curve. The screening method uses a combination of extreme value analysis and sensitivity analysis to find the condition points that have the most significant impact on the life of the filter bag. The performance interpolation calculation is based on the known boundary condition point data to infer the performance parameters of the intermediate condition points. The interpolation process uses multidimensional spline interpolation or Kriging interpolation, which can accurately reflect the nonlinear effect of parameter changes on performance while ensuring data smoothness. The full-condition performance curve set is a set of performance curves covering all possible working conditions, including filtration efficiency curves, pressure drop change curves, and life prediction curves. These curves present the performance characteristics and service life of filter bags under various environmental conditions in an intuitive graphical manner, providing a scientific basis for the selection and application of filter bags.

[0115] For example, when designing a filter bag suitable for a high-humidity industrial environment, first set five temperature levels (15°C, 20°C, 25°C, 30°C, 35°C), four humidity levels (30%, 50%, 70%, 90%) and three pollutant concentration levels (100μg / m 3 , 500 μg / m 3 , 1000 μg / m 3),Construct a multi-dimensional test condition matrix containing 60 working condition points. Then extract the optimal design scheme from the multi-layer composite filtration structure configuration table (a three-layer structure of electrostatic fiber + activated carbon fiber + HEPA fiber, with a thickness ratio of 2:3:1, a pleat angle of 22°, a depth of 20 mm, and a density of 4 pleats / cm), and convert it into a digital twin prototype. When conducting virtual wind tunnel tests, select a standard flow rate of 0.1 m / s, and calculate the initial filtration resistance for each of the 60 working condition points to obtain the initial pressure drop matrix. The results show that at 25 °C, when the humidity increases from 30% to 90%, the initial pressure drop increases by approximately 25%, mainly due to the decrease in porosity caused by the hygroscopic expansion of the material. Then apply accelerated aging treatment to the digital twin prototype to simulate a 6-month usage process and track the accumulation of pollutant particles. Through calculation, under high pollution concentration (1000 μg / m 3 ), the capture efficiency of the filter material drops from the initial 99% to 85% after 1000 hours, while under low concentration (100 μg / m 3 ), the same efficiency decay takes approximately 10000 hours, showing an approximately linear proportional relationship. Analyze the hygroscopic deformation characteristics of the filter material based on the filtration efficiency decay map, and find that when the humidity exceeds 70%, the volume expansion rate of the electrostatic fiber layer reaches 8%, resulting in a decrease in porosity and an increase in pressure drop, thereby affecting the capture efficiency. The constructed humidity response strain map shows that the higher the temperature, the stronger the sensitivity of the material to humidity changes, and the maximum comprehensive strain rate is at 35 °C and 90% humidity. Combine the humidity response strain map with the initial filtration resistance data for analysis, calculate the saturation time of the filter bag under different working conditions, and generate a life prediction data set. The data shows that under the most severe conditions (35 °C, 90% humidity, 1000 μg / m 3 pollutant concentration), the service life of the filter bag is approximately 800 hours, while under the optimal conditions (15 °C, 30% humidity, 100 μg / m 3 pollutant concentration), the life can be extended to 12000 hours. Screen the boundary working conditions of the life prediction data set, select 8 representative working condition points, and use the cubic spline interpolation method to calculate the performance parameters of the intermediate working condition points, finally forming a full working condition performance curve set covering all possible working conditions, providing an accurate performance reference and life prediction for the practical application of the filter bag.

[0116] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0117] (1) Perform reverse analysis on the material performance indicators in the full working condition performance curve set through a material formula parser to determine the material composition ratio relationship and generate a material formula list;

[0118] (2) Evaluate the availability of the formula items in the material formula list, match the existing supplier resource library, and form a material procurement parameter table;

[0119] (3) Based on the correspondence between the multi-layer composite filter structure configuration table and the full-condition performance curve set, extract the key structure dimension data and construct a manufacturing dimension specification card;

[0120] (4) Convert the manufacturing dimension specification card into production equipment parameters, determine the equipment adjustment parameters through process adaptability analysis, and form a process flow instruction set;

[0121] (5) Use the process flow instruction set to conduct small-batch trial production of the filter bag samples, collect actual production deviation data, and establish a process correction factor table;

[0122] (6) Based on the process correction factor table, fine-tune and verify the material formula list and the manufacturing dimension specification card, and integrate them to form a filter bag design scheme that can be directly used for production.

[0123] Specifically, through the material formula parser, perform reverse analysis on the material performance indicators in the full-condition performance curve set to determine the material composition ratio relationship and generate a material formula list. The material formula parser is a data analysis tool based on machine learning algorithms, specifically used to reverse deduce the composition ratio from the performance characteristics of filter materials. The reverse analysis process uses a multi-objective optimization algorithm, taking performance indicators such as filtration efficiency, pressure drop, and service life in the full-condition performance curve set as objective functions, and the material composition ratio as the optimization variable to establish a performance-composition mapping relationship model. Specifically in implementation, first extract the composition-performance correspondence of known materials from the material database as training samples, and use machine learning methods such as support vector regression or random forest to establish a prediction model; then use genetic algorithms or particle swarm optimization methods to search in the composition space to find the material ratio combination that can best match the target performance indicators. The generated material formula list contains the detailed composition and proportion of various filter material layers, such as fiber type, additive type and content, surface treatment agent formula, etc., providing precise guidance for material production.

[0124] Conduct an availability assessment of the formula items in the material formula list, match the existing supplier resource library, and form a material procurement parameter table. The availability assessment is a process of analyzing the supply status of each component in the material formula in the market, aiming to ensure that the designed filter material can be actually produced. The assessment process first matches each component in the formula list with the supplier resource library, which is a structured database containing material supplier information, recording information such as supplier name, material specifications, price, minimum order quantity, delivery cycle, etc. The matching uses fuzzy query and similarity calculation methods to find a list of suppliers who can provide similar or equivalent materials. For the components with successful matching, directly record the supplier information; for the components with failed matching, conduct an alternative solution analysis to find alternative materials with similar performance but easier to obtain. The finally formed material procurement parameter table contains detailed procurement specifications, recommended suppliers, price ranges, order cycles, etc. of each material, facilitating the production department to purchase raw materials efficiently and accurately.

[0125] Based on the correspondence between the multi-layer composite filtration structure configuration table and the full operating condition performance curve set, extract the key structural dimension data and construct the manufacturing dimension specification card. The key structural dimension data refers to the geometric parameters that have a significant impact on the performance of the filter bag, including the thickness of each material layer, the pleat angle, the pleat depth, the pleat density, the overall dimensions, etc. The extraction process first analyzes the optimal design scheme in the multi-layer composite filtration structure configuration table, and then combines the performance data in the full operating condition performance curve set to determine the tolerance range of each parameter. The tolerance calculation is based on the sensitivity analysis method. By calculating the partial derivative of the performance with respect to the change of each parameter, the influence degree of the change of each parameter on the performance is quantified, and then a reasonable tolerance value is determined. The manufacturing dimension specification card is a technical document that details the dimension requirements of each part of the product, including information such as standard dimensions, tolerance ranges, and inspection methods. The construction of the specification card adopts a hierarchical structure design, which unfolds layer by layer from the overall dimensions to the local details to ensure the control of dimension accuracy during the manufacturing process. Convert the manufacturing dimension specification card into production equipment parameters, determine the equipment adjustment parameters through process adaptability analysis, and form a process flow instruction set. Process adaptability analysis is the process of evaluating whether a specific design can be implemented on existing equipment, aiming to identify potential production difficulties and make adjustments in advance. The analysis process first compares the dimension requirements in the manufacturing dimension specification card with the processing capabilities of the production equipment. The equipment parameters include processing accuracy, speed range, temperature control range, pressure control range, etc. The comparison uses the difference analysis method to calculate the gap between the design requirements and the equipment capabilities, and determine whether it is necessary to adjust the equipment parameters or modify the design requirements. For the equipment parameters that need to be adjusted, calculate the optimal setting values to meet the design requirements and form a list of equipment adjustment parameters. The process flow instruction set is a technical document that contains complete production steps and equipment parameter settings, which details the operation methods, equipment parameters, and quality control points of each link from raw material processing to finished product inspection to ensure the consistency of the production process and the stability of product quality.

[0126] Use the process flow instruction set to conduct small-batch trial production of the filter bag samples, collect actual production deviation data, and establish a process correction factor table. Small-batch trial production is a process to verify the design scheme before formal production. Usually, 10-20 samples are produced to test the design feasibility and process stability. The trial production process is carried out strictly in accordance with the process flow instruction set, and at the same time, the actual parameters and intermediate product characteristics of each link are recorded. Actual production deviation data refers to the differences between the trial-produced products and the design targets, including dimensional deviations, performance deviations, appearance deviations, etc. The data collection adopts a multi-point detection method, and detailed measurements are carried out on the key positions of each sample to form a complete deviation data set. Process correction factors are parameters used to compensate for systematic deviations in the production process and are calculated by statistically analyzing the actual production deviation data. The calculation process uses the regression analysis method to establish the mathematical relationship between the deviations and process parameters, and inversely deduce the correction factors that can minimize the deviations. The process correction factor table records the correction parameters and applicable conditions of each process link, providing an accurate basis for parameter adjustment in subsequent large-scale production.

[0127] Based on the process correction factor table, fine-tune and verify the material formula list and manufacturing dimension specification card, and integrate them to form a filter bag design scheme that can be directly used for production. Fine-tuning and verification is a process to finally optimize the design scheme according to the results of small-batch trial production, ensuring the feasibility and stability of the design scheme in the actual production environment. The fine-tuning of the material formula mainly considers the differences between the actual performance of the material and the expected performance, and makes up for the deficiencies by adjusting the component ratio or adding auxiliary materials; the verification of the manufacturing dimensions is based on the dimension deviation data, and the compensation design method is adopted, that is, the influence of production deviations is pre-considered in the design dimensions to obtain more accurate final dimensions. The integration process uniformly arranges the corrected material formula list, manufacturing dimension specification card and process flow instruction set to form a complete design scheme document. The filter bag design scheme that can be directly used for production is a comprehensive technical document, which includes four main parts: product design description, material procurement specification, manufacturing process guide and quality control standard.

[0128] The above describes the intelligent design method of the filter bag based on artificial intelligence in the embodiments of the present application. Next, the intelligent design system of the filter bag based on artificial intelligence in the embodiments of the present application will be described. Please refer to Figure 2 , an embodiment of the intelligent design system of the filter bag based on artificial intelligence in the embodiments of the present application includes:

[0129] An acquisition module, configured to collect multi-dimensional data on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library;

[0130] A quantification module, which is used to accurately quantify the porosity, active site distribution, and surface charge of the filter material by using a material micro-permeability measuring instrument according to the pollutant characteristic digital fingerprint library, so as to obtain a multi-dimensional material performance matrix;

[0131] A calculation module, which is used to perform parametric modeling and airflow distribution calculation on the pleat angle, depth, and density of the filter bag based on the multi-dimensional material performance matrix, so as to obtain a self-balanced pleat structure parameter set;

[0132] An adjustment module, which is used to optimize and adjust the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced pleat structure parameter set, so as to obtain a multi-layer composite filter structure configuration table;

[0133] A testing module, which is used to simulate and test the filtration efficiency and service life of the filter bag in an environment with high humidity and high-concentration pollutants by using the multi-layer composite filter structure configuration table, so as to obtain a full-condition performance curve set;

[0134] A verification module, which is used to accurately convert and verify the filter bag material formula, structural dimensions, and production process parameters according to the full-condition performance curve set, so as to obtain a filter bag design scheme that can be directly used for production.

[0135] Through the collaborative cooperation of the above-mentioned various components, multi-dimensional data collection of indoor air pollutants is carried out by the pollutant particle dynamic capture device, and an accurate digital fingerprint library of pollutant characteristics is established. This fingerprint library contains key information such as the particle size distribution and adsorption characteristics of pollutants, providing an accurate data basis for subsequent designs and solving the problem of insufficient understanding of pollutant characteristics in traditional designs. Secondly, the filtration material is accurately quantified by the material micro-permeability measuring instrument to generate a multi-dimensional material performance matrix. This matrix comprehensively characterizes the characteristics of the material such as porosity, active site distribution, and surface charge, enabling designers to more accurately select filtration materials suitable for specific pollutants. Furthermore, parametric modeling and air flow distribution calculation based on the multi-dimensional material performance matrix generate a self-balancing pleat structure parameter group. By optimizing parameters such as pleat angle, depth, and density through artificial intelligence algorithms, the optimal design of the filter bag structure is achieved, significantly improving the filtration efficiency and service life. In addition, the combination sequence, thickness ratio, and contact interface of different material layers of the filter bag are optimized and adjusted to form a multi-layer composite filtration structure configuration table, giving full play to the synergistic effect of each material layer and enhancing the overall performance of the filtration system. It is particularly worth mentioning that this solution applies artificial intelligence algorithms for virtual testing and life prediction. By simulating the performance of the filter bag in an environment with high humidity and high-concentration pollutants, a set of full-condition performance curves is generated, accurately predicting the performance and service life of the product under various environmental conditions and avoiding the limitations of relying on physical testing in traditional methods. Finally, through precise conversion and verification based on the set of full-condition performance curves, a filter bag design scheme that can be directly used for production is generated, achieving seamless connection from design to production and improving the design conversion efficiency and product consistency. The application of artificial intelligence algorithms in the present invention, especially the deep learning and optimization algorithms in the links of pollutant data fusion processing, material performance prediction, structural parameter optimization, and life prediction, greatly improves the intelligent level and accuracy of the design process, making the filter bag design no longer rely on experience and trial and error, but based on accurate data and scientific calculations, realizing personalized and precise design for complex indoor air pollution environments, thereby significantly improving the filtration efficiency, service life, and environmental adaptability of the filter bag.

[0136] Referring to Figure 3 , in the embodiment of the present invention, a computer device is further provided. This computer device can be a server, and its internal structure can be as Figure 3As shown in the figure. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0137] Those skilled in the art can understand that Figure 3 the structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0138] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0139] Those of ordinary skill in the art can understand that all or part of the process of implementing the method in the above embodiment can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database, or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0140] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0142] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. An intelligent design method for filter bags based on artificial intelligence, characterized in that, The intelligent design method of filter bags based on artificial intelligence includes: Performing multi-dimensional data collection on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library; Precisely quantifying the porosity, active site distribution, and surface charge of the filter material using a material micro-permeability measuring instrument based on the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material property matrix; Performing parametric modeling and airflow distribution calculation on the pleat angle, depth, and density of the filter bag based on the multi-dimensional material property matrix to obtain a self-balanced pleat structure parameter group; Optimizing and adjusting the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced pleat structure parameter group to obtain a multi-layer composite filter structure configuration table; Using the multi-layer composite filter structure configuration table to simulate and test the filtration efficiency and service life of the filter bag in an environment with high humidity and high-concentration pollutants to obtain a full-condition performance curve set; Precisely converting and verifying the filter bag material formula, structural dimensions, and production process parameters based on the full-condition performance curve set to obtain a filter bag design scheme that can be directly used for production.

2. The intelligent design method of filter bags based on artificial intelligence according to claim 1, wherein The performing multi-dimensional data collection on the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library includes: Performing real-time concentration monitoring of PM2.5 particles in indoor air through a high-precision light scattering sensor to obtain a particle size distribution histogram; Using a gas chromatograph analyzer to measure the concentration gradient of formaldehyde and VOC gaseous pollutants in indoor air to form a pollutant concentration change curve; Quantitatively recording the surface adhesion of different pollutants under various temperature and humidity conditions using an electrostatic adsorption test board to construct a pollutant adhesion characteristic data set; Based on the obtained particle size distribution histogram, pollutant concentration change curve, and pollutant adhesion characteristic data set, performing multi-source data correlation analysis through a data fusion processor to generate a pollutant spatio-temporal distribution feature map; Importing the generated pollutant spatio-temporal distribution feature map into a feature extraction unit to extract key pollutant characteristic parameters and establish a pollutant behavior pattern library; Performing cross-validation and normalization processing according to the established pollutant behavior pattern library and historical environmental condition data to form a pollutant characteristic digital fingerprint library.

3. The intelligent design method of filter bags based on artificial intelligence according to claim 1, characterized in that, The precisely quantifying the porosity, active site distribution, and surface charge of the filter material using a material micro-permeability measuring instrument based on the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material property matrix includes: Measuring the specific surface area of the filter material by the nitrogen adsorption method and recording the material pore size distribution curve; Using electron microscopy scanning technology to perform high-magnification imaging of the surface morphology of the filter material to obtain a material surface microstructure diagram; Using a thermogravimetric analyzer to quantitatively test the adsorption capacity of the filter material under different temperature conditions to form an adsorption thermodynamics characteristic map; Fusing the material pore size distribution curve and the material surface microstructure diagram to establish a three-dimensional pore network topological structure of the material; Locate and measure the density of active sites in the three-dimensional pore network topology of the material by fluorescence labeling method, and construct a spatial distribution map of active sites; Combine the spatial distribution map of active sites with the adsorption thermodynamic property map, and construct a prediction model for the capture efficiency of the material through correlation analysis to generate a multi-dimensional material property matrix.

4. The intelligent design method of filter bags based on artificial intelligence according to claim 1, characterized in that Parametrically model the pleat angle, depth, and density of the filter bag based on the multi-dimensional material property matrix and calculate the air flow distribution to obtain a self-balanced pleat structure parameter set, including: Discretize the initial geometric shape of the pleat structure through a geometric parameter generator to form a set of grid points of pleat units; Map the material physical parameters in the multi-dimensional material property matrix onto the set of grid points of pleat units to construct a digital pleated material model; Apply flow field boundary conditions to the digital pleated material model and determine the air flow flux distribution of each pleat unit through segmented pressure drop calculation; Identify the pressure imbalance area based on the air flow flux distribution, and perform gradient adjustment on the pleat angle parameter to generate an angle optimization data table; Combine the angle optimization data table with the pleat depth variable, and determine the depth-density relationship curve through response surface analysis to form a pleat geometry coupling relationship diagram; Evaluate the air flow uniformity and perform parameter iterative optimization according to the pleat geometry coupling relationship diagram to generate a self-balanced pleat structure parameter set.

5. The intelligent design method of filter bags based on artificial intelligence according to claim 1, characterized in that, Optimize and adjust the combination sequence, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced pleat structure parameter set to obtain a multi-layer composite filter structure configuration table, including: Quantitatively measure the interfacial interaction force between candidate filter materials through a material compatibility analyzer to obtain material interface bonding strength data; Evaluate the complementary degree of capture ability of the candidate filter materials, and calculate the material combination capture spectrum based on the pollutant data in the pollutant characteristic digital fingerprint library to form a material complementarity scoring table; Exhaustively analyze the permutation and combination schemes of different material layers according to the material complementarity scoring table, and generate a material sorting scheme library through directional filtration coefficient calculation; Combine the material sorting scheme library with the self-balanced pleat structure parameter set, and determine the optimal thickness ratio of each layer of material through interlayer pressure drop coordination calculation to construct a thickness ratio relationship matrix; Use the thickness ratio relationship matrix and the material interface bonding strength data for cross-analysis, identify the interface stress concentration points, and adjust the interlayer contact mode of materials to generate an interface optimization strategy table; Integrate the interface optimization strategy table with the material sorting scheme library and the thickness ratio relationship matrix to form a multi-layer composite filter structure configuration table.

6. The intelligent design method of filter bags based on artificial intelligence according to claim 1, characterized in that Simulate and test the filtration efficiency and service life of the filter bag in an environment with high humidity and high concentration of pollutants using the multi-layer composite filter structure configuration table to obtain a full-condition performance curve set, including: Gradually combine and set the temperature, humidity, and pollutant concentration through an environmental parameter control box to construct a multi-dimensional test condition matrix; Convert the structural parameters in the multi-layer composite filtration structure configuration table into a digital twin prototype, load the environmental conditions in the multi-dimensional test condition matrix, conduct virtual wind tunnel tests, and obtain initial filtration resistance data; Apply accelerated aging treatment to the digital twin prototype, determine the capture saturation curve through pollutant accumulation calculation, and plot the filtration efficiency decay map; Based on the filtration efficiency decay map, analyze the hygroscopic deformation characteristics of the filter material under different humidity conditions, and construct a humidity response strain map; Combine the humidity response strain map with the initial filtration resistance data, analyze the impact of high-concentration pollutants on the material saturation time, and generate a life prediction data set; Perform boundary condition screening and performance interpolation calculation on the life prediction data set to form a full-condition performance curve set.

7. The intelligent design method of filter bags based on artificial intelligence according to claim 1, wherein Precisely convert and verify the filter bag material formula, structural dimensions, and production process parameters based on the full-condition performance curve set to obtain a filter bag design scheme that can be directly used for production, including: Perform reverse analysis on the material performance indicators in the full-condition performance curve set through a material formula parser to determine the material composition ratio relationship and generate a material formula list; Evaluate the availability of the formula items in the material formula list, match the existing supplier resource library, and form a material procurement parameter table; Extract key structural dimension data based on the corresponding relationship between the multi-layer composite filtration structure configuration table and the full-condition performance curve set, and construct a manufacturing dimension specification card; Convert the manufacturing dimension specification card into production equipment parameters, determine the equipment adjustment parameters through process adaptability analysis, and form a process flow instruction set; Use the process flow instruction set to conduct small-batch trial production of filter bag samples, collect actual production deviation data, and establish a process correction factor table; Fine-tune and verify the material formula list and the manufacturing dimension specification card based on the process correction factor table, and integrate them to form a filter bag design scheme that can be directly used for production.

8. An intelligent design system for filter bags based on artificial intelligence, which is used to implement the intelligent design method for filter bags based on artificial intelligence as described in any one of claims 1-7, characterized in that, The filter bag intelligent design system based on artificial intelligence includes: A collection module for multi-dimensionally collecting the particle size distribution and adsorption characteristics of indoor air pollutants through a pollutant particle dynamic capture device to obtain a pollutant characteristic digital fingerprint library; A quantification module for accurately quantifying the porosity, active site distribution, and surface charge of the filter material using a material micro-permeability measuring instrument based on the pollutant characteristic digital fingerprint library to obtain a multi-dimensional material performance matrix; A calculation module for parametric modeling and airflow distribution calculation of the filter bag fold angle, depth, and density based on the multi-dimensional material performance matrix to obtain a self-balanced fold structure parameter group; An adjustment module for optimizing and adjusting the combination order, thickness ratio, and contact interface of different material layers of the filter bag according to the self-balanced fold structure parameter group to obtain a multi-layer composite filtration structure configuration table; A test module for simulating and testing the filtration efficiency and service life of the filter bag in a high-humidity and high-concentration pollutant environment using the multi-layer composite filtration structure configuration table to obtain a full-condition performance curve set; A verification module is used to accurately convert and verify the filter bag material formula, structural dimensions, and production process parameters according to the full-condition performance curve set, and obtain a filter bag design scheme that can be directly used for production.

9. A computer device, characterized in that, It includes a memory and a processor. The memory stores a computer program that can run on the processor. It is characterized in that when the processor executes the computer program, it implements the artificial intelligence-based intelligent filter bag design method described in any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the processor is caused to execute the artificial intelligence-based intelligent filter bag design method described in any one of claims 1 to 7.

Images