Composite cloth production management optimization method and system based on data module

Abstract

The invention relates to the technical field of composite cloth production management, in particular to a composite cloth production management optimization method and system based on a data module, and the method comprises the steps: collecting the quality parameters of air permeability, tensile strength, water absorption, color fastness and the like of composite cloth, constructing a quality evaluation model, and generating a comprehensive quality score; combining seasonal factors, price fluctuation, random events, historical demands and other external market factors to predict the demand quantity of the composite cloth; internal production factors such as process difficulty, production efficiency and working environment are evaluated, production constraint conditions are generated, a production model is constructed in combination with workload parameters and process parameters of production equipment, and the production capacity is calculated; based on the production balance rate and the comprehensive quality score, the workload and the process parameters are optimized by using the particle swarm optimization algorithm, and efficient optimization of the production process and improvement of the product quality are realized, so that the flexibility of production management is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of composite fabric production management, and in particular to a composite fabric production management optimization method and system based on a data module. Background Art

[0002] Composite fabrics are widely used in clothing, medical and industrial fields because they have the excellent properties of multiple materials. Therefore, composite fabrics have significant advantages in meeting the needs of different scenarios with their unique functionality. However, with the increasingly stringent market requirements for the quality of composite fabric products and the diversification of user needs, the complexity of production management has increased significantly, which has posed higher challenges to traditional production management methods. Therefore, efficient production management optimization solutions are urgently needed to comprehensively improve production efficiency, product quality and resource utilization.

[0003] At present, some existing solutions can determine the quality parameters of composite fabrics, which can help improve the production process to a certain extent and make the product quality more standardized. However, the production process of composite fabrics is complicated, involving multiple key quality parameters such as breathability, waterproofness, and comfort. These parameters are not only affected by the production process, but also closely related to equipment settings and environmental conditions. Static management methods that rely solely on quality parameters are difficult to fully optimize the production process, and are prone to problems such as quality fluctuations and waste of resources. On the other hand, market demand fluctuates frequently due to seasonal changes, price fluctuations, and random events, which puts higher requirements on the flexibility of production management and resource scheduling capabilities. However, existing production management methods usually lack in-depth application of big data technology, resulting in insufficient responsiveness of the production process to market changes, and the level of flexibility still needs to be improved.

[0004] Therefore, a composite fabric production management optimization method and system based on data module is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a composite cloth production management optimization method and system based on a data module, by collecting quality parameters such as air permeability, tensile strength, water absorption and color fastness of the composite cloth, constructing a quality evaluation model, and generating a comprehensive quality score; combining external market factors such as seasonal factors, price fluctuations, random events and historical demand to predict the demand for composite cloth; evaluating internal production factors such as process difficulty, production efficiency and working environment, generating production constraints, and combining the workload parameters and process parameters of production equipment to construct a production model and calculate the production volume; based on the production balance rate and the comprehensive quality score, using the particle swarm optimization algorithm to optimize the workload and process parameters, to achieve efficient optimization of the production process and improvement of product quality, thereby improving the flexibility of composite cloth production management.

[0006] To achieve the above object, the present invention provides the following technical solutions: The first part is a composite fabric production management optimization method based on data module, including: Collecting composite fabric quality parameters of the sample to be tested, wherein the composite fabric quality parameters include air permeability parameters, tensile strength parameters, water absorption parameters and color fastness parameters; Establishing a quality assessment model, the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; normalizing the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value and performing weighted summation to obtain a comprehensive quality score; Acquire external market factors, wherein the external market factors include seasonal factors, price fluctuations, random events and historical demand, and construct a forecasting model based on the external market factors, wherein the forecasting model is used to forecast the demand for composite fabrics; Evaluate internal production factors to obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite cloth, production efficiency and working environment; obtain workload parameters and process parameters of the production equipment, and build a production model based on the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite cloth; Calculating a production balance rate according to the demand for the composite fabric and the production of the composite fabric; The production balance rate and the comprehensive quality score are optimized using a particle swarm optimization algorithm, and the optimized workload parameters and process parameters are output.

[0007] Furthermore, the calculation process of the air permeability evaluation value includes: Acquiring the air permeability parameters, wherein the air permeability parameters include the fabric area, test time, air volume and fabric components of the sample to be tested; Dividing the air volume by the fabric area and the test time to obtain the air permeability per unit area; The air permeability per unit area is corrected according to the fabric component to obtain the air permeability evaluation value.

[0008] Furthermore, the calculation process of the tensile strength evaluation value includes: Acquiring the tensile resistance parameters, wherein the tensile resistance parameters include the transverse cross-sectional area, the longitudinal cross-sectional area, the transverse maximum tensile force and the longitudinal maximum tensile force of the sample to be tested; Dividing the maximum transverse tensile force by the transverse cross-sectional area to obtain the transverse tensile strength; Dividing the longitudinal maximum tensile force by the longitudinal cross-sectional area to obtain the longitudinal tensile strength; The transverse tensile strength and the longitudinal tensile strength are weightedly summed to obtain the tensile resistance evaluation value.

[0009] Furthermore, the calculation process of the water absorption evaluation value includes: Acquiring the water absorption parameters, wherein the water absorption parameters include a first cloth weight, a second cloth weight, a cloth area, a cloth thickness, and a cloth component; Wherein, the first cloth weight is the cloth weight of the sample to be tested in a dry state, and the second cloth weight is the cloth weight of the sample to be tested after absorbing water; Subtract the weight of the first cloth from the weight of the second cloth and divide the result by the area of ​​the cloth to obtain the water absorption rate per unit area; Dividing the water absorption per unit area by the thickness of the cloth to obtain the water absorption per unit thickness; The water absorption rate per unit thickness is corrected according to the fabric components to obtain the water absorption evaluation value.

[0010] Furthermore, the calculation process of the color fastness evaluation value includes: Acquire the color fastness parameter, wherein the color fastness parameter includes a first cloth area, a second cloth area, a first brightness value, a first chromaticity value, a second brightness value, and a second chromaticity value; Wherein, the first cloth area is the cloth area of ​​the sample to be tested before rubbing, and the second cloth area is the cloth area of ​​the sample to be tested whose color falls off after rubbing; the first brightness value and the first chromaticity value are the brightness and chromaticity of the sample to be tested before washing, and the second brightness value and the second chromaticity value are the brightness and chromaticity of the sample to be tested after washing; Calculating the ratio of the second fabric area to the first fabric area to obtain rubbing color fastness; Calculate the color change degree before and after washing according to the first brightness value, the first chromaticity value, the second brightness value, and the second chromaticity value to obtain the washing color fastness; The color fastness evaluation value is obtained by weighted summing the rubbing color fastness and the washing color fastness.

[0011] Furthermore, the production constraints include: A process difficulty constraint, used to limit the upper limit of the temperature and pressure of the production equipment according to the process difficulty; Production efficiency constraints, used to limit the upper limits of the frequency and load rate of the production equipment according to the production efficiency; The working environment constraint is used to limit the upper limit of the operating time of the production equipment according to the working environment.

[0012] Furthermore, the calculation process of the production balance rate includes: The inventory of the previous cycle and the target inventory are obtained, and the production balance rate is calculated according to the inventory of the previous cycle, the target inventory, the demand for the composite cloth and the production of the composite cloth, which is expressed as: ; in, is the production balance rate, is the production volume of the composite fabric, is the inventory volume of the previous period, is the demand for the composite fabric, is the target inventory quantity.

[0013] Furthermore, the decision space of the particle swarm optimization algorithm includes: A process parameter space, used to adjust the process parameters affecting the comprehensive quality score; the process parameters include the temperature and pressure of the production equipment; The workload parameter space is used to adjust the workload parameters that affect the production balance rate; the workload parameters include the frequency, load rate and operating time of the production equipment.

[0014] Furthermore, the objective function of the particle swarm optimization algorithm is expressed as: ; in, is the target value after maximization, Score the overall quality. is the normalized production balance rate, is the normalized production cost, , and Weight coefficient, is the decision space of the particle swarm optimization algorithm.

[0015] The second part is a composite fabric production management optimization system based on data module, including: A data acquisition module is used to collect the composite fabric quality parameters of the sample to be tested; A quality assessment module, used to establish a quality assessment model, wherein the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value are normalized and weightedly summed to obtain a comprehensive quality score; A demand calculation module is used to obtain external market factors, including seasonal factors, price fluctuations, random events and historical demand, and to build a forecasting model based on the external market factors, wherein the forecasting model is used to forecast the demand for composite fabrics; A production calculation module is used to evaluate internal production factors and obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite cloth, the production efficiency and the working environment; obtain the workload parameters and process parameters of the production equipment, and build a production model according to the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite cloth; The parameter optimization module calculates the production balance rate according to the demand for the composite cloth and the production of the composite cloth; and uses a particle swarm optimization algorithm to optimize the production balance rate and the comprehensive quality score to obtain the optimized workload parameters and process parameters.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention collects key quality parameters of composite fabrics and establishes a quality assessment model to assess multiple indicators such as air permeability, tensile strength, water absorption and color fastness, which can fully reflect the various properties of composite fabrics. By normalizing and weighted summing various quality parameters, a comprehensive quality score is generated, which accurately quantifies the comprehensive quality level of the composite fabric and intuitively reflects the multi-dimensional performance of the composite fabric. At the same time, it provides a scientific basis for subsequent production decisions, ensuring that product quality meets market demand expectations, thereby improving the flexibility of composite fabric production management.

[0017] 2. The present invention collects external market factors, establishes a forecasting model, and accurately predicts the market demand for composite fabrics. Combined with the set production constraints, a production model is further constructed to obtain the actual output value under the constraints, thereby ensuring that the production process matches the actual environment. By combining the demand forecasting model with the production model, the production balance rate is calculated, which effectively reduces inventory backlogs and resource waste caused by overproduction, while avoiding market gaps caused by insufficient supply, thereby improving the flexibility of composite fabric production management and resource utilization efficiency.

[0018] 3. The present invention introduces a particle swarm optimization algorithm, comprehensively considers the production balance rate, comprehensive quality score and production cost, constructs a multi-objective optimization function, and meets the balance requirements of different production objectives. In addition, by setting the corresponding particle swarm decision space, it is possible to seek the optimal solution in the multidimensional decision space, and realize the optimization adjustment of the workload parameters and process parameters of the composite cloth production equipment. The present invention can not only meet market demand, but also improve product quality, thereby realizing efficient utilization of resources and maximization of production efficiency, thereby improving the flexibility and comprehensive benefits of composite cloth production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a process flow of a composite fabric production management optimization method based on a data module provided by an embodiment of the present invention; Figure 2 A schematic diagram of the quality structure of the composite fabric provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a composite fabric production management optimization system based on a data module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figures 1 to 3 The present invention provides a composite fabric production management optimization method and system based on a data module, and the technical solution is as follows: As the market demand for high-performance composite fabrics continues to grow, composite fabric companies are facing increasingly complex production management challenges. On the one hand, it is necessary to ensure the high quality of products to meet market demand; on the other hand, it is necessary to take into account production efficiency and resource utilization to avoid inventory backlogs caused by overproduction or market shortages caused by insufficient supply. In addition, under the current "dual carbon" goals, production material control has also become a key issue for companies to optimize production management. Existing methods may lack comprehensive considerations when coordinating production and quality. In order to solve this problem, the present invention proposes a composite fabric production management optimization method based on a data module to enhance the flexibility of composite fabric production management.

[0022] Embodiment 1 is as follows: Figure 1 A schematic flow chart of a composite fabric production management optimization method based on a data module provided in an embodiment of the present invention.

[0023] like Figure 1 As shown, a composite fabric production management optimization method based on a data module includes: Step S1: collecting composite fabric quality parameters of the sample to be tested, wherein the composite fabric quality parameters include air permeability parameters, tensile strength parameters, water absorption parameters and color fastness parameters.

[0024] Among them, the sample to be tested is a composite fabric sample that meets the standard size, which can be 10cm×10cm. After cutting out multiple pieces of the same batch of samples to be tested, fix the sample to be tested on the test bench of the air permeability tester, set the flow parameters of the tester, start the tester, record the parameters required for the airflow to pass through the sample, and obtain the air permeability parameters. Then, clamp the sample to be tested in the upper and lower clamps of the tensile testing machine, set the tensile speed to start the test until the sample is broken, record the parameters required for the sample to be broken, and obtain the tensile resistance parameters. Then, completely immerse the sample to be tested in clean water, keep it for a certain period of time, take out the sample and gently wipe the surface moisture with absorbent paper, quickly weigh the sample mass, measure it multiple times and record the sample parameters before and after water absorption, and obtain the water absorption parameters. Finally, fix the sample to be tested on the color fastness tester, dry rub the sample at a fixed pressure and speed, and wash the sample to be tested in the washing liquid according to standard washing conditions, use a colorimeter to record the area of ​​color shedding and other parameters, and obtain the color fastness parameters. These parameters are stored in the database as the basis for subsequent analysis and model training.

[0025] Figure 2 A schematic diagram of the quality structure of a composite cloth provided in an embodiment of the present invention.

[0026] Step S2: Figure 2 As shown, a quality assessment model is established, and the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value are normalized and weightedly summed to obtain a comprehensive quality score.

[0027] Among them, the comprehensive quality score is expressed as: ; in, For the overall quality rating, is the weight coefficient of each evaluation value, are the normalized evaluation values, is the serial number of each evaluation value; In this embodiment, the weight coefficient of each evaluation value is set to 0.25.

[0028] Furthermore, the calculation process of the air permeability evaluation value includes: Acquiring the air permeability parameters, wherein the air permeability parameters include the fabric area, test time, air volume and fabric components of the sample to be tested; Wherein, the air volume is the air volume of the gas passing through the sample to be tested; Dividing the air volume by the fabric area and the test time to obtain the air permeability per unit area; The air permeability per unit area is corrected according to the fabric components to obtain the air permeability evaluation value, which is expressed as: ; in, is the air permeability evaluation value, is the volume of air, is the cloth area, For test time, It is the air permeability correction factor, which is used to correct the impact of process differences and environmental conditions on air permeability. It is the proportion of breathable materials, such as 30% cotton fiber is breathable material.

[0029] Among them, in this embodiment, the air flow rate of the air permeability tester is 5L / min. Taking sample 1, sample 2 and sample 3 as examples, the sample size is 10cm×10cm, and the collected data is shown in Table 1. The calculated air permeability evaluation value of sample 1 is the highest, and the air permeability evaluation value of sample 3 is the lowest. According to the air permeability evaluation value, the air permeability per unit area and the composition of the cloth can be comprehensively considered, and the process parameters can be guided to adjust so that the product air permeability is stable within the target range to meet the diversified market needs, thereby improving the scientificity and flexibility of the composite cloth production management.

[0030] Table 1 Examples of air permeability parameters

[0031] Furthermore, the calculation process of the tensile strength evaluation value includes: Acquiring the tensile resistance parameters, wherein the tensile resistance parameters include the transverse cross-sectional area, the longitudinal cross-sectional area, the transverse maximum tensile force and the longitudinal maximum tensile force of the sample to be tested; Among them, the maximum transverse tension is the maximum tension in transverse stretching, and the maximum longitudinal tension is the maximum tension in longitudinal stretching; Dividing the maximum transverse tensile force by the transverse cross-sectional area to obtain the transverse tensile strength; Dividing the longitudinal maximum tensile force by the longitudinal cross-sectional area to obtain the longitudinal tensile strength; The transverse tensile strength and the longitudinal tensile strength are weighted and summed to obtain the tensile resistance evaluation value, which is expressed as: ; in, is the tensile strength evaluation value, is the maximum lateral tensile force, is the transverse cross-sectional area, is the maximum longitudinal tensile force, is the longitudinal tensile strength, is the weight of transverse and longitudinal tensile strength.

[0032] The weights of transverse and longitudinal tensile strength are set according to the purpose of the fabric. Assuming that the composite fabric sample 4 used to make protective clothing needs to provide a stronger tensile strength at the shoulder when stretched, the weights can be set If the width of the sample 4 to be tested is 10 cm, the length is 20 cm, and the thickness is 0.1 cm, then the cross-sectional area is 1 , the longitudinal cross-sectional area is 2 In the tensile test, the maximum transverse tensile force was 500N, the maximum longitudinal tensile force was 600N, and the tensile resistance evaluation value was calculated to be 420 .

[0033] By calculating the tensile strength evaluation value, the difference in tensile strength between the transverse and longitudinal directions is comprehensively considered, making the evaluation result more comprehensive and applicable to different types of composite fabrics. At the same time, the weight can be adjusted according to specific uses (such as clothing, protection and industry), which improves the applicability of tensile strength evaluation and thus enhances the flexibility of composite fabric production management.

[0034] Furthermore, the calculation process of the water absorption evaluation value includes: Acquiring the water absorption parameters, wherein the water absorption parameters include a first cloth weight, a second cloth weight, a cloth area, a cloth thickness, and a cloth component; Wherein, the first cloth weight is the cloth weight of the sample to be tested in a dry state, and the second cloth weight is the cloth weight of the sample to be tested after absorbing water; Subtract the weight of the first cloth from the weight of the second cloth and divide the result by the area of ​​the cloth to obtain the water absorption rate per unit area; Dividing the water absorption per unit area by the thickness of the cloth to obtain the water absorption per unit thickness; The water absorption rate per unit thickness is corrected according to the fabric components to obtain the water absorption evaluation value, which is expressed as: ; in, is the water absorption evaluation value, is the second cloth weight, is the first cloth weight, is the cloth area, is the thickness of the cloth, is the fiber density per unit area, is the proportion of non-absorbent material.

[0035] Specifically, suppose there is a sample to be tested 5, and the cloth area is 0.01 The cloth thickness is 2mm, composed of 70% cotton and 30% polyester, and the fiber density per unit area is 1.2 , the weight of the first cloth is 20g, and the weight of the second cloth is 23g. The water absorption per unit area is calculated to be 300 , water absorption per unit thickness is 150 , the water absorption evaluation value is about 178.57 It can be observed that the corrected water absorption evaluation value combines the thickness and material composition of the fabric, which can fully reflect the water absorption performance of the fabric and is applicable to a variety of composite fabrics, such as towels with high water absorption requirements or waterproof fabrics with low water absorption. Based on this quantitative indicator, it provides a reference for the quality evaluation of composite fabrics, thereby improving the flexibility of composite fabric production management.

[0036] Furthermore, the calculation process of the color fastness evaluation value includes: Acquire the color fastness parameter, wherein the color fastness parameter includes a first cloth area, a second cloth area, a first brightness value, a first chromaticity value, a second brightness value, and a second chromaticity value; Wherein, the first cloth area is the cloth area of ​​the sample to be tested before rubbing, and the second cloth area is the cloth area of ​​the sample to be tested whose color falls off after rubbing; the first brightness value and the first chromaticity value are the brightness and chromaticity of the sample to be tested before washing, and the second brightness value and the second chromaticity value are the brightness and chromaticity of the sample to be tested after washing; Calculating the ratio of the second fabric area to the first fabric area to obtain rubbing color fastness; Calculate the color change degree before and after washing according to the first brightness value, the first chromaticity value, the second brightness value, and the second chromaticity value to obtain the washing color fastness; The color fastness evaluation value is obtained by weighted summing the rubbing color fastness and the washing color fastness, which is expressed as: ; in, is the color fastness evaluation value, is the second cloth area, is the first cloth area, is the color difference value, is the maximum color difference value, and They are the weighting factors for color fastness to rubbing and color fastness to washing respectively.

[0037] Among them, the color difference value It is expressed as: ; in, is the first brightness value before washing, and is the first chromaticity value before washing, is the second brightness value after washing, and It is the second chromaticity value after washing.

[0038] Specifically, assuming that there is a sample to be tested 6, the first cloth area is 10 , the second cloth area is 1 , then the rubbing color fastness is 0.9. The first brightness value and the first chromaticity value before washing are , , The second brightness value and the second chromaticity value after washing are , , ,set up is 10, the color fastness evaluation value is 0.654. and The values ​​were set to 0.6 and 0.4 respectively, and the color fastness evaluation value was 0.8016. By comprehensively considering multiple factors of dry friction and wet friction, the comprehensiveness of the color fastness evaluation value was improved, which could meet the application requirements of different composite fabrics, such as workwear with high washability or sportswear with high friction resistance, and provide a reference for the quality evaluation of composite fabrics, thereby improving the flexibility of composite fabric production management.

[0039] Step S3: Obtain external market factors, which include seasonal factors, price fluctuations, random events and historical demand, and build a prediction model based on the external market factors. The prediction model is used to predict the demand for composite fabrics.

[0040] The prediction model may be a Random Forest model, an XGBoost model, or an LSTM model.

[0041] Specifically, the demand for composite fabrics is usually affected by a variety of external factors. For example, the demand for composite fabrics with warm-keeping functions increases in winter, while the demand for composite fabrics with sun protection or breathability is higher in summer; changes in the price of composite fabrics also directly affect market demand, such as price reductions may stimulate demand growth. In addition, random events (such as natural disasters or fashion trends) often lead to short-term fluctuations in market demand; historical demand data is an important basis for forecasting models. Therefore, external market factors specifically include: extracting timestamps (such as months and quarters) as seasonal factors, collecting historical prices of composite fabrics and their fluctuation ranges as price fluctuations, marking key time points as random events to quantify the impact of sudden factors, and collating monthly, quarterly or annual sales data as historical demand to provide demand trends and periodic references. Taking these factors as the input of the forecasting model, the forecasting model outputs the demand for composite fabrics at the next moment, which can predict demand changes in advance and reduce inventory pressure.

[0042] Step S4: Evaluate internal production factors to obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite fabric, production efficiency and working environment.

[0043] Furthermore, the production constraints include: The process difficulty constraint is used to limit the upper limit of the temperature and pressure of the production equipment according to the process difficulty, and is expressed as: ;

[0044] in, is temperature; The difficulty value of the process evaluated by experts ranges from 1 to 5, with higher difficulty giving higher scores; is the maximum temperature; is the initial upper limit of temperature, which can be set to 300℃; is the influence coefficient, which can be set to 20℃ and 0.1MPa; For pressure; is the maximum pressure; is the initial upper limit of pressure, which can be set to 2MPa; The production efficiency constraint is used to limit the upper limit of the frequency and load rate of the production equipment according to the production efficiency, and is expressed as: ; in, The frequency of the production equipment; The automation level of the production line and the operator proficiency of the workers evaluated by experts, ranging from 1 to 5, with higher efficiency being higher. is the highest frequency; It is the initial upper limit of frequency, which can be set to 50HZ; is the gain coefficient, which can be set to 10HZ and 10%; is the load factor; is the maximum load rate; It is the initial upper limit of the load rate, which can be set to 50%; The working environment constraint is used to limit the upper limit of the operating time of the production equipment according to the working environment, and is expressed as: ; in, is the operating time of the production equipment; It is a comprehensive evaluation value of the temperature, humidity range and noise level evaluated by experts, ranging from 1 to 5, with a higher score representing a more suitable environment; is the maximum operating time; The initial upper limit of the running time can be set to 2 hours; is the gain factor, which can be set to 1 hour; Specifically, the more difficult the process is, the more stringent the temperature, pressure and other parameters may be, and more precise control is needed. Through the process difficulty constraint, the upper limit of temperature and pressure of the production equipment is dynamically adjusted to match the specific process requirements. For more difficult processes, the control range can be automatically tightened to ensure the accuracy of key parameters. The higher the production efficiency, the higher the load and frequency the equipment can bear. Through the production efficiency constraint, the production equipment can dynamically adjust the upper limit of frequency and load rate according to the automation level of the production line and the proficiency of the workers, avoiding the overload of equipment due to excessive frequency and load in inefficient production lines. In addition, temperature, humidity and noise have a great impact on the continuous operation of the equipment. By setting the working environment constraint and dynamically adjusting the upper limit of the equipment operation time, the equipment operation time is limited to reduce equipment loss and maintenance costs, thereby improving equipment utilization and production flexibility.

[0045] Step S5: obtaining workload parameters and process parameters of production equipment, and constructing a production model according to the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite fabric; The production model is represented as: ; in, For production volume, is the workload parameter, is the process parameter, is the production function. The production value can be obtained based on the results of the actual factory or can be fitted using the nonlinear regression method.

[0046] Step S6: Calculate the production balance rate according to the demand for the composite cloth and the production of the composite cloth; use a particle swarm optimization algorithm to optimize the production balance rate and the comprehensive quality score to obtain the optimized workload parameters and process parameters.

[0047] Furthermore, the calculation process of the production balance rate includes: The inventory of the previous cycle and the target inventory are obtained, and the production balance rate is calculated according to the inventory of the previous cycle, the target inventory, the demand for the composite cloth and the production of the composite cloth, which is expressed as: ; in, is the production balance rate, is the production volume of the composite fabric, is the inventory volume of the previous period, is the demand for the composite fabric, is the target inventory quantity.

[0048] Specifically, is 0, indicating that the total supply completely matches the demand. If it is greater than 0, it means that the total supply exceeds the demand, there is a risk of oversupply, and the production strategy should be adjusted. Less than 0 means that the total supply is lower than the demand, there is a gap between supply and demand, and capacity management needs to be improved. Assuming that the inventory in the previous cycle is 500kg, the target inventory is 400kg, the demand for composite fabrics in the current cycle is 800kg, and the production of composite fabrics in the current cycle is 600kg, the calculated production balance rate is -8.33%, indicating that the total supply is insufficient to meet the demand and target inventory, and the production volume needs to be increased to balance supply and demand. The production balance rate can be used to evaluate the rationality of the production plan in real time, and dynamically adjust the production rhythm to help realize intelligent scheduling and optimization of the entire process, thereby improving the flexibility of composite fabric production management.

[0049] Furthermore, the decision space of the particle swarm optimization algorithm includes: A process parameter space, used to adjust the process parameters affecting the comprehensive quality score; the process parameters include the temperature and pressure of the production equipment; The workload parameter space is used to adjust the workload parameters that affect the production balance rate; the workload parameters include the frequency, load rate and operating time of the production equipment.

[0050] Table 2 Example of decision space range

[0051] Specifically, each particle is represented as a vector. In this embodiment, the decision space range of the particle is shown in Table 2. The decision space range can be changed according to the actual situation. The particles in the parameter space can also be added and deleted according to the actual situation. For example, the coating thickness and curing time for the quality of the composite cloth can be added to the particle group according to production requirements and optimized accordingly. In the production optimization process, the particle swarm optimization algorithm can effectively search for the optimal production parameter combination by considering process parameters and workload parameters, so that it can quickly respond to different market demand changes and balance production quality and production efficiency. For example, high temperature or high pressure may help improve the strength or comfort of the composite cloth. Adjusting these parameters can improve production quality, thereby improving the flexibility of composite cloth production management.

[0052] Furthermore, the objective function of the particle swarm optimization algorithm is expressed as: ; in, is the target value after maximization, Score the overall quality. is the normalized production balance rate, is the normalized production cost, , and is the weight coefficient, is the decision space of the particle swarm optimization algorithm.

[0053] Specifically, the objective function is used to evaluate the fitness of each particle, that is, the performance of each particle's solution in optimizing the production of composite fabrics. , and They are set to 0.4, 0.4 and 0.2 respectively, the number of iterations is set to 400, the target value before optimization is 0.65, and the target value after optimization is 0.72, which shows that the comprehensive optimization target is effectively improved. According to the set objective function, the comprehensive quality score, production balance rate and production cost can be comprehensively considered, avoiding the problem of excessive pursuit of quality and neglect of cost, thereby improving the flexibility of composite fabric production management.

[0054] The present invention collects quality parameters and establishes a quality assessment model to ensure that key indicators such as the air permeability, tensile strength, water absorption and color fastness of the product can be accurately quantified, thereby improving the comprehensiveness of product quality assessment. The demand forecasting model is constructed in combination with external market factors, as well as the analysis of internal production factors and the setting of constraints, to ensure the scientific nature and market adaptability of production planning. At the same time, the production balance rate is calculated using the demand forecasting model and the production model, which optimizes the matching degree between production volume and demand volume, and reduces inventory and resource waste. Finally, the particle swarm optimization algorithm is introduced to jointly optimize the production balance rate and the comprehensive quality score, dynamically adjust the workload parameters and process parameters of the production equipment, and realize efficient resource allocation and refined production management, thereby improving production efficiency and the flexibility of composite fabric production management, and enhancing the market competitiveness and comprehensive benefits of the enterprise.

[0055] Embodiment 2 is as follows: Company A is an enterprise specializing in the production and processing of composite fabrics. It mainly produces composite fabric materials for sportswear and functional textiles. However, with the diversification of market demand and the intensification of competition, Company A faces many production management challenges. For example, due to the influence of random events, the company's production plan is difficult to adapt to market changes in a timely manner, and supply and demand imbalances or inventory backlogs often occur. In order to cope with the above problems, Company A urgently needs a new solution to improve the flexibility of composite fabric production management. Based on the same inventive concept as a composite fabric production management optimization method based on a data module in the aforementioned embodiment, the present invention also provides a composite fabric production management optimization system based on a data module, and applies this system to Company A, including: Figure 3A schematic diagram of the structure of a composite fabric production management optimization system based on a data module provided in an embodiment of the present invention.

[0056] like Figure 3 As shown, a composite fabric production management optimization system based on a data module includes: A data acquisition module is used to collect the composite fabric quality parameters of the sample to be tested; A quality assessment module, used to establish a quality assessment model, wherein the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value are normalized and weightedly summed to obtain a comprehensive quality score; Table 3 Evaluation results example

[0057] Among them, in this embodiment, a complete quality evaluation is performed on the sample A to be tested through the quality evaluation module. The sample A to be tested is a composite fabric for high-end sportswear, which is required to have excellent air permeability and tensile strength to meet the high requirements of sportswear for comfort and durability. The evaluation results of the sample A to be tested are shown in Table 3. If the comprehensive quality score exceeds 0.8, it is judged to be excellent. According to Table 3, the comprehensive quality score is 0.855, so sample A is judged to be a composite fabric with excellent quality. In particular, the air permeability and tensile strength indicators are outstanding, which meets the needs of sportswear.

[0058] A demand calculation module is used to obtain external market factors, including seasonal factors, price fluctuations, random events and historical demand, and to build a forecasting model based on the external market factors, wherein the forecasting model is used to forecast the demand for composite fabrics; Among them, in this embodiment, the LSTM model is selected as the prediction model, and the LSTM model is compared with other models. As shown in Table 4, it can be seen that the LSTM model shows the lowest prediction error in both MAE and RMSE, indicating that its prediction accuracy is higher and it can well capture the characteristics of demand changes, thereby providing a reliable basis for production planning.

[0059] Table 4 Comparison of model results

[0060] A production calculation module is used to evaluate internal production factors and obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite cloth, the production efficiency and the working environment; obtain the workload parameters and process parameters of the production equipment, and build a production model according to the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite cloth; The parameter optimization module calculates the production balance rate according to the demand for the composite cloth and the production of the composite cloth; and uses a particle swarm optimization algorithm to optimize the production balance rate and the comprehensive quality score to obtain the optimized workload parameters and process parameters.

[0061] Table 5 Comparison of key indicators before and after optimization

[0062] Specifically, since fabric quality data must be obtained through real experiments in each iteration, in order to reduce the workload, sufficient fabric test data is collected through experiments in the early iterations. The LSTM model is also used to predict the fabric quality score based on the process parameters and workload parameters. The error of the trained LSTM model is 10.5%, which can well predict the fabric quality score.

[0063] The system of the present invention is compared with the original non-optimized solution of Company A. As shown in Table 5, the production balance rate, comprehensive quality score and production cost are improved to a certain extent, indicating that the response to the market after optimization is more accurate, and it can flexibly adapt to environmental changes, effectively reduce production costs, and improve the production quality of composite fabrics, enhance the market competitiveness of enterprises, and improve the flexibility of composite fabric production management.

[0064] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A composite fabric production management optimization method based on a data module, characterized in that: include: Collecting composite fabric quality parameters of the sample to be tested, wherein the composite fabric quality parameters include air permeability parameters, tensile strength parameters, water absorption parameters and color fastness parameters; Establishing a quality assessment model, the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; normalizing the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value and performing weighted summation to obtain a comprehensive quality score; Acquire external market factors, wherein the external market factors include seasonal factors, price fluctuations, random events and historical demand, and construct a forecasting model based on the external market factors, wherein the forecasting model is used to forecast the demand for composite fabrics; Evaluate internal production factors to obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite cloth, production efficiency and working environment; obtain workload parameters and process parameters of the production equipment, and build a production model based on the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite cloth; Calculating a production balance rate according to the demand for the composite fabric and the production of the composite fabric; The production balance rate and the comprehensive quality score are optimized using a particle swarm optimization algorithm, and the optimized workload parameters and process parameters are output.

2. The composite fabric production management optimization method based on data module according to claim 1 is characterized in that: The calculation process of the air permeability evaluation value includes: Acquiring the air permeability parameters, wherein the air permeability parameters include the fabric area, test time, air volume and fabric components of the sample to be tested; Dividing the air volume by the fabric area and the test time to obtain the air permeability per unit area; The air permeability per unit area is corrected according to the fabric component to obtain the air permeability evaluation value.

3. The composite fabric production management optimization method based on data module according to claim 1 is characterized in that: The calculation process of the tensile strength evaluation value includes: Acquiring the tensile resistance parameters, wherein the tensile resistance parameters include the transverse cross-sectional area, the longitudinal cross-sectional area, the transverse maximum tensile force and the longitudinal maximum tensile force of the sample to be tested; Dividing the maximum transverse tensile force by the transverse cross-sectional area to obtain the transverse tensile strength; Dividing the longitudinal maximum tensile force by the longitudinal cross-sectional area to obtain the longitudinal tensile strength; The transverse tensile strength and the longitudinal tensile strength are weightedly summed to obtain the tensile resistance evaluation value.

4. The composite fabric production management optimization method based on data module according to claim 1, characterized in that: The calculation process of the water absorption evaluation value includes: Acquiring the water absorption parameters, wherein the water absorption parameters include a first cloth weight, a second cloth weight, a cloth area, a cloth thickness, and a cloth component; Wherein, the first cloth weight is the cloth weight of the sample to be tested in a dry state, and the second cloth weight is the cloth weight of the sample to be tested after absorbing water; Subtract the weight of the first cloth from the weight of the second cloth and divide the result by the area of ​​the cloth to obtain the water absorption rate per unit area; Dividing the water absorption per unit area by the thickness of the cloth to obtain the water absorption per unit thickness; The water absorption rate per unit thickness is corrected according to the fabric components to obtain the water absorption evaluation value.

5. The composite fabric production management optimization method based on data module according to claim 1, characterized in that: The calculation process of the color fastness evaluation value includes: Acquire the color fastness parameter, wherein the color fastness parameter includes a first cloth area, a second cloth area, a first brightness value, a first chromaticity value, a second brightness value, and a second chromaticity value; Wherein, the first cloth area is the cloth area of ​​the sample to be tested before rubbing, and the second cloth area is the cloth area of ​​the sample to be tested whose color falls off after rubbing; the first brightness value and the first chromaticity value are the brightness and chromaticity of the sample to be tested before washing, and the second brightness value and the second chromaticity value are the brightness and chromaticity of the sample to be tested after washing; Calculating the ratio of the second fabric area to the first fabric area to obtain rubbing color fastness; Calculate the color change degree before and after washing according to the first brightness value, the first chromaticity value, the second brightness value, and the second chromaticity value to obtain the washing color fastness; The color fastness evaluation value is obtained by weighted summing the rubbing color fastness and the washing color fastness.

6. The composite fabric production management optimization method based on data module according to claim 1 is characterized in that: The production constraints include: A process difficulty constraint, used to limit the upper limit of the temperature and pressure of the production equipment according to the process difficulty; A production efficiency constraint, used to limit the upper limit of the frequency and load rate of the production equipment according to the production efficiency; The working environment constraint is used to limit the upper limit of the operating time of the production equipment according to the working environment.

7. The composite fabric production management optimization method based on data module according to claim 1 is characterized in that: The calculation process of the production balance rate includes: The inventory of the previous cycle and the target inventory are obtained, and the production balance rate is calculated according to the inventory of the previous cycle, the target inventory, the demand for the composite cloth and the production of the composite cloth, which is expressed as: ； in, is the production balance rate, is the production volume of the composite fabric, is the inventory volume of the previous period, is the demand for the composite fabric, is the target inventory quantity.

8. The composite fabric production management optimization method based on data module according to claim 1, characterized in that: The decision space of the particle swarm optimization algorithm includes: A process parameter space, used to adjust the process parameters affecting the comprehensive quality score; the process parameters include the temperature and pressure of the production equipment; The workload parameter space is used to adjust the workload parameters that affect the production balance rate; the workload parameters include the frequency, load rate and operating time of the production equipment.

9. The composite fabric production management optimization method based on data module according to claim 1, characterized in that: The objective function of the particle swarm optimization algorithm is expressed as: ； in, is the target value after maximization, Score the overall quality. is the normalized production balance rate, is the normalized production cost, , and Weight coefficient, is the decision space of the particle swarm optimization algorithm.

10. A composite fabric production management optimization system based on data module, characterized in that: include: A data acquisition module is used to collect the composite fabric quality parameters of the sample to be tested; A quality assessment module, used to establish a quality assessment model, wherein the quality assessment model is used to output an air permeability assessment value, a tensile strength assessment value, a water absorption assessment value and a color fastness assessment value according to the quality parameters of the composite fabric; the air permeability assessment value, the tensile strength assessment value, the water absorption assessment value and the color fastness assessment value are normalized and weightedly summed to obtain a comprehensive quality score; A demand calculation module is used to obtain external market factors, including seasonal factors, price fluctuations, random events and historical demand, and to build a forecasting model based on the external market factors, wherein the forecasting model is used to forecast the demand for composite fabrics; A production calculation module is used to evaluate internal production factors and obtain production constraints, wherein the internal production factors include the difficulty of the process of producing the composite cloth, the production efficiency and the working environment; obtain the workload parameters and process parameters of the production equipment, and build a production model according to the production constraints, the workload parameters and the process parameters, wherein the production model is used to output the production volume of the composite cloth; The parameter optimization module calculates the production balance rate according to the demand for the composite cloth and the production of the composite cloth; and uses a particle swarm optimization algorithm to optimize the production balance rate and the comprehensive quality score to obtain the optimized workload parameters and process parameters.

Images