Fuzzy optimization method and system for multivariable coordinated control of sterilization bag production

Abstract

This invention discloses a fuzzy optimization method and system for multivariate coordinated control in the production of disinfection bags, relating to the field of disinfection bag production control technology. The method includes: dynamic adjustment of raw material ratios, collecting parameters according to material requirements, and adjusting mixing uniformity and humidity; coordination of extrusion molding parameters, setting and dynamically correcting temperature benchmarks, and adjusting screw speed, die pressure, and clearance; synchronous control of the printing process, setting speeds according to pattern complexity, and adjusting registration deviation, ink viscosity, and drying parameters; coordinated bag forming, matching cutting and printing speeds, and controlling heat-sealing parameters and cutting deviations; multivariate fuzzy optimization, constructing a four-dimensional model, and updating rule weights; closed-loop quality feedback, detecting and optimizing parameters; and dynamic energy consumption balance, collecting data and optimizing energy consumption. This invention improves the stability and efficiency of disinfection bag production quality, reduces energy consumption, enhances adaptability, meets high-standard production requirements, and is highly practical.

Description

Technical Field

[0001] This invention relates to the field of disinfection bag production control technology, and in particular to a fuzzy optimization method and system for multivariate coordinated control of disinfection bag production. Background Technology

[0002] Sterilization bags play an irreplaceable role in medical sterilization and food preservation, and their quality directly affects medical safety and food hygiene. Currently, the production process of sterilization bags faces challenges such as complex multi-variable coupling and difficulty in parameter control. Traditional production methods rely on manual experience to set raw material ratios, extrusion temperatures, and heat-sealing parameters. When raw material batches change or environmental temperature and humidity fluctuate, parameter adjustments lag, easily leading to fluctuations in product quality. For example, excessive humidity in polyethylene raw materials can cause air bubbles in the extruded film, and manual humidity testing often lags by more than 30 minutes, resulting in batches of substandard products.

[0003] Existing automated production line control methods have limitations, often employing simple single-input, single-output control that neglects the interrelationships between variables. In the extrusion process, die pressure is affected by multiple factors, including screw speed, raw material melt index, and temperature in different sections. Simply adjusting the speed is insufficient to stabilize the pressure, leading to film thickness deviations exceeding twice the standard value. In the printing process, registration errors are corrected only through real-time feedback, without considering the film's elongation at different temperatures. This results in lag in adjustment response and a persistently high pattern misalignment rate. Furthermore, the coupling relationship between heat-sealing strength and temperature, pressure, and time is complex. Fixed parameter settings cannot adapt to materials of different thicknesses, frequently resulting in inadequate heat sealing or film burn-through.

[0004] With increasing market demands for the quality of sterilization bags, medical sterilization bags must meet stringent requirements such as a heat-sealing strength of ≥15N / 15mm and a leak-free seal under 0.05MPa negative pressure for 30 seconds. Existing technologies struggle to balance multi-process parameters and rely on crude energy control, often resulting in excessive energy consumption to ensure quality, with unit product energy consumption 15%-20% higher than industry standards. Furthermore, the lack of a dynamic optimization mechanism necessitates shutdowns for adjustments when production conditions change, leading to a 10%-15% reduction in production efficiency. Therefore, a control method capable of coordinating multiple variables and dynamically optimizing parameters is urgently needed to address the problems of unstable quality, high energy consumption, and poor adaptability in sterilization bag production. Summary of the Invention

[0005] The present invention proposes a fuzzy optimization method and system for multivariate coordinated control in the production of disinfection bags, in order to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a fuzzy optimization method for multivariate coordinated control of disinfection bag production, comprising: Dynamic adjustment steps for raw material ratio: According to the material requirements of the disinfection bag, collect parameters such as raw material moisture, particle size, and melt index; establish a raw material characteristic database containing processing compatibility data of 50 raw material combinations; start pre-drying treatment when the moisture content of a batch of raw materials exceeds 8%; analyze the mixing uniformity of raw materials in real time using an online near-infrared spectrometer, and adjust the stirring speed and extend the stirring time when the uniformity is lower than 95%; Extrusion molding parameter coordination steps: Set the temperature baseline values ​​for each section of the extruder and dynamically correct them according to the melt flow index of the raw material: for every 0.5 g / 10 min increase in melt flow index, the metering section temperature decreases by 5℃; use a variable frequency motor to control the screw speed, with the initial speed set at 1.2 times the raw material flow rate; monitor the die pressure in real time, and when the pressure fluctuation exceeds ±0.5 MPa, adjust the screw speed and die temperature synchronously to maintain pressure stability; use a laser thickness gauge to detect the film thickness, and adjust the die clearance when the thickness deviation exceeds ±0.005 mm. The printing process is controlled synchronously as follows: a printing speed baseline is set based on the complexity of the printed pattern on the disinfection bag; a photoelectric sensor is used to detect the printing registration deviation, and when the lateral deviation exceeds 0.1mm or the longitudinal deviation exceeds 0.2mm, the servo motor is activated to adjust the position of the printing roller; the ink viscosity is monitored in real time, and the ink temperature is adjusted or thinner is added every 5 seconds when the viscosity deviates from the baseline value; after printing, the clarity of the pattern is checked through a visual inspection system, and when the proportion of blurred areas exceeds 2%, the printing speed is reduced by 10% and the drying temperature is increased by 5℃.

[0007] Bag forming coordination steps: Set the bag making machine cutting speed according to the size of the sterilization bag to match the previous printing speed; adopt coordinated control of heat sealing temperature and pressure, and set the heat sealing time according to the material thickness; detect the heat sealing strength through a tensile sensor. If it is lower than 10N / 15mm, increase the heat sealing temperature by 5℃ and extend the heat sealing time by 0.1s; if the cutting position deviation exceeds 0.5mm, start the correction motor to correct it, and record the deviation data simultaneously for subsequent parameter optimization. Fuzzy optimization steps for each variable: Construct a four-dimensional fuzzy control model including raw material ratio, extrusion parameters, printing parameters, and bag making parameters. The input variable is the deviation of key indicators of each process, and the output variable is the parameter adjustment amount. Set up a fuzzy rule base, use the centroid method to defuzzify, and convert the fuzzy output into adjustment values. Quality closed-loop feedback steps: A comprehensive testing unit is set up at the end of the production line to test the thickness uniformity, heat seal strength, printing clarity, and sealing performance of the disinfection bags; non-conforming products are classified and statistically analyzed, and when the non-conformity rate of a certain category exceeds 1%, the corresponding process is traced back and parameters are re-optimized; a quality-parameter correlation model is established and the correlation relationship is written into the fuzzy rule base; a quality analysis report is generated monthly, including the impact coefficient of each parameter adjustment on quality indicators, which is used to optimize the initial parameter settings; Energy consumption dynamic balancing steps: collect energy consumption data of each device in real time and calculate the energy consumption per unit product; when energy consumption exceeds the target value by 5%, analyze high energy consumption processes: if the extruder has high energy consumption, reduce the temperature of each section by 3-5℃ without affecting the melt quality; if the printing machine has high energy consumption, optimize the drying temperature curve; establish an energy consumption-quality balance model to control the product defect rate while reducing energy consumption.

[0008] Furthermore, it also includes: The steps for dynamic matching of raw material humidity and drying parameters, and adaptive adjustment of screw speed and raw material flow rate are as follows: Based on the initial humidity value h and the target humidity value h0, the required drying time t and drying temperature T are calculated when the raw material bulk density ρ is between 0.9 and 1.1 g / cm³. 3 Within the specified range, the drying parameters are controlled through the nonlinear relationship between humidity difference and temperature. In the screw speed-raw material flow rate adaptive adjustment step, the real-time raw material flow rate q and screw speed n are collected. When the flow rate fluctuation exceeds ±5%, the speed adjustment coefficient is automatically adjusted based on the flow rate-speed response model established by historical data, so that the flow rate is restored to within ±2% of the set value. At the same time, the influence of the raw material melt index is considered. The higher the melt index, the higher the speed adjustment sensitivity setting.

[0009] The printing registration deviation-plate roller adjustment prediction step and the heat seal strength-temperature-pressure coupled adjustment step are as follows: A time series model is established based on the registration deviation values ​​of the previous 5 times to predict the deviation value of the next occurrence. The plate roller adjustment mechanism is started 0.5 seconds in advance to keep the actual deviation within 0.05mm. Different prediction model weights are set for different printing materials. The greater the film extensibility, the lower the weight coefficient of the historical deviation. In the heat seal strength-temperature-pressure coupled adjustment step, when the heat seal strength detection value F is lower than the standard value F0, the heat seal temperature T and pressure P are adjusted simultaneously. The adjustment ratio of temperature and pressure is determined according to the material thickness d.

[0010] Furthermore, in the fuzzy optimization steps for each variable, the formula for calculating the fuzzy rule weight update is: Let be the weights of the i, j, k, l-th fuzzy rules at time t. The updated weights, where α is the learning rate. The process capability index at time t. The process capability index at time t+1; the initial value of the rule weight is assigned according to the importance of the rule, and is updated once every 1000 products produced.

[0011] Furthermore, the drying time calculation formula for the raw material humidity-drying parameter dynamic matching step is: t=k h ×(h-h0)×ρ×S / (TT a ), where t is the required drying time, kh Here, ρ is the humidity conductivity coefficient, h is the initial humidity, h0 is the target humidity, ρ is the bulk density of the raw material, S is the surface area of ​​the raw material on the drying tray, and T is the drying temperature. a The ambient temperature is used; the humidity is checked every 5 minutes during the drying process. If the actual humidity decrease rate is less than 0.5% / min, the drying time is automatically extended by 20% or the temperature is increased by 5℃; when the raw material particle size is <40 mesh, the S value is calculated as 1.2 times.

[0012] Furthermore, the formula for calculating the heat-sealing parameter correction in the heat-sealing strength-temperature-pressure coupling adjustment step is: ΔT=β×(F0-F)×d / k, ΔP=(1-β)×(F0-F)×k / d, where ΔT is the heat-sealing temperature adjustment amount, ΔP is the heat-sealing pressure adjustment amount, β is the temperature adjustment ratio coefficient, F0 is the standard heat-sealing strength, F is the actual tested strength, d is the material thickness, and k is the interlayer adhesion coefficient. During adjustment, each adjustment should not exceed 5℃ or 0.05MPa. After adjustment, stabilize for 3 minutes before testing the heat-sealing strength. If F0-F>5N, first adjust by 50% according to the calculated value, and then perform a second adjustment after the strength recovers.

[0013] Furthermore, in the energy consumption dynamic balancing step, an energy consumption-quality dual-objective optimization model is adopted, with the objective function being: minE=λ1×(E1×k1+E2×k2+E3×k3) / N+λ2×(1-Q / 100), where E is the comprehensive optimization objective value, E1 is the real-time energy consumption of the extruder, k1 is the extruder energy consumption weight coefficient, dynamically adjusted according to the melting difficulty of the raw material (k1=0.6 when melt index <2.0), E2 is the real-time energy consumption of the printing press, k2 is the printing press energy consumption weight coefficient, E3 is the real-time energy consumption of the bag making machine, k3 is the bag making machine energy consumption weight coefficient, N is the output per unit time, λ1 is the energy consumption weight, λ2 is the quality weight, and Q is the pass rate; in the constraints, F is the heat sealing strength, δ is the film thickness, and D is the printing defect rate; the optimization variables include the temperature of the extruder metering section, the printing drying temperature, and the bag making heat sealing time, which are solved by an improved genetic algorithm, iterating once every 30 minutes.

[0014] A system for implementing a fuzzy optimization method for multivariate coordinated control of the production of disinfection bags, comprising: Raw material processing module: includes raw material storage tank, near-infrared spectrometer, humidity sensor, dryer, and automatic batching device; the batching device is controlled by PLC and dynamically adjusts the feed rate of each component according to the raw material ratio. When the raw material humidity exceeds the threshold, the dryer is automatically started. The drying parameters are calculated and determined by the humidity-drying model; a material level sensor is installed in the storage tank, and a replenishment alarm is issued when the material level is below 100L; a raw material impurity detector is equipped, and the filtration device is automatically started when the impurity content exceeds 0.01%; Extrusion molding module: consists of a single-screw extruder, die head, temperature control system, pressure sensor, and laser thickness gauge; the extruder is driven by a variable frequency motor, and the speed is adjusted by a PID controller; the die head is equipped with a servo motor driven gap adjustment mechanism, which corrects the film thickness in real time based on the thickness gauge data; a melt flow rate detector is set up, which automatically samples and analyzes every 30 minutes, and the data is fed back to the raw material processing module; an electrostatic eliminator is installed at the die head outlet.

[0015] Furthermore, the printing processing module includes a gravure printing machine, a tension control system, an ink circulation device, a viscometer, and a registration detection system; each color group is equipped with an independent drying device, and the drying temperature is adjusted via PID control; the registration detection system includes a CCD camera and an image processing unit, which identifies registration mark deviations and outputs control signals to the plate roller servo motor; the ink circulation device has a built-in heater that automatically adjusts the ink characteristics based on viscometer data; a film pretreatment device is installed at the printing machine inlet to improve ink adhesion; The bag forming module includes a bag making machine, a heat sealing device, a cutting mechanism, a tension sensor, and a deviation correction system. The heat sealing device uses pulse heating and is equipped with dual closed-loop control of temperature and pressure. The cutting mechanism is driven by a servo motor, and the cutting frequency is synchronized with the feeding speed. The deviation correction system identifies film deviation through an edge detection sensor and drives a deviation correction motor to correct the position to achieve accurate cutting. A counting device is set at the bag making outlet to count the output in real time and upload it to the management system.

[0016] Furthermore, the fuzzy control module adopts an industrial control computer and is equipped with fuzzy control algorithm software; it is equipped with a data acquisition card to collect temperature, pressure, speed, and thickness parameters of each module in real time; it outputs control signals to each actuator, has a built-in particle swarm optimization module to optimize the weights of fuzzy rules at regular intervals; and it communicates with the quality inspection module and energy consumption monitoring module through an Ethernet interface. The quality inspection module includes a visual inspection platform, a heat seal strength tester, a sealing performance tester, and a defective product rejection device; the visual inspection platform takes a picture every 0.5 seconds to identify printing defects; the heat seal strength tester samples 5 products per hour, and the sealing performance tester uses the water immersion method; the inspection data is uploaded to the fuzzy control module in real time for parameter optimization. The energy consumption monitoring module consists of an electricity meter, a data concentrator, and energy consumption analysis software. The electricity meter is installed in the power supply circuit of the extruder, printing machine, and bag making machine, which consume energy, and records the real-time power and cumulative energy consumption. The energy consumption analysis software calculates the energy consumption per unit product and the energy consumption ratio of each piece of equipment, and generates an energy consumption trend curve. When the energy consumption exceeds the set threshold, an early warning signal is sent to the fuzzy control module to trigger the energy consumption optimization process. The system supports data export.

[0017] Compared with existing technologies, the beneficial effects of this invention are: By constructing a four-dimensional fuzzy control model, parameters from each stage of raw material processing, extrusion, printing, and bag making are integrated to achieve multi-variable coordinated adjustment. This avoids the limitations of optimizing a single process, making product quality indicators more stable and meeting high standards.

[0018] The system's adaptability has been significantly improved, dynamically adjusting drying parameters based on raw material moisture, particle size, and other characteristics. Combined with real-time correction of extrusion temperature and speed using melt flow index, this ensures stable film forming quality. The printing registration deviation prediction mechanism uses historical data modeling for advance adjustment, reducing adjustment lag and improving pattern accuracy. The coupled adjustment strategy for heat-sealing parameters adapts to different material thicknesses and structures, guaranteeing consistency in heat-sealing strength and sealing performance.

[0019] The dynamic energy balance mechanism optimizes energy allocation across equipment while ensuring quality, reducing energy consumption per unit product and aligning with green production principles. The quality closed-loop feedback system quickly identifies defective products and traces their causes, automatically triggering parameter optimization, reducing manual intervention, and improving production continuity and efficiency. Overall, this method and system enhance the intelligence level of disinfection bag production, balancing quality, efficiency, and energy consumption, and possess significant practical value. Attached Figure Description

[0020] Figure 1 This is a schematic block diagram of the fuzzy optimization system for multivariate coordinated control of disinfection bag production proposed in this invention. Figure 2 This is a schematic block diagram of the fuzzy optimization method for multivariate coordinated control of disinfection bag production proposed in this invention. Figure 3 This diagram illustrates the energy consumption percentage at different production stages for the fuzzy optimization of multivariate coordinated control in the production of disinfection bags proposed in this invention. Figure 4 This is a schematic diagram illustrating the variation of the CPK value with production batches in the multivariate coordinated control of disinfection bag production proposed in this invention. Detailed Implementation

[0021] 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.

[0022] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0023] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0024] Reference Figures 1 to 4 A fuzzy optimization method for multivariate coordinated control of disinfection bag production includes the following steps: Dynamic adjustment steps for raw material ratio: Based on the material requirements of the sterilization bags (polyethylene to functional additive ratio range of 100:3 to 100:8), collect raw material moisture (measurement range 3%-15%), particle size (20-100 mesh), and melt index (1.5-3.0 g / 10 min) parameters; establish a raw material characteristic database containing processing compatibility data of 50 typical raw material combinations; when the moisture content of a batch of raw materials exceeds 8%, start pre-drying treatment (temperature 80-100℃, time 30-60 minutes) until the moisture content drops to the 3%-5% range; analyze the raw material mixing uniformity in real time using an online near-infrared spectrometer (detection accuracy 0.1%), and when the uniformity is lower than 95%, adjust the stirring speed (increase from 300 rpm to 450 rpm) and extend the stirring time (extend by 2 minutes for every 1% decrease in uniformity).

[0025] Extrusion molding parameter coordination steps: Set the temperature reference values ​​for each section of the extruder (feed section 150-170℃, compression section 170-190℃, metering section 190-210℃), and dynamically correct according to the melt index of the raw material: for every 0.5g / 10min increase in melt index, the metering section temperature decreases by 5℃; use a variable frequency motor to control the screw speed (range 50-200rpm), with the initial speed set at 1.2 times the raw material flow rate (50-200kg / h); monitor the die pressure in real time (range 5-15MPa), and when the pressure fluctuation exceeds ±0.5MPa, synchronously adjust the screw speed (adjust 2rpm for every 0.1MPa fluctuation) and the die temperature (adjust 1℃ for every 0.1MPa fluctuation) to maintain pressure stability; use a laser thickness gauge (accuracy ±0.001mm) to detect the film thickness, and when the thickness deviation exceeds ±0.005mm, adjust the die gap (adjustment accuracy 0.001mm).

[0026] The printing process is controlled synchronously as follows: Based on the complexity of the printed pattern on the sterilization bag (divided into three levels: simple, medium, and complex), the printing speed baseline values ​​are set (80, 60, and 40 m / min, respectively); a photoelectric sensor (response time ≤ 1 ms) is used to detect the printing registration deviation. When the lateral deviation exceeds 0.1 mm or the longitudinal deviation exceeds 0.2 mm, the servo motor (positioning accuracy ± 0.01 mm) is started to adjust the position of the printing roller; the ink viscosity is monitored in real time (measured in 20-60 s using a Forecast cup 4). For every 5 s deviation from the baseline value, the ink temperature is adjusted (0.5 ℃ adjustment for every 1 s deviation) or thinner is added (0.5% volume ratio addition for every 5 s deviation); after printing, the pattern clarity is checked using a visual inspection system (resolution 2592×1944). When the blurred area accounts for more than 2%, the printing speed is reduced by 10% and the drying temperature is increased by 5 ℃.

[0027] Bag forming coordination steps: Set the bag making machine cutting speed (30-100 times / minute) according to the size of the sterilization bag (length 100-500mm, width 80-400mm) to ensure it matches the previous printing speed (speed difference ≤5m / min); adopt coordinated control of heat sealing temperature (120-180℃) and pressure (0.2-0.6MPa), and set the heat sealing time according to the material thickness (0.1s for 0.01mm thickness); detect the heat sealing strength through a tensile sensor (accuracy ±0.1N), if it is lower than 10N / 15mm, increase the heat sealing temperature by 5℃ and extend the heat sealing time by 0.1s; if the cutting position deviation exceeds 0.5mm, start the correction motor (adjust speed 5mm / s) to correct it, and record the deviation data simultaneously for subsequent parameter optimization.

[0028] Multivariate fuzzy optimization steps: Construct a four-dimensional fuzzy control model including raw material ratio, extrusion parameters, printing parameters, and bag-making parameters. The input variables are the deviations of key indicators for each process (temperature deviation ±10℃, speed deviation ±10m / min, thickness deviation ±0.01mm, etc.), and the output variables are the parameter adjustment amounts. Set a fuzzy rule library (containing 200 basic rules), such as "if the film thickness is too thick and the die pressure is too high, then reduce the screw speed and increase the die clearance". Use the centroid method to defuzzify and convert the fuzzy output into precise adjustment values. Perform parameter optimization once every 1000 sterilization bags produced. Update the fuzzy rule weights through the particle swarm optimization algorithm (population size 30, number of iterations 50) to keep the process capability index CPK above 1.33.

[0029] Quality closed-loop feedback steps: A comprehensive testing unit is set up at the end of the production line to test the uniformity of the disinfection bag's thickness (deviation ≤3%), heat seal strength (≥12N / 15mm), printing clarity (no broken lines, blurriness), and sealing performance (no leakage under negative pressure of 0.05MPa for 30 seconds); non-conforming products are classified and statistically analyzed (raw material problems, equipment parameter problems, operational problems). When the non-conformity rate of a certain type exceeds 1%, the corresponding process is traced back and parameters are re-optimized; a quality-parameter correlation model is established, for example, for every 1N decrease in heat seal strength, the corresponding heat seal temperature needs to be increased by 3℃, and this correlation is written into the fuzzy rule base; a monthly quality analysis report is generated, including the impact coefficients of each parameter adjustment on quality indicators, used to optimize the initial parameter settings.

[0030] Energy consumption dynamic balancing steps: Real-time collection of energy consumption data for each piece of equipment (extruder 50-150kW, printing press 30-80kW, bag making machine 20-50kW), calculation of unit product energy consumption (target value ≤0.05kW・h / piece); when energy consumption exceeds the target value by 5%, analyze high-energy-consuming processes: if extruder energy consumption is too high, reduce the temperature of each section by 3-5℃ without affecting melt quality; if printing press energy consumption is too high, optimize the drying temperature curve (from constant temperature to gradient cooling); establish an energy consumption-quality balance model to ensure that while energy consumption is reduced, the product qualification rate is not lower than 99%; record energy consumption data of raw materials in different seasons and batches to form an energy consumption benchmark library for subsequent production energy consumption prediction and optimization.

[0031] This invention also includes: The raw material humidity-drying parameter dynamic matching step and the screw speed-raw material flow rate adaptive adjustment step: In the raw material humidity-drying parameter dynamic matching step, based on the initial humidity value h (in %) and the target humidity value h0 (in %), the required drying time t (in min) and drying temperature T (in °C) are calculated, when the raw material bulk density ρ (in g / cm³) is... 3 ) in the range of 0.9-1.1 g / cm 3Within the specified range, precise control of drying parameters is achieved through the nonlinear relationship between humidity difference and temperature. In the screw speed-raw material flow rate adaptive adjustment step, real-time raw material flow rate q (unit: kg / h) and screw speed n (unit: rpm) are collected. When the flow rate fluctuation exceeds ±5%, the flow rate-speed response model established based on historical data automatically adjusts the speed adjustment coefficient to restore the flow rate to within ±2% of the set value. At the same time, the influence of the raw material melt index is considered. The higher the melt index, the higher the speed adjustment sensitivity setting (the adjustment coefficient increases by 10%), ensuring that a stable extrusion volume can be maintained even when the raw material characteristics change.

[0032] Printing registration deviation - plate roller adjustment amount prediction step and heat seal strength - temperature and pressure coupling adjustment step: In the printing registration deviation - plate roller adjustment amount prediction step, a time series model is established using the previous 5 registration deviation values ​​(x1, x2, x3, x4, x5, unit mm) to predict the next possible deviation value x6, and the plate roller adjustment mechanism is started 0.5 seconds in advance to keep the actual deviation within 0.05mm; different prediction model weights are set for different printing materials (BOPP, PE, composite film). The greater the film extensibility, the lower the weight coefficient of historical deviations (the weight of the latest deviation is increased by 20%). In the heat seal strength-temperature-pressure coupled adjustment step, when the heat seal strength test value F (unit N) is lower than the standard value F0 (unit N), the heat seal temperature T (unit °C) and pressure P (unit MPa) are adjusted simultaneously. The adjustment ratio of temperature and pressure is determined according to the material thickness d (unit mm): for every 0.01 mm increase in thickness, the temperature adjustment ratio increases by 5% and the pressure adjustment ratio decreases by 5%. For multilayer composite films, an additional interlayer adhesion coefficient k (0-1) is introduced. The smaller the k value, the larger the temperature adjustment range (the basic range increases by 15%), to ensure that the heat seal strength meets the standard uniformly.

[0033] In this invention, the formula for calculating the fuzzy rule weight update in the multivariate fuzzy optimization step is: Let be the weights (range 0-1) of the i, j, k, l fuzzy rules at time t. The updated weights are represented by α, which is the learning rate (0.01-0.1, dynamically adjusted based on production stability: α=0.01 when CPK>1.67, α=0.05 when 1.33≤CPK≤1.67, and α=0.1 when CPK<1.33). The process capability index at time t. This represents the process capability index at time t+1. The initial weights of rules are assigned according to their importance (0.8-1.0 for basic rules, 0.3-0.7 for auxiliary rules), and are updated every 1000 products produced. When a rule causes a decrease in CPK three times consecutively, its weight is forcibly reduced to 0.1 and marked as needing optimization. The particle swarm optimization algorithm then searches for the optimal weight again. Through dynamic weight adjustment, the rule base prioritizes rules that are effective in improving heat sealing strength and reducing thickness deviation. For example, rules such as "die temperature is positively correlated with thickness" automatically have their weight increased when thickness fluctuations are large, ensuring the accuracy of fuzzy control in regulating key quality indicators.

[0034] In this invention, the drying time calculation formula for the raw material humidity-drying parameter dynamic matching step is: t=k h ×(h-h0)×ρ×S / (TT a ), where t is the required drying time (in minutes), and k h The humidity conductivity coefficient is 0.8-1.2 min・℃ / (g・cm). For polyethylene raw materials, the coefficient is 1.0. For every 1% increase in the additive percentage, k... h Increase by 0.05), h is the initial humidity (in %, averaged by three sensors located at different positions in the raw material pile), h0 is the target humidity (in %, set to 4% for polyethylene raw materials and 3% for composite raw materials), and ρ is the bulk density of the raw material (in g / cm³). 3 (Calculated in real time using the volume-weight method), where S is the surface area of ​​the raw material on the drying tray (unit: cm²). 2 The system automatically calculates the material feeding rate and pallet size, ensuring a pallet coverage coefficient of ≥80%. T represents the drying temperature (unit: °C, base value 90 °C, increase by 2 °C for every 1% increase in humidity above the target value). a The ambient temperature (in °C, collected in real time by a workshop temperature and humidity sensor) is used. Humidity is checked every 5 minutes during the drying process. If the actual humidity decrease rate is less than 0.5% / min, the drying time is automatically extended by 20% or the temperature is increased by 5 °C. When the raw material particle size is <40 mesh, the S value is calculated at 1.2 times (fine particles have a larger surface area) to avoid insufficient drying and ensure that the humidity of the raw material is stable within the target range before entering the extruder.

[0035] In this invention, the formula for correcting the heat sealing parameters in the heat sealing strength-temperature-pressure coupling adjustment step is: ΔT=β×(F0-F)×d / k, ΔP=(1-β)×(F0-F)×k / d, where ΔT is the heat sealing temperature adjustment amount (unit: °C, maximum adjustment range: ±20 °C), ΔP is the heat sealing pressure adjustment amount (unit: MPa, maximum adjustment range: ±0.2 MPa), and β is the temperature adjustment ratio coefficient (0.3-0.8, base value: 0.5, adjusted to 0.3 in high-temperature summer environments). In winter, the value is adjusted to 0.7 for low-temperature environments. F0 is the standard heat-sealing strength (in N, set according to the intended use of the sterilization bag: 15N for medical grade and 12N for food grade), F is the actual tested strength (in N, averaged from 10 samples per batch), d is the material thickness (in mm, measured 10mm before the heat-sealing position using a laser thickness gauge), and k is the interlayer adhesion coefficient (0-1, determined by peel test: 0.9 for PE single-layer film, 0.7 for PE / aluminum foil composite film, and 0.6 for PE / BOPP composite film). Adjustments should follow the principle of "small steps, multiple adjustments," with each adjustment not exceeding 5°C or 0.05MPa. After adjustment, allow 3 minutes for stabilization before testing the heat-sealing strength. If F0-F > 5N, adjust by 50% of the calculated value first, and then perform a second adjustment after the strength recovers. This avoids thermal degradation or puncture of the film due to over-adjustment, ensuring stable heat-sealing quality and undamaged material properties.

[0036] In this invention, the energy consumption dynamic balancing step employs an energy consumption-quality dual-objective optimization model, with the objective function being: minE=λ1×(E1×k1+E2×k2+E3×k3) / N+λ2×(1-Q / 100), st12N≤F≤20N, 0.03mm≤δ≤0.08mm, 0≤D≤0.5%, where E is the comprehensive optimization objective value (dimensionless), E1 is the real-time energy consumption of the extruder (unit: kW·h), k1 is the extruder energy consumption weighting coefficient (0.4-0.6, dynamically adjusted according to the melting difficulty of the raw material: k1=0.6 when the melt index <2.0), and E2 is the real-time energy consumption of the printing press (unit: kW·h). The parameters are: k1 = k2 (0.2-0.3, k2=0.3 when printing colors > 6), E3 = real-time energy consumption of bag making machine (unit: kW·h), k3 = k3 (0.2-0.3, k3=0.3 when heat sealing times > 2), N = output per unit time (unit: bags / h), λ1 = energy consumption weight (0.6-0.8, base value 0.7), λ2 = quality weight (0.2-0.4, base value 0.3), Q = pass rate (unit: %); in the constraints, F = heat sealing strength (unit: N), δ = film thickness (unit: mm), and D = printing defect rate (unit: %). The optimized variables include the extruder metering section temperature (190-210℃), printing and drying temperature (60-120℃), and bag-making heat-sealing time (0.1-1s). These variables are solved using an improved genetic algorithm (population size 40, crossover probability 0.7, mutation probability 0.05), iterating every 30 minutes. When producing medical disinfection bags, λ2 is automatically adjusted to 0.4 to prioritize quality. When raw material costs increase by more than 10%, λ1 is adjusted to 0.8 to enhance energy saving and achieve a dynamic balance between energy consumption and quality under different production scenarios.

[0037] This invention also discloses a system for a fuzzy optimization method for multivariate coordinated control in the production of disinfection bags, comprising: Raw material processing module: includes a raw material storage tank (500L capacity, with stirring device, speed 100-300rpm), a near-infrared spectrometer (detection wavelength 1000-2500nm, sampling frequency 10Hz), a humidity sensor (accuracy ±0.1%), and a dryer (temperature control range 50-120℃, air volume adjustable 0.5-2m). 3The dryer is equipped with a wettable mass airflow rate ( / min) and an automatic batching device (weighing accuracy ±0.1kg). The batching device is controlled by a PLC and dynamically adjusts the feed rate of each component according to the raw material ratio. When the raw material humidity exceeds the threshold, the dryer is automatically started. The drying parameters are determined by the humidity-drying model. A material level sensor (range 0-500L, accuracy ±1L) is installed in the storage tank. When the material level is below 100L, a replenishment alarm is issued. A raw material impurity detector (detection accuracy 0.1mm) is provided. When the impurity content exceeds 0.01%, the filtration device is automatically started to prevent impurities from entering subsequent processes.

[0038] The extrusion molding module consists of a single-screw extruder (screw diameter 50-80mm, length-to-diameter ratio 25:1), a die (width 500-1000mm, gap adjustment range 0.1-1mm), a temperature control system (independent temperature control for each section, accuracy ±1℃), a pressure sensor (range 0-20MPa, accuracy ±0.1MPa), and a laser thickness gauge (scanning frequency 500Hz). The extruder is driven by a variable frequency motor (power 15-30kW), and the speed is adjusted by a PID controller with a response time ≤0.5s. The die is equipped with a servo motor-driven gap adjustment mechanism (adjustment accuracy 0.001mm), which corrects the film thickness in real time based on the thickness gauge data. A melt flow rate detector (detection range 1-10g / 10min) is installed, which automatically samples and analyzes the data every 30 minutes, and the data is fed back to the raw material processing module. An electrostatic eliminator (elimination efficiency ≥95%) is installed at the die outlet to prevent the film from attracting dust due to static electricity.

[0039] In this invention, the printing processing module includes a gravure printing machine (6-8 color groups, maximum printing width 1000mm), a tension control system (control accuracy ±1N), an ink circulation device (flow rate 5-15L / min), a viscometer (measuring range 10-100s), and a registration detection system (detection accuracy ±0.01mm); each color group is equipped with an independent drying device (temperature 50-120℃, air volume 0.3-1m³). 3 The drying temperature is regulated by PID control with a response time of ≤1s; the registration detection system includes a CCD camera (resolution 1280×960, frame rate 30fps) and an image processing unit. After identifying the registration mark deviation, it outputs a control signal to the printing roller servo motor (positioning accuracy ±0.005mm), with an adjustment response time of ≤0.1s; the ink circulation device has a built-in heater (power 1-3kW) and a diluent addition pump (flow rate 0.1-1L / h), which automatically adjusts the ink characteristics according to the viscometer data; a film pretreatment device (including corona treatment, surface tension ≥38dyne / cm) is installed at the printing press inlet to improve ink adhesion.

[0040] Bag forming module: Includes a bag forming machine (maximum bag length 600mm, width 500mm), a heat sealing device (temperature range 100-200℃, pressure 0.1-1MPa), a cutting mechanism (cutting accuracy ±0.1mm), a tension sensor (range 0-50N, accuracy ±0.1N), and a deviation correction system (adjustment range ±10mm); the heat sealing device adopts pulse heating (heating time adjustable from 0.1-2s) and is equipped with dual closed-loop control of temperature and pressure; the cutting mechanism is driven by a servo motor (speed 100-500rpm), and the cutting frequency is synchronized with the feeding speed (synchronization error ≤0.01s); the deviation correction system identifies film offset through an edge detection sensor (detection accuracy ±0.05mm) and drives a deviation correction motor (adjustment speed 10mm / s) to correct the position, ensuring accurate cutting position; a counting device (accuracy ±1 / 1000 bags) is set at the bag outlet to count output in real time and upload it to the management system.

[0041] In this invention, the fuzzy control module uses an industrial control computer (quad-core processor, 3.0GHz, 8GB memory) and is equipped with fuzzy control algorithm software (supporting a custom rule base with ≥500 rules); it also features a data acquisition card (1kHz sampling frequency, 16 analog inputs, 12-bit precision) to collect real-time parameters such as temperature, pressure, speed, and thickness of each module (a total of 32 key parameters); it outputs control signals (12 analog and 8 digital) to each actuator with a control accuracy of ±0.5%FS; it has a built-in particle swarm optimization module (population size can be set from 10 to 50, iteration count from 20 to 100) to periodically optimize the weights of fuzzy rules; and it communicates with the quality detection module and energy consumption monitoring module via an Ethernet interface (1000Mbps) with a data transmission delay ≤100ms.

[0042] The quality inspection module includes a vision inspection platform (2 industrial cameras, resolution 2592×1944, light source is white ring LED), a heat seal strength tester (range 0-100N, accuracy ±0.1N), a sealing tester (negative pressure range -0.1-0MPa, accuracy ±0.001MPa), and a defective product rejection device (pneumatic push rod, response time ≤0.2s); the vision inspection platform takes a picture every 0.5 seconds to identify printing defects (stains, broken lines, misregistration), with an accuracy rate ≥99%; the heat seal strength tester samples 5 pieces per hour, with a testing speed of 300mm / min; the sealing tester uses the water immersion method, and the pressure holding time is adjustable from 10-60s; the inspection data is uploaded to the fuzzy control module in real time for parameter optimization.

[0043] The energy consumption monitoring module consists of a smart meter (measurement accuracy class 0.5, sampling frequency 1Hz), a data concentrator (supporting RS485 bus, with ≤32 connected devices), and energy consumption analysis software. The meter is installed in the power supply circuit of major energy-consuming equipment such as extruders, printing machines, and bag making machines to record real-time power and cumulative energy consumption. The energy consumption analysis software calculates the energy consumption per unit product and the energy consumption ratio of each device, generating an energy consumption trend curve (time granularity 1 minute). When the energy consumption exceeds the set threshold, an early warning signal is sent to the fuzzy control module to trigger the energy consumption optimization process. The system supports data export (CSV format) with a storage period of ≥1 year.

[0044] A fuzzy optimization method and specific implementation of a system for multivariate coordinated control in the production of disinfection bags: Example 1: Multivariate Coordinated Control in the Production of Medical Sterilization Bags This embodiment focuses on the production process of medical disinfection bags (300mm×400mm, 0.05mm thickness), employing the fuzzy optimization method and system of multivariable coordinated control described in this patent. The specific steps are as follows: Dynamic adjustment of raw material ratio: The ratio of polyethylene (PE) to functional additives (antibacterial agent) is 100:5. The uniformity of the raw material mixture is monitored in real time using a near-infrared spectrometer (model NIR-2000), with a sampling frequency of 10Hz. When the uniformity is detected to be below 95%, the stirring speed is increased from 300rpm to 420rpm, and the stirring time is extended (2 minutes for every 1% decrease in uniformity). Raw material humidity is monitored by three distributed sensors (accuracy ±0.1%). When the average humidity exceeds 8%, a dryer (model DR-500) is started for pre-drying treatment, with an initial temperature set at 90℃, and dynamically adjusted according to the humidity value.

[0045] Extrusion molding parameter coordination: The extruder used is a single-screw extruder with a diameter of 65mm (L / D ratio 25:1). The temperature reference values ​​for each section are set as follows: feeding section 160℃, compression section 180℃, metering section 200℃. Based on the raw material melt index (detected value 2.2g / 10min), the metering section temperature is corrected to 198℃. The initial screw speed is set to 144rpm, which is 1.2 times the raw material flow rate (120kg / h). The die pressure (target value 10MPa) is monitored in real time by a pressure sensor (model PT-100). When the pressure fluctuation exceeds ±0.5MPa, the screw speed (adjusted by 2rpm for every 0.1MPa fluctuation) and die temperature (adjusted by 1℃ for every 0.1MPa fluctuation) are adjusted synchronously. A laser thickness gauge (model LT-300) checks the film thickness every 0.5 seconds. When the deviation exceeds ±0.005mm, the die gap is adjusted via a servo motor (adjustment accuracy 0.001mm).

[0046] Printing process synchronous control: The printed pattern is a medical logo (medium complexity), and the baseline printing speed is set to 60m / min. A CCD camera (1280×960 resolution) is used to detect registration deviation. When the lateral deviation exceeds 0.1mm or the longitudinal deviation exceeds 0.2mm, the servo motor (positioning accuracy ±0.005mm) is activated to adjust the position of the printing roller. Ink viscosity (baseline value 40s) is monitored using an online viscometer (model VM-500). For every 5s deviation from the baseline viscosity, the ink temperature is adjusted (0.5℃ adjustment for every 1s deviation) or thinner is added (0.5% volume ratio for every 5s deviation).

[0047] Bag forming coordination: The cutting speed is set to 60 cuts / minute based on the size of the sterilization bag to ensure matching with the printing speed (60m / min) (speed difference ≤ 5m / min). The heat sealing temperature is set to 160℃, the pressure to 0.4MPa, and the heat sealing time to 0.5s (based on a thickness of 0.05mm). The heat sealing strength is detected using a tensile sensor (model FS-100). When it is below 15N / 15mm, the heat sealing temperature is increased by 5℃ and the heat sealing time is extended by 0.1s.

[0048] Multivariate fuzzy optimization: A four-dimensional fuzzy control model is constructed. Input variables include temperature deviation (±10℃), speed deviation (±10m / min), thickness deviation (±0.01mm), and pressure deviation (±1MPa). Output variables are the adjustment amounts of each parameter. The fuzzy rule base contains 200 basic rules. For every 1000 disinfection bags produced, the rule weights are updated using a particle swarm optimization algorithm (population size 30, iterations 50), employing the formula... The calculation is performed, where α is dynamically adjusted according to the CPK value (α=0.01 when CPK>1.67, α=0.05 when 1.33≤CPK≤1.67, and α=0.1 when CPK<1.33).

[0049] Quality closed-loop feedback: A comprehensive inspection unit is set up at the end of the production line to inspect thickness uniformity (deviation ≤3%), heat seal strength (≥15N / 15mm), printing clarity, and sealing performance (no leakage under negative pressure of 0.05MPa for 30s). When the defect rate of a certain type exceeds 1%, the corresponding process is traced back and parameter optimization is triggered.

[0050] Energy consumption dynamic balance: An energy consumption-quality dual-objective optimization model is adopted, with the objective function being minE=λ1×(E1×k1+E2×k2+E3×k3) / N+λ2×(1-Q / 100), where λ1=0.6, λ2=0.4 (prioritizing the quality of medical disinfection bags), k1=0.5, k2=0.3, and k3=0.2. An improved genetic algorithm (population size 40, crossover probability 0.7, mutation probability 0.05) optimizes the parameters every 30 minutes.

[0051] Example 2: Multivariate Coordinated Control in the Production of Food-Grade Sterilization Bags This embodiment focuses on the production process of food-grade sterilization bags (200mm×300mm, 0.04mm thickness), employing the method and system described in this patent. The specific steps are as follows: Dynamic adjustment of raw material ratio: The ratio of polyethylene to functional additives (antioxidants) is 100:3. Three distributed sensors are used to detect raw material humidity; the dryer is activated when the average humidity exceeds 8%. Drying time is calculated using the formula t=k. h ×(h-h0)×ρ×S / (TT a ) calculate, where k h =1.0 (polyethylene raw material), h is the initial humidity, h0=4% (target humidity), ρ is the bulk density of the raw material, S is the surface area of ​​the drying tray, T is the drying temperature, T a The ambient temperature.

[0052] Extrusion molding parameter coordination: The baseline temperatures for each section of the extruder are: 155℃ for the feeding section, 175℃ for the compression section, and 195℃ for the metering section. Based on the melt flow index of the raw material (detected value of 2.8 g / 10 min), the temperature of the metering section is corrected to 190℃. The initial screw speed is set to 120 rpm, which is 1.2 times the raw material flow rate (100 kg / h).

[0053] Printing process synchronous control: The printed pattern is a food label (simple complexity), and the printing speed baseline value is set to 80m / min. The registration deviation detection and correction mechanism is the same as in Example 1.

[0054] Bag forming coordination: Cutting speed is set to 80 cuts / minute, heat sealing temperature to 150℃, pressure to 0.3MPa, and heat sealing time to 0.4s. Heat sealing parameter corrections are calculated using the formulas ΔT=β×(F0-F)×d / k and ΔP=(1-β)×(F0-F)×k / d, where β=0.5 (base value), F0=12N (food grade standard), F is the actual tested strength, d is the material thickness, and k=0.9 (PE single-layer film).

[0055] The steps of multivariate fuzzy optimization, quality closed-loop feedback and energy consumption dynamic balance are basically the same as those in Example 1, wherein λ1=0.8 and λ2=0.2 in the energy consumption optimization objective function (food-grade sterilization bags pay more attention to energy saving).

[0056] The performance comparison data is shown in the table below: index Traditional methods Method of this application (Example 1) Method of this application (Example 2) Product qualification rate 92.5% 99.6% 99.4% Unit product energy consumption 0.065 kWh / unit 0.048 kW・h / unit 0.045 kW・h / unit Heat seal strength stability ±2.5N ±0.8N ±0.9N Diaphragm thickness deviation ±0.008mm ±0.002mm ±0.003mm Printing registration accuracy ±0.15mm ±0.04mm ±0.05mm The above data shows that the product qualification rate is significantly improved after adopting the method of this application, mainly due to the multi-variable collaborative control and fuzzy optimization mechanism, which effectively solves the limitations of parameter adjustment lag and single-variable control in traditional methods. Unit product energy consumption is significantly reduced, reflecting the effect of energy consumption-quality dual-objective optimization, achieving energy saving while ensuring product quality. Indicators such as heat-sealing strength stability, film thickness deviation, and printing registration accuracy are all significantly improved, indicating that the method of this application can effectively coordinate parameters of each process, improving the stability and accuracy of the production process. Overall, the method of this patent has significant advantages in improving product quality, reducing energy consumption, and improving production stability, and is suitable for the production needs of different types of disinfection bags.

[0057] Reference Figure 3 This pie chart visually illustrates the energy consumption distribution across various stages of the sterilization bag production process. The data shows that extrusion and printing processes are the main sources of energy consumption, accounting for 75% combined. This provides a clear direction for energy consumption optimization. The patented method prioritizes reducing energy consumption in high-energy-consuming stages by specifically adjusting the extruder temperature curve and the printing drying gradient. For example, in Example 1, by optimizing the extruder metering section temperature and printing drying temperature curves, the energy consumption of these two processes was reduced by 12% and 15%, respectively, verifying the effectiveness of the dynamic energy balance strategy and providing data support for green production.

[0058] Reference Figure 4 The line graph reflects the improving trend of the process capability index after adopting the method of this patent. The data shows that as the number of production batches increases, the CPK value gradually increases and stabilizes above 1.33, indicating a continuous improvement in the stability of the production process. This is attributed to the fuzzy rule weight update mechanism in claim 4, which continuously optimizes the rule base, enhancing the system's adaptability. In Example 1, the CPK ultimately reached 1.5, far exceeding the 1.1 of the traditional method, verifying that the multivariate fuzzy optimization strategy can effectively improve process capability and ensure the consistency of product quality.

[0059] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A fuzzy optimization method for multivariate coordinated control in the production of disinfection bags, characterized in that, include: Dynamic adjustment steps for raw material ratio: According to the material requirements of the disinfection bag, collect parameters such as raw material moisture, particle size, and melt index; establish a raw material characteristic database containing processing compatibility data of 50 raw material combinations; start pre-drying treatment when the moisture content of a batch of raw materials exceeds 8%; analyze the mixing uniformity of raw materials in real time using an online near-infrared spectrometer, and adjust the stirring speed and extend the stirring time when the uniformity is lower than 95%; Extrusion molding parameter coordination steps: Set the temperature baseline values ​​for each section of the extruder and dynamically correct them according to the melt flow index of the raw material: for every 0.5 g / 10 min increase in melt flow index, the metering section temperature decreases by 5℃; use a variable frequency motor to control the screw speed, with the initial speed set at 1.2 times the raw material flow rate; monitor the die pressure in real time, and when the pressure fluctuation exceeds ±0.5 MPa, adjust the screw speed and die temperature synchronously to maintain pressure stability; use a laser thickness gauge to detect the film thickness, and adjust the die clearance when the thickness deviation exceeds ±0.005 mm. The printing process synchronous control steps are as follows: a printing speed benchmark value is set according to the complexity of the printed pattern on the disinfection bag; a photoelectric sensor is used to detect the printing registration deviation, and when the lateral deviation exceeds 0.1mm or the longitudinal deviation exceeds 0.2mm, the servo motor is started to adjust the position of the printing roller; the ink viscosity is monitored in real time, and the ink temperature is adjusted or thinner is added every 5 seconds when the viscosity deviates from the benchmark value. After printing, the clarity of the pattern is checked by a visual inspection system. If the proportion of blurred areas exceeds 2%, the printing speed is reduced by 10% and the drying temperature is increased by 5°C. Bag forming coordination steps: Set the bag making machine cutting speed according to the size of the sterilization bag to match the previous printing speed; adopt coordinated control of heat sealing temperature and pressure, and set the heat sealing time according to the material thickness; detect the heat sealing strength through a tensile sensor. If it is lower than 10N / 15mm, increase the heat sealing temperature by 5℃ and extend the heat sealing time by 0.1s; if the cutting position deviation exceeds 0.5mm, start the correction motor to correct it, and record the deviation data simultaneously for subsequent parameter optimization. Fuzzy optimization steps for each variable: Construct a four-dimensional fuzzy control model that includes raw material ratio, extrusion parameters, printing parameters, and bag making parameters. The input variable is the deviation of each process index, and the output variable is the parameter adjustment amount. Set up a fuzzy rule base, use the centroid method to defuzzify, and convert the fuzzy output into adjustment values.

2. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 1, characterized in that, Also includes: Quality closed-loop feedback steps: Set up a comprehensive testing unit at the end of the production line to test the thickness uniformity, heat seal strength, printing clarity, and sealing performance of the disinfection bags; Non-conforming products are classified and statistically analyzed. When the non-conformity rate exceeds 1%, the corresponding process is traced and the parameters are re-optimized. A quality-parameter correlation model is established and the correlation relationship is written into the fuzzy rule base. A quality analysis report is generated monthly, which includes the impact coefficient of each parameter adjustment on the quality indicators, and is used to optimize the initial parameter settings. Energy consumption dynamic balance steps: collect energy consumption data of each device in real time and calculate the energy consumption per unit product; when the energy consumption exceeds the target value by 5%, analyze the high energy consumption process: if the extruder has high energy consumption, reduce the temperature of each section by 3-5℃ without affecting the melt quality; if the printing machine has high energy consumption, optimize the drying temperature curve; establish an energy consumption-quality balance model to control the product defect rate while reducing energy consumption. The steps for dynamic matching of raw material humidity and drying parameters, and adaptive adjustment of screw speed and raw material flow rate are as follows: Based on the initial humidity value h and the target humidity value h0, the required drying time t and drying temperature T are calculated when the raw material bulk density ρ is between 0.9 and 1.1 g / cm³. 3 Within the specified range, the drying parameters are controlled through the nonlinear relationship between humidity difference and temperature. In the screw speed-raw material flow rate adaptive adjustment step, the real-time raw material flow rate q and screw speed n are collected. When the flow rate fluctuation exceeds ±5%, the speed adjustment coefficient is automatically adjusted based on the flow rate-speed response model established by historical data, so that the flow rate is restored to within ±2% of the set value. At the same time, the influence of the raw material melt index is considered. The higher the melt index, the higher the speed adjustment sensitivity setting.

3. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 1, characterized in that, Also includes: The printing registration deviation-plate roller adjustment prediction step and the heat seal strength-temperature-pressure coupled adjustment step are as follows: A time series model is established based on the registration deviation values ​​of the previous 5 times to predict the deviation value of the next occurrence. The plate roller adjustment mechanism is started 0.5 seconds in advance to keep the actual deviation within 0.05mm. Different prediction model weights are set for different printing materials. The greater the film extensibility, the lower the weight coefficient of the historical deviation. In the heat seal strength-temperature-pressure coupled adjustment step, when the heat seal strength detection value F is lower than the standard value F0, the heat seal temperature T and pressure P are adjusted simultaneously. The adjustment ratio of temperature and pressure is determined according to the material thickness d.

4. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 1, characterized in that, In the fuzzy optimization steps for each variable, the formula for calculating the fuzzy rule weight update is: The process capability index at time t+1; the initial value of the rule weight is assigned according to the importance of the rule, and is updated once every 1000 products produced.

5. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 2, characterized in that, The drying time calculation formula for the dynamic matching step of raw material humidity and drying parameters is: t=k h ×(h-h0)×ρ×S / (TT a ), where t is the required drying time, k h Here, ρ is the humidity conductivity coefficient, h is the initial humidity, h0 is the target humidity, ρ is the bulk density of the raw material, S is the surface area of ​​the raw material on the drying tray, and T is the drying temperature. a The ambient temperature is used; the humidity is checked every 5 minutes during the drying process. If the actual humidity decrease rate is less than 0.5% / min, the drying time is automatically extended by 20% or the temperature is increased by 5℃; when the raw material particle size is <40 mesh, the S value is calculated as 1.2 times.

6. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 3, characterized in that, The formula for calculating the heat-sealing parameter correction in the heat-sealing strength-temperature-pressure coupled adjustment step is: ΔT=β×(F0-F)×d / k, ΔP=(1-β)×(F0-F)×k / d, where ΔT is the heat-sealing temperature adjustment amount, ΔP is the heat-sealing pressure adjustment amount, β is the temperature adjustment ratio coefficient, F0 is the standard heat-sealing strength, F is the actual tested strength, d is the material thickness, and k is the interlayer adhesion coefficient. Each adjustment should not exceed 5℃ or 0.05MPa. After adjustment, stabilize for 3 minutes before testing the heat-sealing strength. If F0-F>5N, first adjust by 50% according to the calculated value, and then perform a second adjustment after the strength recovers.

7. The fuzzy optimization method for multivariate coordinated control of disinfection bag production according to claim 2, characterized in that, In the energy consumption dynamic balancing step, an energy consumption-quality dual-objective optimization model is adopted. The objective function is: minE=λ1×(E1×k1+E2×k2+E3×k3) / N+λ2×(1-Q / 100), where E is the comprehensive optimization objective value, E1 is the real-time energy consumption of the extruder, k1 is the extruder energy consumption weight coefficient, which is dynamically adjusted according to the melting difficulty of the raw material: when the melt index is <2.0, k1=0.6, E2 is the real-time energy consumption of the printing machine, k2 is the printing machine energy consumption weight coefficient, E3 is the real-time energy consumption of the bag making machine, k3 is the bag making machine energy consumption weight coefficient, N is the output per unit time, λ1 is the energy consumption weight, λ2 is the quality weight, and Q is the pass rate. In the constraints, F is the heat sealing strength, δ is the film thickness, and D is the printing defect rate. The optimization variables include the temperature of the extruder metering section, the printing drying temperature, and the bag making heat sealing time. The solution is obtained by an improved genetic algorithm, which iterates once every 30 minutes.

8. A system for implementing the fuzzy optimization method for multivariate coordinated control of disinfection bag production as described in any one of claims 1-7, characterized in that, include: Raw material processing module: includes raw material storage tank, near-infrared spectrometer, humidity sensor, dryer, and automatic batching device; The batching device is controlled by a PLC and dynamically adjusts the feed rate of each component according to the raw material ratio. When the raw material humidity exceeds the threshold, the dryer is automatically started. The drying parameters are calculated and determined by the humidity-drying model. A material level sensor is installed in the storage tank. When the material level is below 100L, a replenishment alarm is issued. A raw material impurity detector is equipped. When the impurity content exceeds 0.01%, the filtration device is automatically started. Extrusion molding module: consists of a single-screw extruder, die head, temperature control system, pressure sensor, and laser thickness gauge; the extruder is driven by a variable frequency motor, and the speed is adjusted by a PID controller; the die head is equipped with a servo motor driven gap adjustment mechanism, which corrects the film thickness in real time according to the thickness gauge data; a melt flow rate detector is set up, which automatically samples and analyzes every 30 minutes, and the data is fed back to the raw material processing module; An electrostatic eliminator is installed at the die head outlet.

9. The fuzzy optimization system for multivariate coordinated control of disinfection bag production according to claim 8, characterized in that, The printing processing module includes a gravure printing press, a tension control system, an ink circulation device, a viscometer, and a registration detection system. Each color group is equipped with an independent drying device, and the drying temperature is regulated by a PID controller. The registration detection system includes a CCD camera and an image processing unit. After identifying registration mark deviations, it outputs control signals to the plate roller servo motor. The ink circulation device has a built-in heater that automatically adjusts the ink characteristics based on viscometer data. A film pretreatment device is installed at the printing press inlet to improve ink adhesion. The bag forming module includes a bag making machine, a heat sealing device, a cutting mechanism, a tension sensor, and a deviation correction system. The heat sealing device uses pulse heating and is equipped with dual closed-loop control of temperature and pressure. The cutting mechanism is driven by a servo motor, and the cutting frequency is synchronized with the feeding speed. The deviation correction system identifies film deviation through an edge detection sensor and drives a deviation correction motor to correct the position to achieve accurate cutting. A counting device is set at the bag making outlet to count the output in real time and upload it to the management system.

10. The fuzzy optimization system for multivariate coordinated control of disinfection bag production according to claim 8, characterized in that, The fuzzy control module uses an industrial control computer and is equipped with fuzzy control algorithm software; it is equipped with a data acquisition card to collect temperature, pressure, speed, and thickness parameters of each module in real time; it outputs control signals to each actuator; it has a built-in particle swarm optimization module to optimize the weights of fuzzy rules at regular intervals; and it communicates with the quality inspection module and energy consumption monitoring module through an Ethernet interface. The quality inspection module includes a visual inspection platform, a heat seal strength tester, a sealing performance tester, and a defective product rejection device; the visual inspection platform takes a picture every 0.5 seconds to identify printing defects; the heat seal strength tester samples 5 products per hour, and the sealing performance tester uses the water immersion method; the inspection data is uploaded to the fuzzy control module in real time for parameter optimization. The energy consumption monitoring module consists of an electricity meter, a data concentrator, and energy consumption analysis software. The electricity meter is installed in the power supply circuit of the extruder, printing machine, and bag making machine, which consume energy, and records the real-time power and cumulative energy consumption. The energy consumption analysis software calculates the energy consumption per unit product and the energy consumption ratio of each piece of equipment, and generates an energy consumption trend curve. When the energy consumption exceeds the set threshold, an early warning signal is sent to the fuzzy control module to trigger the energy consumption optimization process. The system supports data export.

Images