Search

CN-121979157-A - Production control method and system for fiber filter material

CN121979157ACN 121979157 ACN121979157 ACN 121979157ACN-121979157-A

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 a system. The method comprises the steps of raw material pretreatment, environment parameter monitoring, intelligent production parameter adjustment, fiber forming and detection, product packaging and storage, wherein a production parameter and product performance relation model is established through an improved particle swarm optimization-multiple linear regression algorithm, a process is adjusted in real time according to the environment and the production parameter, and online detection of optimized parameters is combined. The system correspondingly comprises pretreatment, environment monitoring, central control, equipment control, molding detection and packaging storage units. The method and the system improve the performance accuracy and the production stability of the product, optimize the production efficiency, and are suitable for high-efficiency and high-quality production of various fiber filter materials.

Inventors

  • XU YANLEI
  • Zhu Cuilian

Assignees

  • 深圳市瀚溢晟科技有限公司

Dates

Publication Date
20260505
Application Date
20260209

Claims (5)

  1. 1. A method for controlling the production of a fibrous filter material, comprising the steps of: Step 1, preparing raw materials, namely selecting fiber raw materials which meet the performance requirements of target filter materials, determining parameters including but not limited to the types, the lengths and the diameters of fibers, cleaning and drying the fiber raw materials to remove impurities and ensure the consistency of the raw materials; Setting a plurality of environment monitoring points in a production workshop, monitoring temperature, humidity and air pressure environment parameters in real time, and transmitting monitoring data to a central control system in real time; step3, intelligent production parameter adjustment: Establishing a production parameter model, namely establishing a relation model between production parameters of the fiber filter material and product performances by adopting an improved particle swarm optimization-multiple linear regression algorithm through preset experiment and historical production data: wherein Is used as a performance index of the product, For the feed rate of the fibers, In order to achieve the spinning pressure, In order to achieve the molding temperature, In order to shape the humidity of the product, Is the temperature of a workshop, the temperature of the workshop, Is the humidity of the workshop, and the humidity of the workshop, Is the air pressure of a workshop, the air pressure is the air pressure of the workshop, As the coefficient of regression of the coefficient of the data, Is a constant term; Coefficient and constant terms The influence degree of each parameter on the product performance is reflected by fitting experimental data; Real-time data analysis, namely, a central control system receives environment parameter monitoring data and current production parameter data fed back by production equipment in real time, and calculates predicted values of product performance under the current environment parameter and the production parameter according to the established production parameter model And, at the same time, setting target value of product performance Predetermined according to different application requirements; deviation calculation and adjustment decision, calculating predicted value And target value Deviation between According to the deviation And the weight of the influence of each production parameter on the product performance, namely regression coefficient Determining production parameters to be adjusted and adjusting directions and amplitudes thereof; The production parameter adjustment is executed, namely a determined production parameter adjustment instruction is sent to corresponding production equipment, so that the real-time adjustment of the production parameter is realized, and the product performance is ensured to be close to a target value; Step 4, fiber forming and detection, wherein fiber forming operation is carried out according to the adjusted production parameters, and fiber filtering materials are manufactured through spinning, lapping and consolidation processes; the method comprises the steps of carrying out real-time online detection on the produced fiber filter material, wherein detection items comprise, but are not limited to, fiber distribution uniformity, pore size, distribution and filtering efficiency; And 5, packaging and storing the products, namely packaging the qualified fiber filtering materials, selecting preset packaging materials and packaging modes to prevent the products from being damaged in the transportation and storage processes, storing the packaged products under proper environmental conditions, and recording the batch, production time and performance parameter information of the products so as to trace and manage.
  2. 2. The method of claim 1, wherein in the environmental parameter monitoring step, 5 environmental monitoring points are set at different positions of a fiber feeding area, a spinning area and a forming area of a production workshop, each monitoring point is provided with a temperature, humidity and air pressure sensor, the sensors collect data once every 1 minute, and the data are transmitted to a central control system in real time through a wireless communication module.
  3. 3. The method for controlling the production of a fibrous filter material according to claim 1, wherein in said step 3 Coefficient and constant terms The specific acquisition steps are as follows: step S1, initializing a particle group: Determining the particle dimension, wherein each particle represents a group of regression coefficients and constant terms, namely the particle dimension is 8, respectively corresponding to And ; Setting the particle quantity to be Each particle has an initial position and an initial speed in 8-dimensional space, the initial positions are randomly generated in a reasonable range, ( ) At an initial value of Is randomly generated in the process of the method, At an initial value of Randomly generate, the initial speed is at Setting at random; step S2, defining a fitness function: taking the MSE of the predicted value and the actual value as the fitness function, and setting experimental data to be provided with Group of the first Group data, actual product performance index is The predicted value calculated according to the position of the current particle, namely the regression coefficient and the constant term is: wherein , , , , , , Respectively the first Fiber feed rate, spinning pressure, forming temperature, forming humidity, workshop temperature, workshop humidity and workshop air pressure in the group data, then the fitness function The smaller the fitness value is, the more accurate the regression coefficient and constant term represented by the current particle can describe the relation between the production parameter and the product performance; step S3, iterative updating of particle swarm: Updating the individual extremum and the global extremum, namely, for each particle, recording the fitness value of the current position of the particle as the individual extremum And finding out the particle with the smallest fitness value among all the particles, and taking the position of the particle as a global extremum ; Speed and position update-each particle updates its speed and position according to the following formula: the speed update formula: wherein Is the first The particles are at the first The first iteration The speed of the dimension is such that, Corresponding to And ; For inertial weight, global and local search capabilities for balancing particles, initially set to 0.7, and progressively decrease with iteration number, 10 times per iteration, But not less than 0.4; And Setting 1.5 as learning factors, and respectively adjusting the step sizes of the particles moving to the individual extremum and the global extremum; And Is at Random numbers in between; Is the first The particles are at the first The first iteration The individual extremum positions of the dimension; Is the first The first iteration Global extremum position of dimension; Is the first The particles are at the first The first iteration Position of dimension, position update formula: boundary processing, namely if the updated position of the particle exceeds the set range Beyond the limit of , Beyond the limit of Then adjusting its position to a boundary value; step S4, judging termination conditions: Setting the maximum iteration number Terminating the iteration when the iteration number reaches the maximum iteration number or the change of the global extremum of 10 continuous iterations is smaller than a preset minimum value; step S5, determining regression coefficients and constant terms: After the iteration is terminated, the global extremum The corresponding position is the regression coefficient And constant term 。
  4. 4. The method of claim 1, wherein in the step of forming and detecting the fibers, the fibers are sprayed out by a melt-blown spinning process, uniformly laid on a lapping device, then consolidated and formed in a hot-press consolidation device, the pore size and distribution of the fiber filtering material are detected in real time by using a laser particle size analyzer, the filtering efficiency is detected by using a permeability tester, and the uniformity of the fiber distribution is observed by using a microscope.
  5. 5. A production control system for a fibrous filter material, applied to a production control method for a fibrous filter material according to any one of claims 1 to 4, comprising: The raw material pretreatment unit is used for selecting fiber raw materials which meet the performance requirements of target filter materials, determining parameters of the types, the lengths and the diameters of the fibers, and cleaning and drying the fiber raw materials; The environmental parameter monitoring unit is used for setting a plurality of environmental monitoring points in the production workshop, monitoring environmental parameters such as temperature, humidity, air pressure and the like in real time and transmitting monitoring data to the central control unit in real time; The central control unit comprises a model building module, a data analysis module and a data analysis module, wherein the model building module is used for building a relation model between production parameters and product performances of the fiber filter material by adopting an improved particle swarm optimization-multiple linear regression algorithm through preset experiment and historical production data, and the data analysis module is used for receiving environment parameter monitoring data and current production parameter data fed back by production equipment in real time and calculating predicted values of the current environment parameters and the product performances under the production parameters And set target value of product performance A decision-making module is regulated to calculate the predicted value And target value Deviation between According to the deviation And the weight of the influence of each production parameter on the product performance, namely regression coefficient The instruction sending module is used for sending the determined production parameter adjustment instruction to a corresponding production equipment control unit; The production equipment control unit is used for adjusting parameters of the fiber feeding device, the pressure of the spinning equipment, the temperature and humidity control device of the forming equipment according to the adjustment instruction sent by the central control unit; The fiber forming and detecting unit is used for performing fiber forming operation according to the adjusted production parameters to prepare a fiber filtering material, performing real-time online detection on the fiber filtering material, wherein the detection items comprise fiber distribution uniformity, pore size, distribution and filtering efficiency, and feeding back detection data to the central control unit; And the product packaging and storing unit is used for packaging the qualified fiber filtering material, selecting proper packaging materials and packaging modes, storing the packaged product under proper environmental conditions, and recording the batch, production time and performance parameter information of the product.

Description

Production control method and system for fiber filter material Technical Field The invention relates to the field related to production of fiber filter materials, in particular to a production control method and a production control system of a fiber filter material. Background There are currently some significant problems in the production of fibrous filter materials. On the one hand, the uniformity of the distribution of the fibers is difficult to control precisely, which can lead to a large difference in the filtration performance of the filter material in different areas. For example, in air filtration applications, certain regions may filter well, while other regions may not be effective in blocking particulate matter, reducing overall filtration efficiency. On the other hand, the dynamic response to environmental factors (e.g., temperature, humidity) during production is inadequate. The fluctuation of the environmental conditions can influence the physical properties and the forming effect of the fiber, but the existing production control method can not adjust the production parameters according to the environmental change in time, so that the quality of the product is unstable. In addition, the traditional method is not accurate enough for controlling the pore size distribution of the fiber filter material, and can not meet the strict requirements of different application scenes on the filter pore size. Disclosure of Invention The present invention is directed to a method and a system for controlling the production of a fibrous filter material, which solve the above-mentioned problems. In order to achieve the above purpose, the invention provides a production control method of a fiber filter material, which comprises the following steps: Step 1, preparing raw materials, namely selecting fiber raw materials which meet the performance requirements of target filter materials, determining parameters including but not limited to the types, the lengths and the diameters of fibers, cleaning and drying the fiber raw materials to remove impurities and ensure the consistency of the raw materials; Setting a plurality of environment monitoring points in a production workshop, monitoring temperature, humidity and air pressure environment parameters in real time, and transmitting monitoring data to a central control system in real time; step3, intelligent production parameter adjustment: establishing a production parameter model, namely establishing a relation model between production parameters and product performances of the fiber filter material by adopting an improved particle swarm optimization-multiple linear regression algorithm (PSO-MLR) through preset experiment and historical production data: wherein Is used as a performance index of the product,For the feed rate of the fibers,In order to achieve the spinning pressure,In order to achieve the molding temperature,In order to shape the humidity of the product,Is the temperature of a workshop, the temperature of the workshop,Is the humidity of the workshop, and the humidity of the workshop,Is the air pressure of a workshop, the air pressure is the air pressure of the workshop,As the coefficient of regression of the coefficient of the data,Is a constant term; Coefficient and constant terms The influence degree of each parameter on the product performance is reflected by fitting experimental data; Real-time data analysis, namely, a central control system receives environment parameter monitoring data and current production parameter data fed back by production equipment in real time, and calculates predicted values of product performance under the current environment parameter and the production parameter according to the established production parameter model And, at the same time, setting target value of product performancePredetermined according to different application requirements; deviation calculation and adjustment decision, calculating predicted value And target valueDeviation betweenAccording to the deviationAnd the weight of the influence of each production parameter on the product performance, namely regression coefficientAnd determining the production parameters to be adjusted and the adjustment direction and the adjustment amplitude thereof. For example, ifIndicating that the predicted performance is lower than the target performance, based on the production parameter model analysis, if(Fiber feed speed)Is positive), indicating that increasing the fiber feed rate may improve product performance, then increasing the fiber feed rate appropriately. The adjustment amplitude is determined according to the deviation and the adjustable range of the production parameter, and the adjustment amplitude coefficient is set as,The range of the values is as followsAmount of adjustment of the fiber feeding speed(WhenWhen, at that time); the production parameter adjustment is executed, namely, a determined production parameter adjustment instruction is sent to c