Production control method and system of fiber filter material

Abstract

The invention relates to the field of fiber filter material production, aims to solve the problems of inaccurate product performance control and unstable quality in traditional production, and provides a production control method and system. The method comprises the steps of raw material pretreatment, environmental parameter monitoring, intelligent production parameter adjustment, fiber forming and detection and product packaging and storage. A production parameter and product performance relation model is established through an improved particle swarm optimization-multiple linear regression algorithm, the process is adjusted in real time according to environment and production parameters, and the parameters are optimized in combination with online detection. The system correspondingly comprises a pretreatment unit, an environment monitoring unit, a central control unit, an equipment control unit, a forming detection unit and a packaging storage unit. According to the method and system, the product performance accuracy and production stability are improved, the production efficiency is optimized, and the method and system are suitable for efficient and high-quality production of various fiber filtering materials.

Description

Technical Field

[0001] This invention relates to the field of fiber filter material production, specifically to a production control method and system for fiber filter materials. Background Technology

[0002] Several significant problems currently exist in the production process of fiber filter materials. On the one hand, the uniformity of fiber distribution is difficult to control precisely, leading to significant differences in filtration performance across different areas of the filter material. For example, in air filtration applications, some areas may perform well while others may fail to effectively block particulate matter, reducing overall filtration efficiency. On the other hand, the production process suffers from insufficient dynamic response to environmental factors (such as temperature and humidity). Fluctuations in environmental conditions affect the physical properties and molding effect of the fibers, but existing production control methods fail to adjust production parameters in a timely manner according to environmental changes, resulting in unstable product quality. Furthermore, traditional methods are not precise enough in controlling the pore size distribution of fiber filter materials, failing to meet the stringent requirements for pore size in different application scenarios. Summary of the Invention

[0003] The purpose of this invention is to provide a production control method and system for fiber filter materials to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a production control method for fiber filter materials, comprising the following steps: Step 1: Raw material preparation: Select fiber raw materials that are suitable for the performance requirements of the target filter material, determine the fiber type, length, and diameter parameters, and pre-treat the fiber raw materials by cleaning and drying to remove impurities and ensure the consistency of the raw materials; Step 2, Environmental Parameter Monitoring: Set up multiple environmental monitoring points in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control system in real time; Step 3: Adjusting intelligent production parameters: Establish a production parameter model: Based on pre-set experiments and historical production data, an improved particle swarm optimization-multiple linear regression (PSO-MLR) algorithm is used to establish a model of the relationship between the production parameters of fiber filter materials and product performance. ,in For product performance indicators, For fiber feed rate, The spinneret pressure, For molding temperature, For molding humidity, For workshop temperature, For workshop humidity, For workshop air pressure, For regression coefficients, For constant terms; Coefficients and constant terms The results, obtained by fitting the experimental data, reflect the degree of influence of each parameter on product performance. Real-time data analysis: The central control system receives real-time environmental parameter monitoring data and current production parameter data fed back from production equipment; based on the established production parameter model, it calculates predicted values ​​of product performance under the current environmental and production parameters. At the same time, set target values ​​for product performance. It is determined in advance according to different application requirements; Deviation Calculation and Adjustment Decision: Calculating Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. Determine the production parameters that need to be adjusted, as well as the direction and magnitude of such adjustments. For example, if This indicates that the predicted performance is lower than the target performance. Based on the production parameter model analysis, if... (fiber feed rate) If the coefficient is positive, it indicates that increasing the fiber feed rate may improve product performance; therefore, the fiber feed rate should be increased appropriately. The adjustment range is determined based on the magnitude of the deviation and the adjustable range of the production parameters. Let the adjustment range coefficient be... , The range of values ​​is The adjustment amount of the fiber feed rate (when hour); Production parameter adjustment execution: The determined production parameter adjustment instructions are sent to the corresponding production equipment, such as adjusting the speed of the fiber feeding device, the pressure of the spinning equipment, and the temperature and humidity control devices of the forming equipment, so as to realize the real-time adjustment of production parameters and ensure that the product performance is close to the target value. Step 4, Fiber Forming and Inspection: Perform fiber forming operation according to the adjusted production parameters, and produce fiber filter material through spinning, web laying and consolidation processes; perform real-time online inspection on the produced fiber filter material, and the inspection items include but are not limited to fiber distribution uniformity, pore size and distribution, and filtration efficiency; feed the inspection data back to the central control system, and if the inspection results do not meet the requirements, repeat the steps of the intelligent production parameter adjustment module in Step 3 above to further optimize the production parameters; Step 5, Product Packaging and Storage: Pack the qualified fiber filter materials, selecting preset packaging materials and methods to prevent damage during transportation and storage; store the packaged products under suitable environmental conditions, and record the batch number, production time, and performance parameter information of the products for traceability and management.

[0005] Preferably, in the environmental parameter monitoring step, five environmental monitoring points are set at different locations in the fiber feeding area, spinning area, and forming area of ​​the production workshop. Each monitoring point is equipped with temperature, humidity, and air pressure sensors. The sensors collect data once every minute and transmit the data to the central control system in real time through a wireless communication module.

[0006] Preferably, in step 3 Coefficients and constant terms The specific steps to obtain it are as follows: Step S1: Initialize the particle swarm: Determine the particle dimension: Each particle represents a set of regression coefficients and constant terms, i.e., the particle dimension is 8, corresponding to... and ; Set the number of particles: Set the number of particles to... Each particle has an initial position and an initial velocity in 8-dimensional space; the initial position is randomly generated within a reasonable range. ( The initial value of ) is in Randomly generated between The initial value is in Randomly generated between, with an initial velocity of Internal random setting; Step S2: Define the fitness function: The mean squared error (MSE) between predicted and actual values ​​is used as the fitness function; assuming the experimental data are... Group, for the first The data set shows that the actual product performance indicators are... The predicted value, calculated based on the current particle position (i.e., the regression coefficients and constant term), is: ,in , , , , , , The first The data set includes fiber feed rate, spinneret pressure, forming temperature, forming humidity, workshop temperature, workshop humidity, and workshop air pressure; then the fitness function... The smaller the fitness value, the more accurately the regression coefficients and constants represented by the current particle can describe the relationship between production parameters and product performance. Step S3, Particle Swarm Iterative Update: Individual Extrema and Global Extrema Update: For each particle, record its current fitness value as the individual extrema. Among all particles, find the particle with the smallest fitness value, and take its position as the global extreme value. ; Velocity and position update: Each particle updates its velocity and position according to the following formula: Speed ​​update formula: ,in It is the first The particle in the first During the nth iteration Dimensional speed, ,correspond and ; This is the inertial weight, used to balance the global and local search capabilities of particles. It is initially set to 0.7 and gradually decreases with each iteration, with a maximum value every 10 iterations. But not less than 0.4; and The learning factor is set to 1.5, which respectively adjusts the step size of the particle moving towards the individual extremum and the global extremum; and Is Random numbers between; It is the first The particle in the first During the nth iteration The location of the individual extreme value in dimension; It is the first During the nth iteration The location of the global extremum in dimension; It is the first The particle in the first During the nth iteration The position of the dimension; the position update formula: Boundary handling: If the updated position of a particle exceeds the set range, i.e. Exceeding , Exceeding If so, then adjust its position to the boundary value; Step S4: Termination condition determination: Set the maximum number of iterations (For example The iteration terminates when the number of iterations reaches the maximum number of iterations, or when the change in the global extremum is less than a preset minimum value (e.g., 10⁻⁶) after 10 consecutive iterations. Step S5: Determine the regression coefficients and constant term: After the iteration terminates, the global extremum The corresponding position is the regression coefficient we are looking for. and constant term These coefficients and constants can more accurately reflect the relationship between production parameters and product performance. Compared with the traditional multiple linear regression method, the introduction of particle swarm optimization algorithm avoids local optima, improves the accuracy and reliability of the model, and provides a more accurate basis for subsequent intelligent production parameter adjustment.

[0007] Preferably, in the fiber forming and testing steps, the fibers are sprayed out by meltblown spinning process, uniformly laid on a web-laying device, and then consolidated in a hot-pressing consolidation device. A laser particle size analyzer is used to detect the pore size and distribution of the fiber filter material in real time, an air permeability tester is used to test the filtration efficiency, and a microscope is used to observe the uniformity of fiber distribution.

[0008] Preferably, a production control system for fiber filter materials includes: Raw material pretreatment unit: used to select fiber raw materials that meet the performance requirements of the target filter material, determine the type, length and diameter parameters of the fiber, and pretreat the fiber raw materials by cleaning and drying; Environmental parameter monitoring unit: Multiple environmental monitoring points are set up in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control unit in real time; Central Control Unit: Model Building Module: Utilizes pre-set experiments and historical production data, employing an improved particle swarm optimization-multiple linear regression algorithm to establish a model relating fiber filter material production parameters to product performance; Data Analysis Module: Receives real-time environmental parameter monitoring data and current production parameter data from production equipment, calculating predicted product performance values ​​under the current environmental and production parameters. And set target values ​​for product performance. Adjustment Decision Module: Calculates Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. The module determines the production parameters that need to be adjusted, as well as the direction and magnitude of the adjustment; the instruction sending module sends the determined production parameter adjustment instructions to the corresponding production equipment control unit. Production equipment control unit: Adjusts the speed of the fiber feeding device, the pressure of the spinneret, and the parameters of the temperature and humidity control devices of the forming equipment according to the adjustment instructions sent by the central control unit; Fiber forming and testing unit: Performs fiber forming operation according to the adjusted production parameters to produce fiber filter material, and performs real-time online testing on it. The testing items include fiber distribution uniformity, pore size and distribution, and filtration efficiency. The test data is fed back to the central control unit. Product Packaging and Storage Unit: Pack the qualified fiber filter materials, select appropriate packaging materials and methods, store the packaged products under suitable environmental conditions, and record the batch, production time, and performance parameter information of the products.

[0009] Compared with the prior art, the beneficial effects of the present invention are: Precise control of product performance: By establishing a production parameter model and adjusting the production parameters in real time, this invention can precisely control the performance of fiber filter materials, ensuring that the product meets strict requirements in terms of fiber distribution uniformity, pore size distribution, and filtration efficiency.

[0010] Improved production stability: This invention monitors environmental parameters in real time and adjusts production parameters promptly based on their changes, enhancing the adaptability of the production process to environmental fluctuations and improving the stability of product quality.

[0011] Optimize production efficiency: The intelligent production parameter adjustment module of this invention can quickly respond to changes in the production process, reduce production stagnation and product defects caused by unreasonable parameters, and improve production efficiency. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the intelligent production parameter adjustment workflow of the present invention; Figure 3 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] Please see Figure 1-3 This invention provides a technical solution: a production control method for fiber filter materials, comprising the following steps: Step 1: Raw material preparation: Select fiber raw materials that are suitable for the performance requirements of the target filter material, determine the fiber type, length, and diameter parameters, and pre-treat the fiber raw materials by cleaning and drying to remove impurities and ensure the consistency of the raw materials; Step 2, Environmental Parameter Monitoring: Set up multiple environmental monitoring points in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control system in real time; Step 3: Adjusting intelligent production parameters: Establish a production parameter model: Based on pre-set experiments and historical production data, an improved particle swarm optimization-multiple linear regression (PSO-MLR) algorithm is used to establish a model of the relationship between the production parameters of fiber filter materials and product performance. ,in For product performance indicators, For fiber feed rate, The spinneret pressure, For molding temperature, For molding humidity, For workshop temperature, For workshop humidity, For workshop air pressure, For regression coefficients, For constant terms; Coefficients and constant terms The results, obtained by fitting the experimental data, reflect the degree of influence of each parameter on product performance. Real-time data analysis: The central control system receives real-time environmental parameter monitoring data and current production parameter data fed back from production equipment; based on the established production parameter model, it calculates predicted values ​​of product performance under the current environmental and production parameters. At the same time, set target values ​​for product performance. It is determined in advance according to different application requirements; Deviation Calculation and Adjustment Decision: Calculating Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. Determine the production parameters that need to be adjusted, as well as the direction and magnitude of such adjustments. For example, if This indicates that the predicted performance is lower than the target performance. Based on the production parameter model analysis, if... (fiber feed rate) If the coefficient is positive, it indicates that increasing the fiber feed rate may improve product performance; therefore, the fiber feed rate should be increased appropriately. The adjustment range is determined based on the magnitude of the deviation and the adjustable range of the production parameters. Let the adjustment range coefficient be... , The range of values ​​is The adjustment amount of the fiber feed rate (when hour); Production parameter adjustment execution: The determined production parameter adjustment instructions are sent to the corresponding production equipment, such as adjusting the speed of the fiber feeding device, the pressure of the spinning equipment, and the temperature and humidity control devices of the forming equipment, so as to realize the real-time adjustment of production parameters and ensure that the product performance is close to the target value. Step 4, Fiber Forming and Inspection: Perform fiber forming operation according to the adjusted production parameters, and produce fiber filter material through spinning, web laying and consolidation processes; perform real-time online inspection on the produced fiber filter material, and the inspection items include but are not limited to fiber distribution uniformity, pore size and distribution, and filtration efficiency; feed the inspection data back to the central control system, and if the inspection results do not meet the requirements, repeat the steps of the intelligent production parameter adjustment module in Step 3 above to further optimize the production parameters; Step 5, Product Packaging and Storage: Pack the qualified fiber filter materials, selecting preset packaging materials and methods to prevent damage during transportation and storage; store the packaged products under suitable environmental conditions, and record the batch number, production time, and performance parameter information of the products for traceability and management.

[0015] Furthermore, in the environmental parameter monitoring step, five environmental monitoring points are set up at different locations in the fiber feeding area, spinning area, and forming area of ​​the production workshop. Each monitoring point is equipped with temperature, humidity, and air pressure sensors. The sensors collect data every minute and transmit the data to the central control system in real time through a wireless communication module.

[0016] Furthermore, in step 3 Coefficients and constant terms The specific steps to obtain it are as follows: Step S1: Initialize the particle swarm: Determine the particle dimension: Each particle represents a set of regression coefficients and constant terms, i.e., the particle dimension is 8, corresponding to... and ; Set the number of particles: Set the number of particles to... Each particle has an initial position and an initial velocity in 8-dimensional space; the initial position is randomly generated within a reasonable range. ( The initial value of ) is in Randomly generated between The initial value is in Randomly generated between, with an initial velocity of Internal random setting; Step S2: Define the fitness function: The mean squared error (MSE) between predicted and actual values ​​is used as the fitness function; assuming the experimental data are... Group, for the first The data set shows that the actual product performance indicators are... The predicted value, calculated based on the current particle position (i.e., the regression coefficients and constant term), is: ,in , , , , , , The first The data set includes fiber feed rate, spinneret pressure, forming temperature, forming humidity, workshop temperature, workshop humidity, and workshop air pressure; then the fitness function... The smaller the fitness value, the more accurately the regression coefficients and constants represented by the current particle can describe the relationship between production parameters and product performance. Step S3, Particle Swarm Iterative Update: Individual Extrema and Global Extrema Update: For each particle, record its current fitness value as the individual extrema. Among all particles, find the particle with the smallest fitness value, and take its position as the global extreme value. ; Velocity and position update: Each particle updates its velocity and position according to the following formula: Speed ​​update formula: ,in It is the first The particle in the first During the nth iteration Dimensional speed, ,correspond and ; This is the inertial weight, used to balance the global and local search capabilities of particles. It is initially set to 0.7 and gradually decreases with each iteration, with a maximum value every 10 iterations. But not less than 0.4; and The learning factor is set to 1.5, which respectively adjusts the step size of the particle moving towards the individual extremum and the global extremum; and Is Random numbers between; It is the first The particle in the first During the nth iteration The location of the individual extreme value in dimension; It is the first During the nth iteration The location of the global extremum in dimension; It is the first The particle in the first During the nth iteration The position of the dimension; the position update formula: Boundary handling: If the updated position of a particle exceeds the set range, i.e. Exceeding , Exceeding If so, then adjust its position to the boundary value; Step S4: Termination condition determination: Set the maximum number of iterations (For example The iteration terminates when the number of iterations reaches the maximum number of iterations, or when the change in the global extremum is less than a preset minimum value (e.g., 10⁻⁶) after 10 consecutive iterations. Step S5: Determine the regression coefficients and constant term: After the iteration terminates, the global extremum The corresponding position is the regression coefficient we are looking for. and constant term These coefficients and constants can more accurately reflect the relationship between production parameters and product performance. Compared with the traditional multiple linear regression method, the introduction of particle swarm optimization algorithm avoids local optima, improves the accuracy and reliability of the model, and provides a more accurate basis for subsequent intelligent production parameter adjustment.

[0017] Furthermore, in the fiber forming and testing steps, the fibers are sprayed out through meltblown spinning process, uniformly laid on a web-laying device, and then consolidated and formed in a hot-pressing consolidation device. A laser particle size analyzer is used to detect the pore size and distribution of the fiber filter material in real time, an air permeability tester is used to test the filtration efficiency, and a microscope is used to observe the uniformity of fiber distribution.

[0018] Furthermore, a production control system for fiber filter materials includes: Raw material pretreatment unit: used to select fiber raw materials that meet the performance requirements of the target filter material, determine the type, length and diameter parameters of the fiber, and pretreat the fiber raw materials by cleaning and drying; Environmental parameter monitoring unit: Multiple environmental monitoring points are set up in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control unit in real time; Central Control Unit: Model Building Module: Utilizes pre-set experiments and historical production data, employing an improved particle swarm optimization-multiple linear regression algorithm to establish a model relating fiber filter material production parameters to product performance; Data Analysis Module: Receives real-time environmental parameter monitoring data and current production parameter data from production equipment, calculating predicted product performance values ​​under the current environmental and production parameters. And set target values ​​for product performance. Adjustment Decision Module: Calculates Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. The module determines the production parameters that need to be adjusted, as well as the direction and magnitude of the adjustment; the instruction sending module sends the determined production parameter adjustment instructions to the corresponding production equipment control unit. Production equipment control unit: Adjusts the speed of the fiber feeding device, the pressure of the spinneret, and the parameters of the temperature and humidity control devices of the forming equipment according to the adjustment instructions sent by the central control unit; Fiber forming and testing unit: Performs fiber forming operation according to the adjusted production parameters to produce fiber filter material, and performs real-time online testing on it. The testing items include fiber distribution uniformity, pore size and distribution, and filtration efficiency. The test data is fed back to the central control unit. Product Packaging and Storage Unit: Pack the qualified fiber filter materials, select appropriate packaging materials and methods, store the packaged products under suitable environmental conditions, and record the batch, production time, and performance parameter information of the products.

[0019] This invention relates to the field of fiber filter material production, aiming to solve the problems of inaccurate product performance control and unstable quality in traditional production, and to provide a production control method and system.

[0020] The method includes raw material pretreatment, environmental parameter monitoring, intelligent production parameter adjustment, fiber forming and testing, and product packaging and storage steps. An improved particle swarm optimization-multiple linear regression algorithm is used to establish a model of the relationship between production parameters and product performance. The process is adjusted in real time based on environmental and production parameters, and parameters are optimized through online detection. The system includes pretreatment, environmental monitoring, central control, equipment control, forming and testing, and packaging and storage units.

[0021] This method and system improve product performance accuracy and production stability, optimize production efficiency, and are suitable for the efficient and high-quality production of various fiber filter materials.

[0022] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for controlling the production of a fiber filter material, characterized in that, Includes the following steps: Step 1: Raw material preparation: Select fiber raw materials that are suitable for the performance requirements of the target filter material, determine the fiber type, length, and diameter parameters, and pre-treat the fiber raw materials by cleaning and drying to remove impurities and ensure the consistency of the raw materials; Step 2, Environmental Parameter Monitoring: Set up multiple environmental monitoring points in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control system in real time; Step 3: Adjusting intelligent production parameters: Establish a production parameter model: Based on pre-set experiments and historical production data, an improved particle swarm optimization-multiple linear regression algorithm is used to establish a model of the relationship between the production parameters of fiber filter materials and product performance. ,in For product performance indicators, For fiber feed rate, The spinneret pressure, For molding temperature, For molding humidity, For workshop temperature, For workshop humidity, For workshop air pressure, For regression coefficients, For constant terms; Coefficients and constant terms The results, obtained by fitting the experimental data, reflect the degree of influence of each parameter on product performance. Real-time data analysis: The central control system receives real-time environmental parameter monitoring data and current production parameter data fed back from production equipment; based on the established production parameter model, it calculates predicted values ​​of product performance under the current environmental and production parameters. At the same time, set target values ​​for product performance. It is determined in advance according to different application requirements; Deviation Calculation and Adjustment Decision: Calculating Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. Determine the production parameters that need to be adjusted, as well as the direction and magnitude of the adjustment; Production parameter adjustment execution: The determined production parameter adjustment instructions are sent to the corresponding production equipment to realize the real-time adjustment of production parameters, so as to ensure that the product performance is close to the target value; Step 4, Fiber Forming and Inspection: Perform fiber forming operation according to the adjusted production parameters, and produce fiber filter material through spinning, web laying and consolidation processes; perform real-time online inspection on the produced fiber filter material, and the inspection items include but are not limited to fiber distribution uniformity, pore size and distribution, and filtration efficiency; feed the inspection data back to the central control system, and if the inspection results do not meet the requirements, repeat the steps of the intelligent production parameter adjustment module in Step 3 above to further optimize the production parameters; Step 5, Product Packaging and Storage: Pack the qualified fiber filter materials, selecting preset packaging materials and methods to prevent damage during transportation and storage; store the packaged products under suitable environmental conditions, and record the batch number, production time, and performance parameter information of the products for traceability and management.

2. The production control method for a fiber filter material according to claim 1, characterized in that: In the environmental parameter monitoring step, five environmental monitoring points are set up at different locations in the fiber feeding area, spinning area, and forming area of ​​the production workshop. Each monitoring point is equipped with temperature, humidity, and air pressure sensors. The sensors collect data every minute and transmit the data to the central control system in real time through a wireless communication module.

3. The production control method for a fiber filter material according to claim 1, characterized in that: In step 3 Coefficients and constant terms The specific steps to obtain it are as follows: Step S1: Initialize the particle swarm: Determine the particle dimension: Each particle represents a set of regression coefficients and constant terms, i.e., the particle dimension is 8, corresponding to... and ; Set the number of particles: Set the number of particles to... Each particle has an initial position and an initial velocity in 8-dimensional space; the initial position is randomly generated within a reasonable range. ( The initial value of ) is in Randomly generated between The initial value is in Randomly generated between, with an initial velocity of Internal random setting; Step S2: Define the fitness function: The mean squared error (MSE) between predicted and actual values ​​is used as the fitness function; assuming the experimental data are... Group, for the first The data set shows that the actual product performance indicators are... The predicted value, calculated based on the current particle position (i.e., the regression coefficients and constant term), is: ,in , , , , , , The first The data set includes fiber feed rate, spinneret pressure, forming temperature, forming humidity, workshop temperature, workshop humidity, and workshop air pressure; then the fitness function... The smaller the fitness value, the more accurately the regression coefficients and constants represented by the current particle can describe the relationship between production parameters and product performance. Step S3, Particle Swarm Iterative Update: Individual Extrema and Global Extrema Update: For each particle, record its current fitness value as the individual extrema. Among all particles, find the particle with the smallest fitness value, and take its position as the global extreme value. ; Velocity and position update: Each particle updates its velocity and position according to the following formula: Speed ​​update formula: ,in It is the first The particle in the first During the nth iteration Dimensional speed, ,correspond and ; This is the inertial weight, used to balance the global and local search capabilities of particles. It is initially set to 0.7 and gradually decreases with each iteration, with a maximum value every 10 iterations. But not less than 0.4; and The learning factor is set to 1.5, which respectively adjusts the step size of the particle moving towards the individual extremum and the global extremum; and Is Random numbers between; It is the first The particle in the first During the nth iteration The location of the individual extreme value in dimension; It is the first During the nth iteration The location of the global extremum in dimension; It is the first The particle in the first During the nth iteration The position of the dimension; the position update formula: Boundary handling: If the updated position of a particle exceeds the set range, i.e. Exceeding , Exceeding If so, then adjust its position to the boundary value; Step S4: Termination condition determination: Set the maximum number of iterations The iteration is terminated when the maximum number of iterations is reached, or when the change in the global extremum is less than a preset minimum value after 10 consecutive iterations. Step S5: Determine the regression coefficients and constant term: After the iteration terminates, the global extremum The corresponding position is the regression coefficient we are looking for. and constant term .

4. The production control method for a fiber filter material according to claim 1, characterized in that: In the fiber forming and testing steps, the fibers are sprayed out through meltblown spinning process, uniformly laid on a web-laying device, and then consolidated and formed in a hot-pressing consolidation device. A laser particle size analyzer is used to detect the pore size and distribution of the fiber filter material in real time, an air permeability tester is used to test the filtration efficiency, and a microscope is used to observe the uniformity of fiber distribution.

5. A production control system for fiber filter materials, applied to the production control method for a fiber filter material as described in any one of claims 1-4, characterized in that, include: Raw material pretreatment unit: used to select fiber raw materials that meet the performance requirements of the target filter material, determine the type, length and diameter parameters of the fiber, and pretreat the fiber raw materials by cleaning and drying; Environmental parameter monitoring unit: Multiple environmental monitoring points are set up in the production workshop to monitor environmental parameters such as temperature, humidity, and air pressure in real time, and transmit the monitoring data to the central control unit in real time; Central Control Unit: Model Building Module: Utilizes pre-set experiments and historical production data, employing an improved particle swarm optimization-multiple linear regression algorithm to establish a model relating fiber filter material production parameters to product performance; Data Analysis Module: Receives real-time environmental parameter monitoring data and current production parameter data from production equipment, calculating predicted product performance values ​​under the current environmental and production parameters. And set target values ​​for product performance. ; Adjustment Decision Module: Calculates Predicted Values With target value Deviation between According to the deviation And the weights of each production parameter on product performance, i.e., regression coefficients. The module determines the production parameters that need to be adjusted, as well as the direction and magnitude of the adjustment; the instruction sending module sends the determined production parameter adjustment instructions to the corresponding production equipment control unit. Production equipment control unit: Adjusts the speed of the fiber feeding device, the pressure of the spinneret, and the parameters of the temperature and humidity control devices of the forming equipment according to the adjustment instructions sent by the central control unit; Fiber forming and testing unit: Performs fiber forming operation according to the adjusted production parameters to produce fiber filter material, and performs real-time online testing on it. The testing items include fiber distribution uniformity, pore size and distribution, and filtration efficiency. The test data is fed back to the central control unit. Product Packaging and Storage Unit: Pack the qualified fiber filter materials, select appropriate packaging materials and methods, store the packaged products under suitable environmental conditions, and record the batch, production time, and performance parameter information of the products.

Images