Anti-static dust-free clothing micro-pollution blocking regulation and control system based on static electricity distribution prediction

Abstract

The invention relates to the technical field of computer simulation, in particular to an anti-static dust-free clothing micro-pollution blocking regulation and control system based on static electricity distribution prediction, which comprises a static electricity data acquisition module for acquiring various data of a working environment and a dust-free clothing surface to construct first static electricity monitoring characteristic parameters; the electrostatic simulation module comprises a simulation unit and a prediction unit, and the simulation unit obtains second electrostatic monitoring characteristic parameters through a multi-dimensional data space clustering analysis method according to the change rule and characteristic parameter joint probability distribution of the collected first electrostatic monitoring characteristic parameters and in combination with an electrostatic physical model and environmental parameters; the prediction unit processes the second electrostatic monitoring characteristic parameter based on a mathematical model and a simulation method to obtain an electrostatic distribution prediction result; the micro-pollution prediction module is used for dynamically predicting and dividing the static electricity distribution prediction result according to the collected micro-pollution data to obtain a micro-pollution distribution area set; according to the dust-free clothes data and the first static monitoring characteristic parameters, micro-pollution blocking in the area is carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of computer simulation, and in particular to an anti-static cleanroom clothing micro-pollution blocking and control system based on static electricity distribution prediction. Background Art

[0002] Static electricity, a common physical effect, is prevalent in industrial production, power systems, aerospace, and other fields. Its hazards involve multiple aspects such as equipment safety, personnel protection, and system reliability. For example, in substations, transient currents generated by static electricity induced by the human body or equipment may interfere with electronic equipment or cause safety accidents. In pneumatic conveying systems, the accumulation of static electricity caused by particle friction may reduce conveying efficiency or cause fire hazards. Traditional static electricity monitoring methods often rely on finite element simulation or fixed sensors, which have problems such as low computational efficiency, poor real-time performance, and insufficient adaptability. Especially in complex electromagnetic environments or dynamic working conditions, it is difficult to accurately capture static electricity characteristics and achieve effective early warning.

[0003] Electrostatic discharge not only damages sensitive equipment, but also easily absorbs tiny particles in the air, causing pollution problems. In a high-requirement clean environment, even tiny pollution may lead to reduced product quality, equipment failure, and even process interruption. Especially in the semiconductor and precision manufacturing fields, micro-pollution is considered a major risk factor.

[0004] In recent years, with the rapid development of technologies such as machine learning and neural networks, electrostatic monitoring and prediction methods have gradually developed in the direction of intelligence and multi-dimensionality. Methods based on state-space models, grey correlation analysis and deep learning can integrate multi-source monitoring data and explore the correlation between electrostatic parameters and system performance; combining field-circuit joint simulation with closed-loop iterative optimization can improve the model's adaptability to dynamic environments; and the electric field strength and potential distribution can be calculated through three-dimensional simulation models and finite element methods. However, existing technologies still face problems such as insufficient extraction of electrostatic signal features and insufficient accuracy in multi-factor coupling predictions. In particular, further breakthroughs are needed in real-time monitoring, cross-scenario generalization and closed-loop feedback mechanisms. How to build an efficient and accurate electrostatic prediction and micro-pollution blocking system remains a key challenge in current research.

[0005] Therefore, an anti-static cleanroom clothing micro-pollution blocking and control system based on static electricity distribution prediction was proposed. Summary of the Invention

[0006] The object of the present invention is to provide an anti-static and dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction. The system collects various data of the working environment and the surface of the dust-free clothing through an electrostatic data acquisition module to construct a first electrostatic monitoring characteristic parameter. The electrostatic simulation module includes a simulation unit and a prediction unit. The simulation unit analyzes the variation law of the first electrostatic monitoring characteristic parameter and the joint probability distribution of the characteristic parameters collected, combines the electrostatic physical model and environmental parameters through a multi-dimensional data space clustering analysis method to obtain a second electrostatic monitoring characteristic parameter. The prediction unit processes the second electrostatic monitoring characteristic parameter based on a mathematical model and a simulation method to obtain an electrostatic distribution prediction result. The micro-pollution prediction module dynamically predicts and divides the electrostatic distribution prediction result according to the collected micro-pollution data to obtain a set of micro-pollution distribution regions, and blocks micro-pollution within the region according to the dust-free clothing data and the first electrostatic monitoring characteristic parameter.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An anti-static and dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction, comprising:

[0009] An electrostatic data acquisition module, which collects various data of the working environment and the surface of the dust-free clothing in real time through several types of sensors to construct a first electrostatic monitoring characteristic parameter;

[0010] Further, the electrostatic data acquisition module includes several types of sensor arrays. The sensor array includes a charge quantity detection unit, an environmental parameter sensing unit, and a device state perception unit. Among them, the charge quantity detection unit collects the charge accumulation amount and distribution position on the surface of the dust-free clothing and the device shell in real time. The environmental parameter sensing unit monitors the temperature, humidity, air pressure, gas flow rate, and air particle concentration in the working area. The device state perception unit captures the motion acceleration and vibration frequency of the operating device through an inertial measurement element;

[0011] Further, the collected sensing data is processed to construct a first electrostatic monitoring characteristic parameter. The first electrostatic monitoring characteristic parameter includes an environmental monitoring characteristic parameter and a dust-free clothing monitoring characteristic parameter. Among them, the environmental monitoring characteristic parameter includes the temperature, humidity, and air particle concentration of the working environment. The dust-free clothing monitoring characteristic parameter includes the surface resistance from surface to surface, the resistance from surface to ground point, the surface potential, and the fabric capacitance.

[0012] The electrostatic simulation module includes a simulation unit and a prediction unit. The simulation unit analyzes the variation law of the first electrostatic monitoring characteristic parameter and the joint probability distribution of the characteristic parameters collected, combines the electrostatic physical model and environmental parameters through a multi-dimensional data space clustering analysis method to obtain a second electrostatic monitoring characteristic parameter. The prediction unit processes the second electrostatic monitoring characteristic parameter based on a mathematical model and a simulation method to obtain an electrostatic distribution prediction result;

[0013] Further, the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters are segmented into a number of corresponding monitoring characteristic parameter pairs according to the collection time; the multi-dimensional data space clustering analysis method includes data dimensionality reduction, clustering analysis, and dynamic correlation analysis;

[0014] Further, the simulation unit uses the multi-dimensional data space clustering analysis method to perform data dimensionality reduction and clustering analysis on the monitoring characteristic parameter pairs, and performs dynamic correlation analysis according to the time series to obtain the joint probability distribution of the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters; through Monte Carlo simulation under environmental parameter constraints, the monitoring characteristic parameter pairs and the joint probability distribution of the characteristic parameters are mapped to a three-dimensional characteristic space to generate the second electrostatic monitoring characteristic parameters including the spatial gradient distribution and the risk probability.

[0015] Further, the prediction unit establishes an electrostatic diffusion partial differential equation model including the second environmental monitoring characteristic parameters based on the finite element numerical simulation and the stochastic process theory; the second electrostatic monitoring characteristic parameters are converted into a grid simulation input to the electrostatic diffusion partial differential equation model through a discretization method, and the implicit difference algorithm is used to iteratively solve the electrostatic potential field distribution; the boundary conditions are dynamically adjusted in combination with the environmental parameters, and the electrostatic distribution prediction results including the spatial electric potential gradient, the charge density, and the discharge probability are output.

[0016] The micro-pollution prediction module dynamically predicts and divides the electrostatic distribution prediction results according to the collected micro-pollution data to obtain a set of micro-pollution distribution regions; micro-pollution blocking within the region is performed according to the cleanroom suit data and the first electrostatic monitoring characteristic parameters.

[0017] Further, the collected micro-pollution data includes air particle monitoring data, air microorganism monitoring data, surface pollution monitoring data, and chemical pollution monitoring data;

[0018] Further, the micro-pollution prediction module performs data fusion on the micro-pollution data and the electrostatic distribution prediction results on a unified spatial grid based on the weight assignment rules of the pollution concentration gradient and the discharge probability through spatial overlay analysis to obtain a pollution-electrostatic coupling index, and divides the pollution-electrostatic coupling index through an adaptive threshold to dynamically divide a set of micro-pollution distribution regions including different micro-pollution severity levels.

[0019] Further, the data of the anti-static cleanroom suit in the working environment during the working state is obtained in real time through the wearing state monitoring unit, and the cleanroom suit data is constructed, including static data and dynamic data, where the static data includes the material dielectric constant, the surface resistivity, the wearing fit degree, and the local friction coefficient, and the dynamic data includes the cleanroom suit positioning data, the electrostatic decay time, the surface potential, and the discharge current;

[0020] Furthermore, the collected cleanroom suit data is processed and cleaned to construct a micro-pollution blocking and regulation vector.

[0021] Furthermore, according to the position of the anti-static cleanroom suit in the set of micro-pollution distribution regions, the data of the corresponding micro-pollution distribution region is obtained, including the space electric potential gradient, charge density, discharge probability, and pollution-electrostatic coupling index, and a micro-pollution blocking and regulation evaluation vector is constructed.

[0022] Furthermore, the difference between the real-time micro-pollution blocking and regulation evaluation vector and the micro-pollution blocking and regulation evaluation vector of the corresponding micro-pollution distribution region in the electrostatic-free state in the historical data is calculated, and the micro-pollution blocking and regulation vector is adjusted according to the difference.

[0023] Furthermore, after obtaining the difference, the micro-pollution blocking and regulation vector is corrected online according to the difference combined with the mapping rule; through the closed-loop feedback mechanism, the charge state on the surface of the cleanroom suit and the environmental sensing data are continuously read, and a new difference is calculated for correction to achieve the coordinated blocking of the pollution diffusion path and the electrostatic risk area.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0025] 1. Dynamic correlation analysis further captures the mutations and coupling evolutions of parameters in time series, enhancing the sensitivity to sudden electrostatic disturbances; the Monte Carlo simulation under environmental parameter constraints can fully quantify the input uncertainties, approximate the joint probability distribution through a large number of random samplings, and make the prediction results have a reliable risk probability assessment; the gradient distribution and risk probability generated after mapping the monitoring feature pairs and their joint probability distribution to the three-dimensional feature space can not only intuitively reflect the spatial hot spot layout but also support refined decision-making, which helps to deploy anti-static strategies according to local conditions.

[0026] 2. By superimposing and analyzing multi-source data of air particles, microorganisms, surface and chemical pollution and the electrostatic distribution prediction results in the same spatial grid, multi-level spatial coupling can be achieved, and the spatial distribution laws of pollution and static electricity can be intuitively revealed; a pollution-electrostatic coupling index is constructed based on the weight distribution rule of pollution concentration gradient and discharge probability, which can quantify the interaction intensity between the two and provide a quantitative basis for risk assessment; by segmenting the pollution-electrostatic coupling index with an adaptive threshold, different pollution severity levels can be reflected, and the micro-pollution distribution regions can be accurately divided.

[0027] 3. By calculating the difference between the real-time micro-pollution blocking and regulation evaluation vector and the corresponding area in the historical electrostatic-free state, the system can quantify the deviation amplitude of the current blocking effect from the ideal state. Based on the driving update mechanism of this difference, the blocking control vector can be adaptively optimized to make the strategy continuously fit the current pollution distribution and static charge state, significantly improving the system response speed and sensitivity. Using the gradient descent algorithm to iteratively optimize the blocking strategy combination can efficiently converge to the optimal electrostatic discharge and pollution path blocking measures, minimizing the decision-making time. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 FIG. is a schematic structural diagram of the anti-static dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction provided by an embodiment of the present invention;

[0029] Figure 2 FIG. is a flowchart of obtaining the second electrostatic monitoring characteristic parameter provided by an embodiment of the present invention;

[0030] Figure 3 FIG. is a schematic structural diagram of obtaining the set of micro-pollution distribution areas provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] By predicting electrostatic hotspots and electrostatic accumulation areas, potential electrostatic discharge risks can be identified in advance, providing a basis for targeted design of protection measures. This is particularly important in fields with high environmental cleanliness requirements such as clean rooms, electronic manufacturing, semiconductors, and biomedicine, because electrostatic discharge not only damages sensitive equipment but also easily adsorbs tiny particles in the air, thus causing pollution problems.

[0033] Micro-pollution refers to extremely fine particles, microorganisms, organic or inorganic microparticles and other pollutants existing in the environment. The sources of such pollutants are extensive, including human exfoliated dander, clothing fibers or dust generated during the processing process. Due to the electrostatic adsorption effect, particles from the surrounding air are more likely to accumulate at electrostatic hotspots. A semiconductor manufacturing company introduced the anti-static dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction provided by the present invention to customize anti-static dust-free clothing. The system structure is as Figure 1 shown, and the specific implementation method is as follows:

[0034] The static electricity data acquisition module collects various data of the working environment and the surface of the cleanroom suit in real time through several types of sensors, and constructs the first static electricity monitoring characteristic parameters;

[0035] Further, the static electricity data acquisition module includes several types of sensor arrays. The sensor array includes a charge quantity detection unit, an environmental parameter sensing unit, and a device state perception unit. Among them, the charge quantity detection unit collects the charge accumulation amount and distribution position on the surface of the cleanroom suit and the device shell in real time; the environmental parameter sensing unit monitors the temperature, humidity, air pressure, gas flow rate, and the concentration of fine particles in the air in the working area; the device state perception unit captures the motion acceleration and vibration frequency of the operating device through inertial measurement elements;

[0036] Further, the collected sensing data is processed to construct the first static electricity monitoring characteristic parameters. The first static electricity monitoring characteristic parameters include environmental monitoring characteristic parameters and cleanroom suit monitoring characteristic parameters. Among them, the environmental monitoring characteristic parameters include the temperature, humidity, and the concentration of fine particles in the air in the working environment, and the cleanroom suit monitoring characteristic parameters include the surface-to-surface surface resistance, the surface-to-grounding point resistance, the surface potential, and the fabric capacitance. Table 1 shows some of the collected data.

[0037] Table 1. Some collected data

[0038]

[0039] Through the static electricity accumulation, electrical, and motion data collected by the three types of sensing units, namely the charge quantity detection unit, the environmental parameter sensing unit, and the device state perception unit, the system can comprehensively and accurately collect the static charge distribution, resistance characteristics, and dynamic working conditions of the surface of the cleanroom suit, the working environment, and the device shell, significantly improving the sensitivity and reliability of static electricity anomaly detection.

[0040] The static electricity simulation module includes a simulation unit and a prediction unit. The simulation unit obtains the second static electricity monitoring characteristic parameters through multi-dimensional data space clustering analysis of the variation law of the first static electricity monitoring characteristic parameters and the joint probability distribution of the characteristic parameters, combined with the static electricity physical model and environmental parameters; the prediction unit processes the second static electricity monitoring characteristic parameters based on the mathematical model and simulation method to obtain the static electricity distribution prediction result;

[0041] Further, the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters are divided into several corresponding pairs of monitoring characteristic parameters according to the collection time; the multi-dimensional data space clustering analysis method includes data dimensionality reduction, clustering analysis, and dynamic correlation analysis;

[0042] Further, the simulation unit uses a multi-dimensional data space clustering analysis method to perform data dimensionality reduction and clustering analysis on the pairs of monitored characteristic parameters, and conducts dynamic correlation analysis based on the time series to obtain the joint probability distribution of the environmental monitoring characteristic parameters and the cleanroom clothing monitoring characteristic parameters; through Monte Carlo simulation under environmental parameter constraints, the pairs of monitored characteristic parameters and the joint probability distribution of characteristic parameters are mapped to a three-dimensional characteristic space to generate the second electrostatic monitoring characteristic parameter including the spatial gradient distribution and the risk probability.

[0043] Further, first, the environmental monitoring characteristic parameters and the cleanroom clothing monitoring characteristic parameters are segmented into several corresponding pairs of monitored characteristic parameters according to the acquisition time to ensure a one-to-one mapping relationship between the environmental and clothing states at the same time point or within the same time window. This time series segmentation method based on a sliding window or moment-by-moment pairing is a common practice in time series data mining and helps with subsequent correlation analysis and feature comparison.

[0044] Further, in the multi-dimensional data space clustering analysis method, first, data dimensionality reduction needs to be performed on the high-dimensional pairs of monitored characteristic parameters. A common solution is to combine principal component analysis and K-means clustering, and optimize the dimensionality reduction space through iterative feedback so that the low-dimensional representation can retain the maximum variance information and enhance the cluster separation; subsequently, clustering analysis is carried out. The subspace clustering algorithm can be used to discover local groups in the subspace after dimensionality reduction, or methods such as density-based DBSCAN can be used to identify non-convex cluster structures; finally, through dynamic correlation analysis, the cluster labels obtained in consecutive time windows are matched, and combined with dynamic time warping or cross-correlation analysis methods to capture the coupled evolution of the environmental monitoring characteristic parameters and the cleanroom clothing monitoring characteristic parameters over time.

[0045] Further, based on the above multi-dimensional clustering results, the simulation unit obtains the joint probability distribution of the environmental monitoring characteristic parameters and the cleanroom clothing monitoring characteristic parameters through the cluster center trajectory and similarity measure of the time series. This process is equivalent to constructing a distribution estimation model of multivariate random variables in the characteristic space and can quantify the joint variation characteristics of the two under different working conditions.

[0046] Further, then under the constraints of environmental parameters (such as temperature, humidity, air flow rate), Monte Carlo simulation is used to perform large-scale random sampling on the pairs of monitored characteristic parameters and their joint probability distribution. By repeatedly generating sample vectors that conform to this joint distribution and inputting them into the electrostatic simulation model, the samples generated by Monte Carlo are mapped to a three-dimensional characteristic space, and the electrostatic potential gradient and the corresponding risk probability are calculated at each grid point to form the second electrostatic monitoring characteristic parameter including the spatial gradient distribution of the electric potential and the risk probability, making the high-dimensional complex data intuitive and operable in visualization and control decision-making. Table 2 shows the second electrostatic monitoring characteristic parameters at some positions, and the overall process is as Figure 2 shown.

[0047] Table 2, Second Electrostatic Monitoring Feature Parameters

[0048] Three-dimensional feature space position Spatial gradient of electric potential (V / cm) Risk probability (0.8,-0.2,1.5) 0.50 0.06 (0.9,-0.3,1.6) 0.55 0.05 (-0.5,1.2,0.1) 0.14 0.02 (1.1,-0.5,1.9) -0.23 0.04

[0049] Dynamic correlation analysis further captures the abrupt changes and coupled evolutions of parameters over time, enhancing the sensitivity to sudden electrostatic disturbances; Monte Carlo simulation under environmental parameter constraints can fully quantify the input uncertainties, approximate the joint probability distribution through a large number of random samplings, and enable the prediction results to have a reliable risk probability assessment; the gradient distribution and risk probability generated after mapping the monitoring feature pairs and their joint probability distribution to a three-dimensional feature space can not only intuitively reflect the spatial hot spot layout but also support refined decision-making, contributing to the layout control of anti-static strategies according to local conditions.

[0050] The prediction unit establishes a partial differential equation model of electrostatic diffusion containing environmental monitoring feature parameters based on finite element numerical simulation and stochastic process theory; converts the second electrostatic monitoring feature parameters into grid-based simulations through discretization methods, inputs them into the partial differential equation model of electrostatic diffusion, and uses the implicit difference algorithm to iteratively solve the electrostatic potential field distribution; dynamically adjusts the boundary conditions in combination with environmental parameters, and outputs the electrostatic distribution prediction results including spatial electric potential gradient, charge density, and discharge probability.

[0051] By introducing environmental monitoring feature parameters into the partial differential equation model of electrostatic diffusion and combining finite element numerical simulation, the system can accurately characterize the electrostatic potential field distribution under complex geometries and multi-physical field coupling conditions; modeling the diffusion equation using stochastic process theory can fully reflect the randomness and uncertainty brought by environmental disturbances and material heterogeneity; using the implicit difference algorithm to iteratively solve can achieve unconditional stability, support fast simulations with larger time steps, and significantly improve the computational efficiency and numerical robustness. The final output of high-precision prediction results such as spatial electric potential gradient, charge density, and discharge probability provides a scientific basis for the refined deployment of micro-pollution blocking strategies.

[0052] The micro-pollution prediction module dynamically predicts and divides the electrostatic distribution prediction results based on the collected micro-pollution data to obtain a set of micro-pollution distribution regions; performs micro-pollution blocking within the regions according to the cleanroom suit data and the first electrostatic monitoring feature parameters.

[0053] Furthermore, the collected micro-pollution data includes air particle monitoring data, air microorganism monitoring data, surface pollution monitoring data, and chemical pollution monitoring data;

[0054] Further, the micro-pollution prediction module performs data fusion on the micro-pollution data and the electrostatic distribution prediction results on a unified spatial grid based on the weight assignment rules of pollution concentration gradient and discharge probability through spatial overlay analysis, obtaining a pollution-electrostatic coupling index. The pollution-electrostatic coupling index is segmented by an adaptive threshold to dynamically divide the set of micro-pollution distribution regions containing different micro-pollution severity levels. The specific process is as Figure 3 shown.

[0055] Further, the micro-pollution monitoring data and the electrostatic distribution prediction results are resampled to the same grid cells, and then data fusion is performed according to the pollution concentration gradient, the discharge probability of the electrostatic distribution prediction results, and the corresponding weights. The formula is:

[0056]

[0057] where K ij represents the coupling index, Q represents the types of micro-pollution data, ω q represents the weight coefficient of the q-th type of micro-pollution data, represents the Euclidean norm of the pollution gradient of the q-th type of micro-pollution data in the grid cell at the (i, j) position, max||C q || represents the maximum value of the gradients of the q-th type of micro-pollution data in all grid cells, ω represents the weight coefficient of the discharge probability, and R ij represents the discharge probability of the grid cell at the (i, j) position.

[0058] Further, to distinguish the high-coupling area from the low-coupling area, an adaptive threshold segmentation algorithm is used to dynamically calculate the threshold according to the mean and standard deviation of the coupling index within the neighborhood of each grid cell. The adaptive threshold can overcome the failure problem of the global threshold under non-uniform backgrounds and maintain the segmentation accuracy.

[0059] Further, 4-neighborhood (or 8-neighborhood) connectivity detection is performed to identify several connected sub-regions, and each sub-region is a micro-pollution distribution region.

[0060] By performing overlay analysis on multi-source data of air particles, microorganisms, surface, and chemical pollution and the electrostatic distribution prediction results in the same spatial grid, multi-level spatial coupling can be achieved, intuitively revealing the co-occurrence pattern and spatial distribution law of pollution and static electricity; constructing a pollution-electrostatic coupling index based on the weight assignment rules of pollution concentration gradient and discharge probability can quantify the interaction strength between the two, providing a quantitative basis for risk assessment; segmenting the pollution-electrostatic coupling index by an adaptive threshold can reflect different pollution severity levels and accurately divide the micro-pollution distribution regions.

[0061] Further, the data of the anti-static cleanroom suit in the working environment during the working state is obtained in real time by the wearing state monitoring unit, and the cleanroom suit data is constructed, including static data and dynamic data, where the static data includes material dielectric constant, surface resistivity, wearing conformity, and local friction coefficient, and the dynamic data includes cleanroom suit positioning data, electrostatic decay time, surface potential, and discharge current;

[0062] Further, the collected cleanroom suit data is processed and cleaned to construct a micro-pollution blocking regulation vector.

[0063] Further, the collected cleanroom suit data is subjected to time series synchronization and denoising, outlier detection, and feature normalization processing. The cleaned static and dynamic features are concatenated into a high-dimensional vector, and the high-dimensional vector is mapped to a low-dimensional regulation subspace using PCA or Autoencoder to obtain a micro-pollution blocking regulation vector, which is convenient for online calculation and strategy matching.

[0064] By real-time fusing features such as the static and dynamic electrical and positioning data of the cleanroom suit, the system can not only comprehensively characterize the anti-static performance of the anti-static cleanroom suit in the actual working environment, but also generate an accurate micro-pollution blocking regulation vector after data cleaning and high-dimensional vectorization, significantly improving the sensitivity of the model to the coupling risk of static electricity and particles.

[0065] Further, according to the position of the anti-static cleanroom suit in the set of micro-pollution distribution regions, the data of the corresponding micro-pollution distribution region is obtained, including spatial electric potential gradient, charge density, discharge probability, and pollution-static electricity coupling index, and a micro-pollution blocking regulation evaluation vector is constructed;

[0066] Further, the difference between the real-time micro-pollution blocking regulation evaluation vector and the micro-pollution blocking regulation evaluation vector of the corresponding micro-pollution distribution region in the historical data under the static electricity-free state is calculated, and the micro-pollution blocking regulation vector is adjusted according to the difference;

[0067] Further, through a closed-loop feedback mechanism, the surface charge state of the cleanroom suit is matched with the change of environmental parameters in real time, and the gradient descent algorithm is used to optimize the blocking strategy combination to achieve the collaborative blocking of the pollution diffusion path and the electrostatic risk area.

[0068] Further, according to the position of the anti-static cleanroom suit in the set of micro-pollution distribution regions, the spatial electric potential gradient, charge density, discharge probability, and pollution-static electricity coupling index within the grid cell are obtained, and a micro-pollution blocking regulation evaluation vector is constructed through vector concatenation. This evaluation vector integrates a large amount of data and provides a comprehensive state description for subsequent difference calculation and control optimization.

[0069] Further, after obtaining the difference, according to the difference and in combination with the mapping rule, the micro-pollution blocking regulation vector is corrected online. The system, through a closed-loop feedback mechanism, continuously reads the charge state on the surface of the cleanroom suit and environmental sensing data, and calculates a new difference for correction; the mapping rule refers to finding the correction data in the historical data according to the real-time micro-pollution blocking regulation evaluation vector and performing correction. The search method can be based on the similarity degree between data, the similarity degree between events, and the similarity degree of data in space.

[0070] By calculating the difference between the real-time micro-pollution blocking regulation evaluation vector and the corresponding area in the historical electrostatic non-disturbance state, the system can quantify the amplitude of the current blocking effect deviating from the ideal state. This difference-based driving update mechanism can adaptively optimize the blocking control vector, making the strategy continuously fit the normal pollution distribution and static charge state, and significantly improving the system response speed and sensitivity; using the gradient descent algorithm to iteratively optimize the blocking strategy combination can efficiently converge to the optimal electrostatic discharge and pollution path blocking measures, minimizing the decision-making time.

[0071] Through the anti-static cleanroom suit micro-pollution blocking regulation system based on electrostatic distribution prediction provided by the present invention, the electrostatic acquisition module realizes the accurate acquisition of data and constructs the first electrostatic monitoring characteristic parameters, achieving the preprocessing of data; the electrostatic simulation module realizes the construction of the electrostatic model through the simulation of data, and realizes the prediction of the electrostatic distribution through the prediction unit, providing data support for subsequent micro-pollution blocking; the micro-pollution prediction module combines the electrostatic distribution prediction result and the collected micro-pollution data, divides the micro-pollution distribution area, and performs micro-pollution blocking, improving the accuracy of blocking and shortening the blocking time.

[0072] Embodiment 2:

[0073] An electronic component company introduced the anti-static cleanroom suit micro-pollution blocking regulation system based on electrostatic distribution prediction provided by the present invention to prevent static electricity and micro-pollution. The specific implementation method is as follows:

[0074] The electrostatic data acquisition module continuously acquires various data of the working environment and the surface of the cleanroom suit through several types of sensors, and constructs the first electrostatic monitoring characteristic parameters;

[0075] Further, the electrostatic data acquisition module includes several types of sensor arrays. The sensor array includes a charge amount detection unit, an environmental parameter sensing unit, and a device state perception unit; among them, the charge amount detection unit continuously acquires the charge accumulation amount and distribution position on the surface of the cleanroom suit and the device shell; the environmental parameter sensing unit monitors the temperature, humidity, air pressure, gas flow rate, and particle concentration in the working area; the device state perception unit captures the motion acceleration and vibration frequency of the operating device through inertial measurement elements;

[0076] Table 3, Partial Collected Data

[0077]

[0078] Further, the collected sensing data is processed to construct the first electrostatic monitoring characteristic parameters, which include environmental monitoring characteristic parameters and cleanroom suit monitoring characteristic parameters. Among them, the environmental monitoring characteristic parameters include the temperature, humidity, and airborne particle concentration of the working environment, and the cleanroom suit monitoring characteristic parameters include the surface resistance from surface to surface, the resistance from surface to ground, the surface potential, and the fabric capacitance. Shown in Table 3 are some of the collected data.

[0079] The electrostatic simulation module includes a simulation unit and a prediction unit. The simulation unit performs multi-dimensional data space clustering analysis on the variation law of the first electrostatic monitoring characteristic parameters collected and the joint probability distribution of the characteristic parameters, combines the electrostatic physical model and environmental parameters, and obtains the second electrostatic monitoring characteristic parameters; the prediction unit processes the second electrostatic monitoring characteristic parameters based on a mathematical model and a simulation method to obtain the electrostatic distribution prediction result;

[0080] Further, the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters are segmented into several corresponding pairs of monitoring characteristic parameters according to the collection time; the multi-dimensional data space clustering analysis method includes data dimensionality reduction, clustering analysis, and dynamic association analysis;

[0081] Further, the simulation unit uses the multi-dimensional data space clustering analysis method to perform data dimensionality reduction and clustering analysis on the pairs of monitoring characteristic parameters, and performs dynamic association analysis according to the time series to obtain the joint probability distribution of the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters; through Monte Carlo simulation under the constraint of environmental parameters, the pairs of monitoring characteristic parameters and the joint probability distribution of the characteristic parameters are mapped to a three-dimensional characteristic space to generate the second electrostatic monitoring characteristic parameters including the spatial gradient distribution and the risk probability.

[0082] Further, the prediction unit establishes an electrostatic diffusion partial differential equation model including the second environmental monitoring characteristic parameters based on the finite element numerical simulation and the stochastic process theory; the second electrostatic monitoring characteristic parameters are transformed into a grid simulation input for the electrostatic diffusion partial differential equation model through a discretization method, and the implicit difference algorithm is used to iteratively solve the electrostatic potential field distribution; the boundary conditions are dynamically adjusted in combination with the environmental parameters, and the electrostatic distribution prediction result including the spatial electric potential gradient, charge density, and discharge probability is output.

[0083] The micro-pollution prediction module dynamically predicts and divides the electrostatic distribution prediction result according to the collected micro-pollution data to obtain a set of micro-pollution distribution regions; micro-pollution blocking within the region is performed according to the cleanroom suit data and the first electrostatic monitoring characteristic parameters.

[0084] Furthermore, the collected micro-pollution data includes air particle monitoring data, air microorganism monitoring data, surface pollution monitoring data, and chemical pollution monitoring data;

[0085] Table 4. Pollution-electrostatic coupling indicators of some grid cells

[0086] Grid cell number Pollution-electrostatic coupling index (normalized value) Grid-00223 0.75 Grid-01254 0.41 Grid-14983 0.92 Grid-03024 0.80

[0087] Furthermore, the micro-pollution prediction module performs data fusion on the micro-pollution data and the electrostatic distribution prediction results on a unified spatial grid based on the weight assignment rules of pollution concentration gradient and discharge probability through spatial overlay analysis, obtains the pollution-electrostatic coupling indicators, and divides the set of micro-pollution distribution regions containing different micro-pollution severity levels dynamically by segmenting the pollution-electrostatic coupling indicators with an adaptive threshold. Table 4 shows the pollution-electrostatic coupling indicators of some grid cells.

[0088] Furthermore, data of the anti-static cleanroom suit in the working environment during the working state is obtained in real time through the wearing status monitoring unit, and cleanroom suit data is constructed, including static data and dynamic data. The static data includes material dielectric constant, surface resistivity, wearing fit degree, and local friction coefficient, and the dynamic data includes cleanroom suit positioning data, electrostatic decay time, surface potential, and discharge current;

[0089] Furthermore, the collected cleanroom suit data is processed and cleaned to construct a micro-pollution blocking and regulation vector.

[0090] Furthermore, according to the position of the anti-static cleanroom suit in the set of micro-pollution distribution regions, data of the corresponding micro-pollution distribution region is obtained, including spatial electric potential gradient, charge density, discharge probability, and pollution-electrostatic coupling indicators, and a micro-pollution blocking and regulation evaluation vector is constructed; among them, data such as spatial electric potential gradient and charge density can be obtained through the first electrostatic monitoring characteristic parameters.

[0091] Furthermore, the difference between the real-time micro-pollution blocking and regulation evaluation vector and the micro-pollution blocking and regulation evaluation vector of the corresponding micro-pollution distribution region in the historical data under the static electricity-free state is calculated, and the micro-pollution blocking and regulation vector is adjusted according to the difference;

[0092] Furthermore, after obtaining the difference, the micro-pollution blocking and regulation vector is corrected online according to the difference in combination with the mapping rule; through a closed-loop feedback mechanism, the charge state on the surface of the cleanroom suit and the environmental sensing data are continuously read, and a new difference is calculated for correction to achieve the collaborative blocking of the pollution diffusion path and the electrostatic risk region.

[0093] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An anti-static and dust-free clothing micro-pollution blocking and regulation system based on static electricity distribution prediction, characterized in that Comprising: An electrostatic data acquisition module that collects various data on the working environment and the surface of the cleanroom suit in real time through several types of sensors, and constructs the first electrostatic monitoring characteristic parameters; The electrostatic simulation module includes a simulation unit and a prediction unit. The simulation unit performs multi-dimensional data space clustering analysis on the variation law of the first electrostatic monitoring characteristic parameters collected and the joint probability distribution of the characteristic parameters, combines the electrostatic physical model and environmental parameters, and obtains the second electrostatic monitoring characteristic parameters; the prediction unit processes the second electrostatic monitoring characteristic parameters based on a mathematical model and a simulation method to obtain the electrostatic distribution prediction result; A micro-pollution prediction module that dynamically predicts and divides the electrostatic distribution prediction result according to the collected micro-pollution data to obtain a set of micro-pollution distribution regions; and performs micro-pollution blocking within the region according to the cleanroom suit data and the first electrostatic monitoring characteristic parameters.

2. The anti-static cleanroom suit micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, wherein: The electrostatic data acquisition module includes several types of sensor arrays. The sensor array includes a charge quantity detection unit, an environmental parameter sensing unit, and a device state sensing unit; among them, the charge quantity detection unit collects the charge accumulation quantity and distribution position on the surface of the cleanroom suit and the device shell in real time; the environmental parameter sensing unit monitors the temperature, humidity, air pressure, gas flow rate, and air particle concentration in the working area; the device state sensing unit captures the motion acceleration and vibration frequency of the operating device through an inertial measurement element; The collected sensing data is processed to construct the first electrostatic monitoring characteristic parameters. The first electrostatic monitoring characteristic parameters include environmental monitoring characteristic parameters and cleanroom suit monitoring characteristic parameters. Among them, the environmental monitoring characteristic parameters include the temperature, humidity, and air particle concentration in the working environment, and the cleanroom suit monitoring characteristic parameters include the surface resistance from surface to surface, the resistance from surface to ground, the surface potential, and the fabric capacitance.

3. The anti-static cleanroom suit micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, wherein: The environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters are divided into several corresponding monitoring characteristic parameter pairs according to the collection time; the multi-dimensional data space clustering analysis method includes data dimensionality reduction, clustering analysis, and dynamic correlation analysis; The simulation unit uses the multi-dimensional data space clustering analysis method to perform data dimensionality reduction and clustering analysis on the monitoring characteristic parameter pairs, and performs dynamic correlation analysis according to the time series to obtain the joint probability distribution of the characteristic parameters of the environmental monitoring characteristic parameters and the cleanroom suit monitoring characteristic parameters; through Monte Carlo simulation under environmental parameter constraints, the monitoring characteristic parameter pairs and the joint probability distribution of the characteristic parameters are mapped to a three-dimensional characteristic space to generate the second electrostatic monitoring characteristic parameters including the spatial gradient distribution and the risk probability.

4. The anti-static cleanroom suit micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, wherein: Based on finite element numerical simulation and stochastic process theory, the prediction unit establishes a partial differential equation model of electrostatic diffusion containing the second environmental monitoring characteristic parameters; through the discretization method, the second electrostatic monitoring characteristic parameters are transformed into grid-based simulations and input into the partial differential equation model of electrostatic diffusion. The implicit difference algorithm is used to iteratively solve the electrostatic potential field distribution; the boundary conditions are dynamically adjusted in combination with environmental parameters, and the electrostatic distribution prediction results including spatial electric potential gradient, charge density, and discharge probability are output.

5. The anti-static dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, characterized in that: The collected micro-pollution data includes air particle monitoring data, air microorganism monitoring data, surface pollution monitoring data, and chemical pollution monitoring data; The micro-pollution prediction module performs data fusion on the micro-pollution data and the electrostatic distribution prediction results on a unified spatial grid based on the weight distribution rules of pollution concentration gradient and discharge probability through spatial overlay analysis, obtains a pollution-electrostatic coupling index, and divides the pollution-electrostatic coupling index through an adaptive threshold to dynamically divide a set of micro-pollution distribution regions containing different micro-pollution severity levels.

6. The anti-static dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, characterized in that: The data of the anti-static dust-free clothing in the working environment during the working state is obtained in real time through the wearing state monitoring unit, and the dust-free clothing data is constructed, including static data and dynamic data, where the static data includes material dielectric constant, surface resistivity, wearing fit, and local friction coefficient, and the dynamic data includes dust-free clothing positioning data, electrostatic decay time, surface potential, and discharge current; The collected dust-free clothing data is processed and cleaned to construct a micro-pollution blocking and regulation vector.

7. The anti-static dust-free clothing micro-pollution blocking and regulation system based on electrostatic distribution prediction according to claim 1, characterized in that: According to the position of the anti-static dust-free clothing in the set of micro-pollution distribution regions, the data of the corresponding micro-pollution distribution region is obtained, including spatial electric potential gradient, charge density, discharge probability, and pollution-electrostatic coupling index, and a micro-pollution blocking and regulation evaluation vector is constructed; Calculate the difference between the real-time micro-pollution blocking and regulation evaluation vector and the micro-pollution blocking and regulation evaluation vector of the corresponding micro-pollution distribution region in the historical data under the static electricity-free state, and adjust the micro-pollution blocking and regulation vector according to the difference; After obtaining the difference, the micro-pollution blocking and regulation vector is corrected online based on the difference in combination with the mapping rule; through a closed-loop feedback mechanism, continuously read the charge state on the surface of the dust-free clothing and environmental sensing data, and calculate a new difference for correction to achieve the coordinated blocking of the pollution diffusion path and the electrostatic risk region.

Images