Fabric performance and process prediction method and system

Abstract

The invention discloses a fabric performance and process prediction method and system. The prediction method comprises the steps of establishing a feature domain data set, performing feature domain division and proportion statistics in a coil, and constructing a fabric one-way moisture conduction calculation model. The prediction system comprises four components, namely a component 1 fabric performance prediction component, a component 2 fabric process prediction component, a component 3 database management component and a component 4 user interface and interaction component, and can realize a fabric thermal-wet comfort performance-fabric process dual-prediction function; according to the method, under the condition that independent modeling does not need to be carried out on each kind of fabric, the thermal-wet comfort performance of wide fabrics can be accurately and rapidly predicted, and meanwhile, corresponding fabric process information can be predicted under the condition that specific functions of the fabrics are provided, so that the purposes of reducing the test amount, avoiding raw material waste, shortening the research and development period and improving the fabric quality are achieved.

Description

Technical Field

[0001] The present invention relates to the field of textile technology, and in particular to a method and system for predicting fabric performance and process, which can predict various performance parameters of a fabric based on input fabric design parameters, and provide a scientific basis for fabric design. Background Art

[0002] The development of knitting technology has made the application scope and development prospects of knitting products very broad. At the same time, with the development of computer technology, knitting computer-aided design systems use computers and graphics processing equipment to carry out design work, which can effectively improve design efficiency and shorten product development cycles. At present, there are pattern design software M1PLUS developed by Germany's STOLL company, Shima Seiki SDS-ONE APEX software developed by Japan's Shima Seiki company, and Internet textile CAD system iTDS1.0 developed by Jiangnan University. In the past, the research on fabric properties was mainly obtained through experimental tests. However, this method of using only experimental tests has many shortcomings, such as the need to consume a large amount of experimental materials and the time-consuming nature of a large number of repeated experiments. With the development of computer technology, using computers to build models for performance research has become a new hotspot. This research method saves time and cost, can improve efficiency, and optimizes experimental parameters after rapid computer simulation, which has strong practical value and practical significance.

[0003] However, current fabric design software basically does not have a performance prediction function, and fabric performance prediction mostly uses finite element simulation software, ANSYS, COMSOL, etc. for simulation calculations. Each type of fabric needs to be modeled separately, and the fabric modeling must be adjusted if there is a slight change in parameters; therefore, the present application proposes a fabric performance and process prediction method and system, which can accurately, quickly and extensively predict performance before fabric weaving, and can predict the fabric information under known fabric function conditions. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a method and system for predicting fabric properties and process.

[0005] The present invention provides a method for predicting fabric properties and processes, which realizes the prediction of fabric properties and the optimization of process parameters by constructing a feature domain data set, developing a strategy for statistically analyzing the types and proportions of feature domains in fabric coils, and establishing a single-conductor performance prediction formula; the method for predicting fabric properties and processes predicts fabric properties and fabric processes respectively; the method for predicting fabric properties comprises the following steps:

[0006] S1) Establish feature domain dataset

[0007] Solid Works was used to simulate the single-sided weft knitted fabric. According to the different yarn interlacing conditions, a complete fabric loop was divided into different feature domains according to categories, including single yarn domain, two yarn interlaced domain, three yarn interlaced domain, four yarn interlaced domain, five yarn interlaced domain, blank domain, single yarn plated domain, two yarn interlaced plated domain and blank plated domain. COMSOL was used to simulate the unidirectional moisture conduction performance of the feature domain and establish the feature domain data set.

[0008] S2) Count the types and proportions of feature domains in fabric loops

[0009] The steps of feature domain division and proportion statistics in fabric loops are as follows:

[0010] 1) Identify and determine a complete fabric loop;

[0011] 2) Divide into different characteristic domains according to the number of interwoven yarns in the coil;

[0012] 3) Use Photoshop software to mark different characteristic domains of the coil with different colors;

[0013] 4) Count the number and proportion of pixels occupied by different colors;

[0014] 5) Analyze and record the type of raw materials and the fineness of the raw materials used in each characteristic domain in the thickness direction of the fabric;

[0015] 6) Integrate the information of the interweaving ratio, horizontal length, vertical length, raw material type and raw material fineness obtained by the above statistics and measurements to construct a feature domain data set of the fabric and save it in the system for users to select corresponding information;

[0016] S3) Construct a fabric unidirectional moisture conduction calculation model

[0017] Combining the results in steps S1) and S2), a fabric unidirectional moisture conduction calculation model is constructed:

[0018] According to formula ①, the one-way transfer index of each coil can be calculated:

[0019]

[0020] Among them, O T is the one-way transmission index of the coil, a is the side length of the pixel 0.04 mm, O i is the one-way transfer index of the feature domain, i is the sequence number of the feature domain, and f is the proportion of the feature domain;

[0021] Substitute the coil one-way transmission index calculated in formula ① into the test fabric one-way transmission index calculation formula ②:

[0022]

[0023] Among them, P A is the fabric horizontal density, P B is the longitudinal density of the fabric, L is the specified length of 5 cm, and R is the radius of the test area of ​​4.5 cm;

[0024] For composite fabrics: The calculation formula of the performance index of a complete pattern cycle③:

[0025] O F =X1O T1 +X2O T2 +…X i O Ti ③

[0026] Among them, O F is the one-way transmission index of a complete pattern cycle, O Ti is the one-way transfer index of each coil; X i It is the number of each coil in a complete pattern cycle;

[0027] Substitute the one-way transfer index of a complete pattern cycle calculated in step formula ③ into the one-way transfer index calculation formula of composite fabric ④:

[0028]

[0029] Among them, O P is the one-way transmission index of the composite fabric, O F is the one-way transmission index of a complete pattern cycle; h is the flower height of a complete pattern; w is the flower width of a complete pattern;

[0030] The method for predicting fabric technology is specifically based on formula ① and formula ②, when the one-way transfer index of the fabric is known, the fabric transverse density, fabric longitudinal density, characteristic domain type and proportion can be reversely calculated; according to formula ③ and formula ④, when the one-way transfer index of the fabric is known, the flower height and flower width of a complete pattern in the fabric, as well as the number of each type of coil in a complete pattern cycle can be reversely inferred, and the fabric technology can be adjusted according to the fabric performance requirements.

[0031] A fabric performance and process prediction system includes a fabric performance prediction component, a fabric process prediction component, a database management component, and a user interface and interaction component; wherein:

[0032] The fabric performance prediction component includes a process parameter design module, a performance type selection module, a performance calculation module and a performance output module, which are used to predict the thermal and moisture comfort performance of the fabric;

[0033] The fabric process prediction component includes a performance selection module, a restriction information module, a process calculation module and a process output module, which are used to reversely predict the process information of the fabric;

[0034] The database management component stores and manages the entered data to ensure the integrity and security of the data;

[0035] The user interface and interactive components are used to provide an intuitive user interface, which facilitates the user to input parameters, view results and perform data analysis operations.

[0036] Furthermore, the process parameter design module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the performance type selection module is composed of a heat transfer unit, a thermal insulation unit, a breathability unit, a unidirectional moisture conductivity unit and a moisture permeability unit; the performance calculation module is composed of multiple performance prediction calculation formulas built into the system, and the multiple performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; the performance output module is composed of a performance type unit and a performance data unit.

[0037] Furthermore, the fabric type unit has built-in knitted fabric sub-unit and woven fabric sub-unit; the feature domain information unit has built-in type and performance index sub-unit, and proportion sub-unit; the raw material information unit has built-in yarn type sub-unit, fiber fineness sub-unit, unit sub-unit and F number sub-unit; the weaving process unit has built-in fabric transverse density sub-unit, fabric longitudinal density sub-unit, fabric gram weight sub-unit, fabric thickness sub-unit, composite fabric pattern width sub-unit, and composite fabric pattern height sub-unit.

[0038] Furthermore, the performance selection module is composed of a performance type unit and a performance parameter unit; the restriction information module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the process calculation module is composed of multiple performance prediction calculation formulas built into the system, and the multiple performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; the process output module outputs other fabric process information except the restriction information.

[0039] Furthermore, the performance type unit is composed of a heat transfer sub-unit, a thermal insulation sub-unit, a breathability sub-unit, a unidirectional moisture conductivity sub-unit and a moisture permeability sub-unit; the fabric type unit has a knitted fabric sub-unit and a woven fabric sub-unit; the feature domain information unit has a type and performance index sub-unit and a proportion sub-unit; the raw material information unit has a yarn type sub-unit, a fiber fineness sub-unit, a unit sub-unit and an F number sub-unit; the weaving process unit has a fabric transverse density sub-unit, a fabric longitudinal density sub-unit, a fabric gram weight sub-unit, a fabric thickness sub-unit, a composite fabric pattern width sub-unit and a composite fabric pattern height sub-unit.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] The fabric performance and process prediction method and system of the present invention have the following advantages:

[0042] (1) Reduce the amount of information that needs to be input, facilitate workers' operation, and provide convenient conditions for the fabric research and development process;

[0043] (2) It not only has the function prediction function, but also can predict fabric information through known functions and constraints, thus guiding the fabric weaving process;

[0044] (3) Accurately, quickly, and extensively predict fabric properties and weaving processes;

[0045] (4) Before fabric weaving, without the need to independently model each fabric, the thermal and moisture comfort properties of a wide range of fabrics can be accurately and quickly predicted. At the same time, the fabric information can be predicted under known fabric functional conditions, so as to reduce the amount of testing, avoid raw material waste, shorten the R&D cycle, and improve fabric quality.

[0046] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0048] Figure 1 It is a schematic diagram of the feature domain dataset;

[0049] Figure 2 It is a schematic diagram of a complete loop and characteristic domain of a weft plain knitted fabric;

[0050] Figure 3 It is a flow chart of a fabric performance and process prediction system;

[0051] Figure 4 Schematic diagram of the components for fabric performance prediction;

[0052] Figure 5 Schematic diagram of fabric process prediction components. DETAILED DESCRIPTION

[0053] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0054] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0055] Please refer to Figures 1 to 5 The embodiment of the present invention provides a fabric performance and process prediction method, which follows the progressive analysis idea of ​​starting from the feature domain, gradually deepening into the fabric coil structure, and finally expanding to the whole fabric. By constructing a feature domain data set, developing a statistical feature domain type and proportion strategy in the fabric coil, and establishing a single-conductor performance prediction formula, the fabric performance is accurately predicted and the process parameters are optimized; the fabric performance and process prediction method predicts the fabric performance and the fabric process respectively; the method for predicting fabric performance includes the following steps:

[0056] (1) Establishing feature domain dataset

[0057] Solid Works was used to simulate the single-sided weft knitted fabric. According to the yarn interlacing situation, a complete fabric loop can be divided into several different characteristic domains, including single yarn domain (D1), two yarn interlaced domain (D2), three yarn interlaced domain (D3), four yarn interlaced domain (D4), five yarn interlaced domain (D5), blank domain (DB), single yarn plated domain (D1-1), two yarn interlaced plated domain (D2-1) and blank plated domain (DB-1). COMSOL was used to simulate the unidirectional moisture conduction performance of the characteristic domain and establish the characteristic domain data set.

[0058] (2) Statistical analysis of the types and proportions of characteristic domains in fabric coils

[0059] Steps for feature domain division and proportion statistics in fabric loops:

[0060] 1) Identify and determine a complete fabric loop;

[0061] 2) Divide into different characteristic domains according to the number of interwoven yarns in the coil;

[0062] 3) Use Photoshop software to mark different characteristic domains of the coil with different colors;

[0063] 4) Count the number and proportion of pixels occupied by different colors;

[0064] 5) Analyze and record the type of raw materials and the fineness of the raw materials used in each characteristic domain in the thickness direction of the fabric;

[0065] 6) The interweaving ratio, horizontal length, vertical length, raw material type and raw material fineness obtained by the above statistics and measurements are integrated to construct a feature domain data set of the fabric and saved in the system for users to select corresponding information.

[0066] (3) Construct a unidirectional moisture conduction calculation model for fabrics

[0067] Combining the results in steps (1) and (2), a fabric unidirectional moisture conduction calculation model is constructed:

[0068] According to formula (1), the one-way transfer index of each coil can be calculated:

[0069]

[0070] Among them, O T is the one-way transmission index of the coil, a is the side length of the pixel point 0.04mm, O i is the one-way transfer index of the feature domain, i is the sequence number of the feature domain, and f is the proportion of the feature domain;

[0071] Substitute the coil unidirectional transmission index calculated in formula (1) into the test fabric unidirectional transmission index calculation formula (2):

[0072]

[0073] Among them, P A is the fabric horizontal density, P B is the longitudinal density of the fabric, L is the specified length of 5 cm, and R is the radius of the test area of ​​4.5 cm;

[0074] For composite fabrics: The performance index for a complete pattern cycle is calculated using the formula (3):

[0075] O F =X1O T1 +X2O T2 +…X i O Ti (3)

[0076] Among them, O F is the one-way transmission index of a complete pattern cycle, O Tiis the one-way transfer index of each coil; X i It is the number of each coil in a complete pattern cycle;

[0077] Substitute the one-way transmission index of a complete pattern cycle calculated in step formula (3) into the one-way transmission index calculation formula (4) of the composite fabric:

[0078]

[0079] Among them, O P is the one-way transmission index of the composite fabric, O F is the one-way transmission index of a complete pattern cycle; h is the flower height of a complete pattern; w is the flower width of a complete pattern;

[0080] The method for predicting fabric technology is specifically based on formula ① and formula ②, when the one-way transfer index of the fabric is known, the fabric transverse density, fabric longitudinal density, characteristic domain type and proportion can be reversely calculated; according to formula ③ and formula ④, when the one-way transfer index of the fabric is known, the flower height and flower width of a complete pattern in the fabric, as well as the number of each type of coil in a complete pattern cycle can be reversely inferred, and the fabric technology can be adjusted according to the fabric performance requirements.

[0081] A fabric performance and process prediction system can realize the dual prediction functions of fabric thermal and moisture comfort performance and fabric process; the system includes 4 components, namely component 1 fabric performance prediction component, component 2 fabric process prediction component, component 3 database management component and component 4 user interface and interaction component; wherein,

[0082] Fabric performance prediction component, including process parameter design module, performance type selection module, performance calculation module and performance output module, used to predict the thermal and moisture comfort performance of fabrics;

[0083] The fabric process prediction component includes a performance selection module, a restriction information module, a process calculation module and a process output module, which is used to reversely predict the process information of the fabric;

[0084] The database management component stores and manages the entered data to ensure the integrity and security of the data; users can manually or automatically enter fabric performance data and weaving process data into the system database; users can query and analyze the data in the database to understand the performance trend of the fabric and the improvement direction of the weaving process;

[0085] The user interface and interactive components are used to provide an intuitive user interface to facilitate users to perform operations such as parameter input, result viewing and data analysis; the system supports interactive operations between users and the system, such as parameter adjustment, result feedback, etc., to improve the flexibility and accuracy of the system.

[0086] In a preferred embodiment, the process parameter design module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the performance type selection module is composed of a heat transfer unit, a thermal insulation unit, a breathability unit, a unidirectional moisture conductivity unit and a moisture permeability unit; the performance calculation module is composed of multiple performance prediction calculation formulas built into the system, and the multiple performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; the performance output module is composed of a performance type unit and a performance data unit.

[0087] In a preferred embodiment, the fabric type unit has built-in knitted fabric sub-units (basic structure and pattern structure) and woven fabric sub-units; the feature domain information unit has built-in type and performance index sub-units and proportion sub-units; the raw material information unit has built-in yarn type sub-units, fiber fineness sub-units, units sub-units and F number sub-units; the weaving process unit has built-in fabric transverse density sub-units, fabric longitudinal density sub-units, fabric gram weight sub-units, fabric thickness sub-units, composite fabric pattern width sub-units, and composite fabric pattern height sub-units.

[0088] In a preferred embodiment, the performance selection module is composed of a performance type unit and a performance parameter unit; the restriction information module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the process calculation module is composed of multiple performance prediction calculation formulas built into the system, and the multiple performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; the process output module outputs other fabric process information except the restriction information.

[0089] In a preferred embodiment, the performance type unit is composed of a heat transfer sub-unit, a thermal insulation sub-unit, a breathability sub-unit, a unidirectional moisture conductivity sub-unit and a moisture permeability sub-unit; the fabric type unit has a built-in knitted fabric sub-unit (basic structure and pattern structure) and a woven fabric sub-unit; the feature domain information unit has a built-in type and performance index sub-unit and a proportion example sub-unit; the raw material information unit has a built-in yarn type sub-unit, a fiber fineness sub-unit, a unit sub-unit and an F number sub-unit; the weaving process unit has a built-in fabric transverse density sub-unit, a fabric longitudinal density sub-unit, a fabric gram weight sub-unit, a fabric thickness sub-unit, a composite fabric pattern width sub-unit and a composite fabric pattern height sub-unit.

[0090] The fabric performance and process prediction system of the present application includes the prediction of fabric performance and the prediction of fabric process.

[0091] The operating method for predicting fabric properties by the prediction system of the present application comprises the following steps:

[0092] 1) Enter the fabric performance prediction component;

[0093] 2) Inputting fabric process design information into the process parameter design module, including fabric structure type, feature domain information, raw material information and manufacturing process;

[0094] 3) Select the required predicted performance in the performance type selection module, including heat transfer performance, thermal insulation performance, unidirectional moisture conduction performance, air permeability performance and moisture permeability performance;

[0095] 4) Perform performance calculation through the performance calculation module;

[0096] 5) Output the calculation results in step 4) through the performance output module.

[0097] Among them, the system's simulation calculation program for fabric performance prediction includes:

[0098] import numpy as np

[0099] import pandas as pd

[0100] from sklearn.model_selection import train_test_split

[0101] from sklearn.preprocessing import PolynomialFeatures

[0102] from sklearn.linear_model import LinearRegression

[0103] from sklearn.metrics import mean_squared_error,r2_score

[0104] #Data loading

[0105] data = pd.DataFrame({

[0106] 'X1':[7.2,7.2,7.2,7.2,7.2,7.2,7.2,7.2,32.2,32.2,32.2,32.2,32.2,7.2,32.2,32.2,7.2,32.2,32.2,2.13,4.15],

[0107] 'X2':[0,0,7.2,0,7.2,7.2,7.2,7.2,7.2,7.2,7.2,7.2,0,0,7.2,7.2,7.2,7.2,32.2,4.15,2.13],

[0108] 'X3':[40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,44,43],

[0109] 'X4':[0,0,40,0,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,43,44],

[0110] 'X5':[49.02,49.02,49.02,49.02,59.52,59.52,59.52,59.52,55.56,55.56, 55.56,55.56,88.33,88.33,88.33,88.33,88.33,88.33,88.33,50.51,50.51],

[0111] 'X6':[192.5,192.5,385,192.5,500,577.5,962.5,385,383.63,383.63,767.26, 383.63,191.13,192.5,576.13,768.8,577.5,383.63,1150.89,253.48,253.48],

[0112] 'Y':[1,1,1.0003,1,0,0.8021,0,1,23.7114,21.4681,0,9.908,1,1,18.4362,17.6861,0.8568,45.6596,0,-1.6245,-4.2212]

[0113] })

[0114] #Independent variables and dependent variables

[0115] X=data[['X1','X2','X3','X4','X5','X6']]

[0116] Y=data['Y']

[0117] # Split the dataset

[0118] X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.25,random_state=42)

[0119] #Choose the degree of the polynomial

[0120] degree = 2

[0121] #Generate polynomial features

[0122] poly=PolynomialFeatures(degree=degree)

[0123] X_poly_train=poly.fit_transform(X_train)

[0124] X_poly_test=poly.transform(X_test)

[0125] #Create and train the model

[0126] model=LinearRegression()

[0127] model.fit(X_poly_train,Y_train)

[0128] #Predict and evaluate the model

[0129] Y_pred=model.predict(X_poly_test)

[0130] mse=mean_squared_error(Y_test,Y_pred)

[0131] r2=r2_score(Y_test,Y_pred)

[0132] print(f'Mean Squared Error:{mse}')

[0133] print(f'R^2Score:{r2}')

[0134] #Get the intercept

[0135] intercept = model.intercept_

[0136] #Get the column names of polynomial features

[0137] poly_feature_names=poly.get_feature_names_out(X.columns)

[0138] #Build a relation

[0139] relationship=f'Y={intercept:.4f}'

[0140] for iin range(1,X_poly_train.shape[1]):

[0141] relationship+=f'+{model.coef_[i]:.4f}*{poly_feature_names[i]}'

[0142] print("Relationship:",relationship)

[0143] The calculation process of the performance calculation module includes the following steps:

[0144] 1) Substitute the fabric process parameters into the characteristic domain performance prediction calculation formula, and the characteristic domain performance prediction calculation formula is as follows:

[0145] Y=8.4178-0.0003*X1+0.0005*X2+0.0000*X3+0.0003*X4-0.0002*X5-0.0002*X6+0.0034*X1^2+0.1755*X1 X2

[0146] -0.0140*X1 X3-0.0089*X1 X4+0.0121*X1 X5-0.0015*X1 X6

[0147] -0.0015*X2^2+0.0222*X2 X3+0.0198*X2 X4-0.0146*X2 X5

[0148] -0.0051*X2 X6+0.0040*X3^2+0.0118*X3 X4-0.0074*X3 X5

[0149] -0.0002*X3 X6-0.0239*X4^2+0.0044*X4 X5+0.0009*X4 X6+0.0015*X5^2-0.0001*X5

[0150] Among them, Y is the predicted value of the characteristic domain performance; X1-X6 represent the single fiber diameter of material 1, the single fiber diameter of material 2, the surface energy of material 1, the surface energy of material 2, the horizontal width of the characteristic domain and the thickness of the characteristic domain respectively;

[0151] 2) Substitute the characteristic domain performance prediction value calculated in step 1) into the unit area fabric performance index calculation formula, and the unit area fabric performance index calculation formula is as follows:

[0152]

[0153] Among them, O T is the structural performance index, a is the side length of the divided area; O is the characteristic domain performance index, i is the characteristic domain number, and f is the proportion of the characteristic domain;

[0154] 3) Substitute the unit area fabric performance index calculated in step 2) into the fabric overall performance calculation formula to obtain the fabric overall performance; the fabric overall performance calculation formula is as follows:

[0155]

[0156] Among them, P A is the fabric horizontal density, P B is the longitudinal density of the fabric, L is the specified length of 5 cm, and R is the radius of the test area of ​​4.5 cm;

[0157] 4) The calculation formula for the performance index of a complete pattern cycle of the composite fabric is as follows:

[0158] O F =X1O T1 +X2O T2 +…X i O Ti

[0159] Among them, O F is the performance index for a complete tread cycle, O Ti is the performance index for each structure; X i The number of each structure in a complete pattern cycle;

[0160] 5) Substituting the performance index of a complete pattern cycle calculated in step 4) into the composite fabric performance calculation formula to obtain the composite fabric performance; the composite fabric performance calculation formula is as follows:

[0161]

[0162] Among them, O P is the performance index of the composite fabric, O Fis the performance index of a complete pattern cycle; h is the flower height of a complete pattern; w is the flower width of a complete pattern;

[0163] Among them, when predicting other thermal and moisture comfort properties of fabrics, other performance parameters can be brought into the characteristic domain performance prediction calculation formula.

[0164] In a preferred embodiment, when predicting fabric technology through the prediction system of the present application, the user reversely predicts fabric technology information through the calculation formula of fabric performance index per unit area according to the expected performance type, performance parameters and level of the product and the input restriction information; the specific operation process includes the following steps:

[0165] 1) Enter the fabric process prediction component;

[0166] 2) Select the performance type and parameters in the performance selection module, the performance types include heat transfer, thermal insulation, air permeability, unidirectional moisture conduction and moisture permeability;

[0167] 3) Enter known process information in the restriction information module as restriction information; the restriction information includes fabric type, feature domain information, raw material information and weaving process. According to actual needs, select one or no more than three pieces of information to enter;

[0168] 4) Through the process calculation module, reverse process calculation is performed according to multiple performance prediction calculation formulas;

[0169] 5) Outputting the calculation result in step 4) through the process output module to obtain the process information other than the input information in the restriction information in step 3);

[0170] For example, the fabric type, feature domain information, and raw material information are input into the restriction information module, and after reverse calculation through the process calculation module, the relevant information of the weaving process is output through the process output module.

[0171] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0172] Embodiment 1:

[0173] This embodiment provides a method for establishing a feature domain dataset. Figure 1Solid Works was used to simulate the single-sided weft knitted fabric. According to the number of yarn interlacing, a complete loop can be divided into several different areas, including single yarn area (D1), two yarn interlacing area (D2), three yarn interlacing area (D3), four yarn interlacing area (D4), five yarn interlacing area (D5), blank area (DB), single yarn plating area (D1-1), two yarn interlacing plating area (D2-1) and blank plating area (DB-1). COMSOL was used to simulate the unidirectional moisture conduction performance of the characteristic domain and establish the characteristic domain data set.

[0174] Embodiment 2:

[0175] This embodiment provides a method for constructing a feature domain. Taking a plain knitted fabric as an example, the method includes:

[0176] 1) Identify and determine a complete fabric loop, such as Figure 2 S201 in;

[0177] 2) Divide into different characteristic domains according to the number of interlaced yarns in the coil, such as Figure 2 S202 in;

[0178] 3) Use Photoshop software to mark different characteristic domains of the coil with different colors. Figure 2 S203-S205 in;

[0179] 4) The number and proportion of pixels occupied by different colors are counted, which are 37.4%, 50.23%, and 12.17% respectively. The size of each pixel is 0.04 mm;

[0180] 5) Analyze and record the type and fineness of the raw materials used in each characteristic domain in the fabric thickness direction. The raw material used for the plain knitted fabric is 50D / 144F polyester fiber;

[0181] 6) The interweaving ratio, horizontal length, vertical length, raw material type and raw material fineness obtained by the above statistics and measurements are integrated to construct a feature domain data set of the fabric and saved in the system for users to select corresponding information.

[0182] Embodiment three:

[0183] The construction of the fabric unidirectional moisture conduction calculation model, taking weft plain knitted fabric as an example, includes:

[0184] According to formula (1), the one-way transfer index of each coil can be calculated:

[0185]

[0186] Among them, O Tis the one-way transmission index of the coil, a is the side length of the pixel point 0.04mm, O i is the one-way transfer index of the feature domain, i is the sequence number of the feature domain, and f is the proportion of the feature domain;

[0187] Substitute the coil unidirectional transmission index calculated in formula (1) into the test fabric unidirectional transmission index calculation formula (2):

[0188]

[0189] Among them, P A is the fabric horizontal density, P B is the longitudinal density of the fabric, L is the specified length of 5 cm, and R is the radius of the test area of ​​4.5 cm;

[0190] Embodiment 4:

[0191] This embodiment provides a fabric performance and process prediction system and operation flow, the system can realize the dual prediction function of fabric thermal and moisture comfort performance and fabric process, see Figure 3 .

[0192] When the user selects fabric performance prediction, the system will enter prediction model 1, that is, enter component 1 fabric performance prediction component, see Figure 4 .

[0193] The user inputs the process design information according to the system prompts. The process design parameter module consists of a fabric structure type unit, a feature domain information unit, a raw material information unit, and a weaving process unit. The fabric structure type unit has built-in knitted fabric subunits and woven fabric subunits. The feature domain information unit has built-in types and performance index subunits and proportion subunits. The raw material information unit has built-in yarn type subunits, fiber fineness subunits, unit subunits, and F number subunits. The weaving process unit has built-in fabric transverse density subunits, fabric longitudinal density subunits, fabric gram weight subunits, and fabric thickness subunits.

[0194] The user selects the performance type according to the needs. The performance type selection module consists of a heat transfer unit, a thermal insulation unit, a breathable unit, a unidirectional moisture conduction unit, and a moisture permeability unit;

[0195] The user clicks on performance calculation, and the system outputs the performance type and performance data and saves the results.

[0196] When the user selects fabric process prediction, the system will enter prediction model 2, that is, component 2 fabric process prediction component, see Figure 5 .

[0197] The user selects the performance type and performance parameters according to the system prompts. The performance type selection unit is composed of a heat transfer subunit, a heat insulation subunit, a breathable subunit, a unidirectional moisture conduction subunit, and a moisture permeability subunit;

[0198] The user inputs known process information as restriction information. The restriction information module consists of a fabric structure type unit, a feature domain information unit, a raw material information unit, and a weaving process unit. One or no more than three pieces of information are selected for input;

[0199] The fabric organization type unit has built-in knitted fabric subunits and woven fabric subunits; the feature domain information unit has built-in type and performance index subunits and proportion subunits; the raw material information unit has built-in yarn type subunits, fiber fineness subunits, unit subunits, and F number subunits; the weaving process unit has built-in fabric transverse density subunits, fabric longitudinal density subunits, fabric gram weight subunits, and fabric thickness subunits;

[0200] The user clicks on the process calculation, and the system outputs the calculation results and saves the results.

[0201] Embodiment five:

[0202] This embodiment provides a practical example of a fabric performance and process prediction system. Taking plated fabric as an example, the operation process given in the fourth embodiment is adopted and the operation is performed according to the feature domain division method of the second embodiment. Specifically:

[0203] S1. User logs into the system and creates a new file;

[0204] S2. In this embodiment, the prediction model is selected as fabric performance prediction;

[0205] S3. According to the product prediction type, the user selects the variable structure in the fabric process parameter design module: the fabric type selects the variable structure, and the feature domain information selects 7, 8, and 9 in the system built-in database. The corresponding unidirectional moisture conduction index is 20, 0, and 10 respectively (reference Figure 1 ), the characteristic domain ratios are 39.25%, 35.4%, and 25.38% respectively. The raw material information is polyester 50D / 12F yarn and polyester 50D / 144F yarn. The fabric transverse density is 15 coils / cm, the fabric longitudinal density is 23 coils / cm, and the fabric weight is 100g / m 2 , fabric thickness 0.47mm;

[0206] S4. The user selects unidirectional moisture conductivity in the performance selection module;

[0207] S5. The user clicks the performance calculation button and the system starts calculating;

[0208] S6. After the calculation is completed, the user clicks the performance output button, and the system displays that the unidirectional moisture conductivity coefficient of the product is 13.9;

[0209] S7. Users can save the product as needed.

[0210] Embodiment six:

[0211] This embodiment provides a practical example of a fabric performance and process prediction system. Taking plated fabric as an example, the operation process given in the fourth embodiment is adopted and the operation is performed according to the feature domain division method of the second embodiment. Specifically:

[0212] S1. User logs into the system and creates a new file;

[0213] S2. In this embodiment, the prediction model is selected as fabric performance prediction;

[0214] S3. According to the predicted product type, in the fabric process parameter design module, the user selects the variable structure for fabric type, selects 7, 8, and 9 for feature domain type in the system built-in database, and the air permeability index is 1100, 950, and 1900 respectively (reference Figure 1 ), the characteristic domain ratios are 30%, 20%, 25%, and 25% respectively. The raw material information is polyester 50D / 12F yarn and polyester 50D / 144F yarn. The fabric transverse density is 15 coils / cm, the fabric longitudinal density is 23 coils / cm, and the fabric weight is 100g / m 2 , fabric thickness 0.47mm;

[0215] S4. The user selects air permeability in the performance selection module;

[0216] S5. The user clicks the performance calculation button and the system starts calculating;

[0217] S6. After the calculation is completed, the user clicks the performance output button, and the system displays that the air permeability index of the product is 1245.5;

[0218] S7. Users can save the product as needed.

[0219] Embodiment seven:

[0220] This embodiment provides a practical example of a fabric performance and process prediction system. Taking a plain knitted fabric as an example, the operation flow given in the fourth embodiment is adopted and the operation is performed according to the feature domain division method of the second embodiment. Specifically:

[0221] S1. User logs into the system and creates a new file;

[0222] S2. In this embodiment, the prediction model is selected as fabric process prediction;

[0223] S3. In this embodiment, the performance type is unidirectional moisture conduction, and the unidirectional moisture conduction transfer index is 8.0478;

[0224] S4, in this embodiment, the fabric type selects basic structure; the feature domain types select 1-3 respectively; the raw material information selects polyester 50D / 144F yarn, and the fabric weight selects 140;

[0225] S5. The user clicks the process calculation button and the system starts calculation;

[0226] S6. After waiting for the calculation to be completed, the user clicks the performance output button, and the system will display the proportion of the product feature domain based on the calculation results, which may be: 35%, 50%, or 15%.

[0227] S7. Users can save the product as needed, or save it after adjustment.

[0228] The design process adopted by the simulation system for fabric design and function prediction of the present invention is more efficient and quick, thus saving production cost and cycle.

[0229] In the description of this specification, the terms "connection", "installation", "fixation" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0230] In the description of this specification, the description of the terms "one embodiment", "some embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0231] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting fabric properties and process, characterized in that: The prediction of fabric properties and the optimization of process parameters are achieved by constructing a feature domain data set, developing a statistical feature domain type and ratio strategy in fabric coils, and establishing a single-conductor performance prediction formula; the fabric performance and process prediction method predicts fabric properties and fabric process respectively; the method for predicting fabric properties includes the following steps: S1) Establish feature domain dataset Solid Works was used to simulate the single-sided weft knitted fabric. According to the different yarn interlacing conditions, a complete fabric loop was divided into different characteristic domains according to categories, including single yarn domain, two yarn interlaced domain, three yarn interlaced domain, four yarn interlaced domain, five yarn interlaced domain, blank domain, single yarn plated domain, two yarn interlaced plated domain and blank plated domain. COMSOL is used to simulate the unidirectional moisture conduction performance of the characteristic domain and establish a characteristic domain data set; S2) Count the types and proportions of feature domains in fabric loops The steps of feature domain division and proportion statistics in fabric loops are as follows: 1) Identify and determine a complete fabric loop; 2) Divide into different characteristic domains according to the number of interwoven yarns in the coil; 3) Use Photoshop software to mark different characteristic domains of the coil with different colors; 4) Count the number and proportion of pixels occupied by different colors; 5) Analyze and record the type of raw materials and the fineness of the raw materials used in each characteristic domain in the thickness direction of the fabric; 6) Integrate the information of the interweaving ratio, horizontal length, vertical length, raw material type and raw material fineness obtained by the above statistics and measurements to construct a feature domain data set of the fabric and save it in the system for users to select corresponding information; S3) Construct a fabric unidirectional moisture conduction calculation model Combining the results in steps S1) and S2), a fabric unidirectional moisture conduction calculation model is constructed: According to formula ①, the one-way transfer index of each coil can be calculated: Among them, O T is the one-way transmission index of the coil, a is the side length of the pixel 0.04 mm, O i is the one-way transfer index of the feature domain, i is the sequence number of the feature domain, and f is the proportion of the feature domain; Substitute the coil one-way transmission index calculated in formula ① into the test fabric one-way transmission index calculation formula ②: Among them, P A is the fabric horizontal density, P B is the longitudinal density of the fabric, L is the specified length of 5 cm, and R is the radius of the test area of ​​4.5 cm; For composite fabrics: The calculation formula of the performance index of a complete pattern cycle③: The F =X1O T1 +X2O T2 +…X i The Ti ③ Among them, O F is the one-way transmission index of a complete pattern cycle, O Ti is the one-way transfer index of each coil; X i It is the number of each coil in a complete pattern cycle; Substitute the one-way transfer index of a complete pattern cycle calculated in step formula ③ into the one-way transfer index calculation formula of composite fabric ④: Among them, O P is the one-way transmission index of the composite fabric, O F is the one-way transmission index of a complete pattern cycle; h is the flower height of a complete pattern; w is the flower width of a complete pattern; The method for predicting fabric technology is specifically based on formula ① and formula ②, when the one-way transfer index of the fabric is known, the fabric transverse density, fabric longitudinal density, characteristic domain type and proportion can be reversely calculated; according to formula ③ and formula ④, when the one-way transfer index of the fabric is known, the flower height and flower width of a complete pattern in the fabric, as well as the number of each type of coil in a complete pattern cycle can be reversely inferred, and the fabric technology can be adjusted according to the fabric performance requirements.

2. A fabric performance and process prediction system, characterized in that: It includes fabric performance prediction component, fabric process prediction component, database management component and user interface and interaction component; among them, The fabric performance prediction component includes a process parameter design module, a performance type selection module, a performance calculation module and a performance output module, which are used to predict the thermal and moisture comfort performance of the fabric; The fabric process prediction component includes a performance selection module, a restriction information module, a process calculation module and a process output module, which are used to reversely predict the process information of the fabric; The database management component stores and manages the entered data to ensure the integrity and security of the data; The user interface and interactive components are used to provide an intuitive user interface, which facilitates users to input parameters, view results and perform data analysis operations.

3. The fabric performance and process prediction system according to claim 2, characterized in that: The process parameter design module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the performance type selection module is composed of a heat transfer unit, a thermal insulation unit, a breathability unit, a unidirectional moisture conduction unit and a moisture permeability unit; the performance calculation module is composed of a plurality of performance prediction calculation formulas built into the system, and the plurality of performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; The performance output module is composed of a performance type unit and a performance data unit.

4. The fabric performance and process prediction system according to claim 3, characterized in that: The fabric type unit has built-in knitted fabric sub-unit and woven fabric sub-unit; the feature domain information unit has built-in type and performance index sub-unit and proportion sub-unit; the raw material information unit has built-in yarn type sub-unit, fiber fineness sub-unit, unit sub-unit and F number sub-unit; the weaving process unit has built-in fabric transverse density sub-unit, fabric longitudinal density sub-unit, fabric gram weight sub-unit, fabric thickness sub-unit, composite fabric pattern width sub-unit and composite fabric pattern height sub-unit.

5. The fabric performance and process prediction system according to claim 2, characterized in that: The performance selection module is composed of a performance type unit and a performance parameter unit; the restriction information module is composed of a fabric type unit, a feature domain information unit, a raw material information unit and a weaving process unit; the process calculation module is composed of a plurality of performance prediction calculation formulas built into the system, and the plurality of performance prediction calculation formulas include a feature domain performance prediction calculation formula, a unit area fabric performance index calculation formula and a fabric overall performance calculation formula; The process output module outputs other fabric process information except the restriction information.

6. The fabric performance and process prediction system according to claim 5, characterized in that: The performance type unit is composed of a heat transfer subunit, a thermal insulation subunit, a breathability subunit, a unidirectional moisture conductivity subunit and a moisture permeability subunit; the fabric type unit has a knitted fabric subunit and a woven fabric subunit; the feature domain information unit has a type and performance index subunit and a proportion subunit; the raw material information unit has a yarn type subunit, a fiber fineness subunit, a unit subunit and an F number subunit; the weaving process unit has a fabric transverse density subunit, a fabric longitudinal density subunit, a fabric gram weight subunit, a fabric thickness subunit, a composite fabric pattern width subunit and a composite fabric pattern height subunit.

Images