Textile Shrinkage Qualification Rate Detection Method Based on Dual Data Model Processing

Abstract

The present invention discloses a method for detecting the qualified rate of textile shrinkage based on dual data model processing. A shrinkage data model is constructed to obtain the shrinkage rate under different humidity environments, and the first shrinkage influencing factor is obtained. Then, a weight influence data model is constructed to obtain the weight influence factor. The comprehensive shrinkage rate of the test sample is obtained by constructing a model for obtaining the shrinkage rate influenced by the dual model. Compared with the prior art, the present invention first obtains the preliminary shrinkage rate under different humidity environments, which is more accurate than the shrinkage rate obtained by the existing method of direct complete immersion, and comprehensively considers the influence under different humidity environments. In particular, the present invention also constructs a weight influence data model, and obtains the final shrinkage rate through the comprehensive consideration of the dual model, further improving the accuracy of the obtained detection result. At the same time, the present invention uses the drying method to replace air drying, and sets the drying temperature and drying time correspondingly according to different situations, greatly improving the detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of textile detection, and particularly to a method for detecting the shrinkage qualification rate of textiles based on dual data model processing. Background Art

[0002] In the field of textile production, the shrinkage rate of textiles is a key quality indicator, which reflects the change in size of textiles during use. Traditional methods for detecting the shrinkage rate of textiles mainly include the wetting method, the distillation method, the heat treatment method, and the ultrasonic method. Taking the wetting method, which has the lowest cost and the widest application, as the research object, the conventional steps of the wetting method are as follows: putting a textile sample into water and soaking it for a period of time to make it fully absorb water, then taking out the sample, wrapping it with a dry towel and squeezing it to remove the excess water, and finally laying the sample flat on a dry platform and waiting for it to dry naturally. After drying, the size of the sample is measured and the shrinkage rate is calculated.

[0003] When the requirements for the shrinkage rate index of the sample to be detected are relatively high, such as silk samples, on the one hand, the above traditional methods are too rough in the detection method, resulting in the difficulty of ensuring the accuracy of the detection results, which may lead to unstable quality during the production process, thereby affecting the quality and sales of the products; on the other hand, the traditional detection methods need to go through the process of fully wetting textile fibers - wringing - natural drying during the operation process. This process takes a long time and has low efficiency, and there is also a problem of great damage to delicate samples.

[0004] Therefore, developing a detection method that can automatically, quickly, and accurately detect the shrinkage rate of textiles is of great significance for improving the production efficiency and quality control of textiles. Summary of the Invention

[0005] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing methods for detecting the shrinkage rate of textiles, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is to solve the problems that the accuracy of the detection results of the existing methods for detecting the shrinkage rate of textiles is difficult to guarantee on the one hand, and on the other hand, the time consumption is long, the efficiency is low, and the damage to delicate samples is large.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: A method for detecting the qualified rate of textile shrinkage based on dual data model processing, comprising the following steps: S1: Randomly select a sample from the textiles to be detected, and evenly cut several detection samples with the same size using an automatic cutting machine, and record the initial size A1 and weight H1 of the detection samples; S2: Set corresponding humidities for several humidity machines of the same model. After the humidities are constant, place the detection samples in different humidity machines with different humidities for humidity infiltration respectively; S3: After the infiltration is completed, take out the detection samples, and measure the size A2 and weight H2 of the detection samples at this time respectively; S4: Place each detection sample in a constant warm air blower for drying, take out the dried detection samples, and measure the size A3 and weight H3 of the detection samples at this time respectively; S5: Obtain the shrinkage rate S of the detection samples under different humidity infiltration conditions respectively; S6: Construct a shrinkage data model, input the shrinkage rate S under different humidity infiltration conditions, and obtain the first shrinkage influencing factor of the detection samples; S7: Construct a weight influence data model, and obtain the weight influence factor based on the weight H1 and weight H3, that is, the second shrinkage influencing factor of the detection samples; S8: Construct a dual model influence shrinkage rate acquisition model, input the first shrinkage influencing factor and the second shrinkage influencing factor, and obtain the comprehensive shrinkage rate S of the detection samples 综 ; S9: Compare the comprehensive shrinkage rate S 综 and the shrinkage qualified rate parameter to determine whether the shrinkage rate of the current sample is qualified.

[0009] As a preferred solution of the method for detecting the qualified rate of textile shrinkage based on dual data model processing according to the present invention, wherein: when setting corresponding humidities for several humidity machines of the same model, the set humidities are RH30%, RH50%, RH70% and RH100%; wherein, when placing the detection samples in the humidity machines for humidity infiltration, the infiltration time is not less than 30 min.

[0010] As a preferred solution of the method for detecting the qualified rate of textile shrinkage based on dual data model processing according to the present invention, wherein: place each detection sample in a constant warm air blower for drying while hanging it;

[0011] Among them, the drying temperature and drying time set by the warm air blower are respectively: Among them, T is the drying temperature, °C; t is the total drying duration, min; ρ is the fiber density of the detection sample, g / cm³; A2 is the size of the detection sample after infiltration is completed, cm 2 ; H1 is the weight of the detection sample before infiltration, g; H2 is the weight of the detection sample after infiltration, g.

[0012] As a preferred solution of the method for detecting the qualified rate of textile shrinkage based on dual data model processing according to the present invention, wherein: the constructed shrinkage data model is specifically: Among them, δ is the first shrinkage influence factor, and S 30% is the shrinkage rate obtained by infiltration at a humidity of RH30%, and S 50% is the shrinkage rate obtained by infiltration at a humidity of RH50%, and S 70% is the shrinkage rate obtained by infiltration at a humidity of RH70%, and S 100% is the shrinkage rate obtained by infiltration at a humidity of RH100%. 1.32, 1.47, 1.41, 1.65, 1.66 are dynamic adjustment constants, and dx is an integral operation with an integral constant of 0.

[0013] As a preferred scheme of the textile shrinkage qualification rate detection method based on dual data model processing described in the present invention, wherein: the constructed weight influence data model is specifically: Among them, η is the second shrinkage influence factor; H 1，RH30% is the initial weight of the test sample selected under the infiltration condition of RH30%, g; H 1，RH50% is the initial weight of the test sample selected under the infiltration condition of RH50%, g; H 1，RH70% is the initial weight of the test sample selected under the infiltration condition of RH70%, g; H 1，RH100% is the initial weight of the test sample selected under the infiltration condition of RH100%, g; H 3，RH30% is the weight of the test sample after drying under the infiltration condition of RH30%, g; H 3，RH50% is the weight of the test sample after drying under the infiltration condition of RH50%, g; H 3，RH70% is the weight of the test sample after drying under the infiltration condition of RH70%, g; H 3，RH100% is the weight of the test sample after drying under the infiltration condition of RH100%, g; 1.07, 1.24, 1.18, 1.181, 1.30 are dynamic adjustment constants, and dx is an integral operation with an integral constant of 0.

[0014] As a preferred scheme of the textile shrinkage qualification rate detection method based on dual data model processing described in the present invention, wherein: the constructed dual model influence shrinkage rate acquisition model is specifically: Among them, γ is the comprehensive shrinkage rate S 综 ; δ is the first shrinkage influence factor; η is the second shrinkage influence factor; 1.32, 0.87, 1.380, 1.381 are dynamic adjustment constants, and dx is an integral operation with an integral constant of 0.

[0015] As a preferred scheme of the textile shrinkage qualification rate detection method based on dual data model processing described in the present invention, wherein: when the comprehensive shrinkage rate S 综When the error of the shrinkage pass rate parameter is in (0, 0.05), it is determined that the shrinkage rate of the current sample is qualified.

[0016] Among them, the comprehensive shrinkage rate S 综 and the error of the shrinkage pass rate parameter are obtained through the following formula: Among them, γ is the error, S 综 is the comprehensive shrinkage rate, S 参 is the shrinkage pass rate parameter.

[0017] Advantages of the present invention: The present invention provides a method for detecting the shrinkage pass rate of textiles based on dual data model processing. A shrinkage data model is constructed to obtain the shrinkage rate under different humidity environments, and the first shrinkage influencing factor of the test sample is obtained. Then, a weight influence data model is constructed to obtain the weight influence factor. By constructing a dual-model influencing shrinkage rate acquisition model and inputting the first shrinkage influencing factor and the second shrinkage influencing factor, the comprehensive shrinkage rate of the test sample is obtained. Compared with the prior art, the present invention first obtains the preliminary shrinkage rate under different humidity environments, which is more accurate than the shrinkage rate obtained by the prior art's method of directly and completely soaking. The influence under different humidity environments is comprehensively considered. In particular, the present invention also constructs a weight influence data model, and the final shrinkage rate is obtained through the comprehensive consideration of the dual models, and the obtained test results are more accurate. At the same time, compared with the drying method of the prior art, the present invention uses a drying method for replacement, and the drying temperature and drying time are correspondingly set for different situations, greatly improving the detection efficiency, and solving the problems that the accuracy of the detection results of the existing textile shrinkage rate detection method is difficult to guarantee on the one hand, and the time-consuming and low efficiency, and the large damage degree of fine samples on the other hand. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0019] Figure 1 is the overall method flow chart of the method for detecting the shrinkage pass rate of textiles based on dual data model processing provided by the present invention. Detailed Embodiments

[0020] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0021] When obtaining the shrinkage rate of a sample during the textile product inspection process, the wetting method, which has the lowest cost and the widest application, is taken as the research object. On the one hand, due to the overly rough detection method of this traditional method, it is difficult to guarantee the accuracy of the detection results, which may lead to unstable quality during the production process, thereby affecting the quality and sales of the product. On the other hand, the traditional detection method needs to go through the following processes during operation: fully wetting the textile fibers - wringing - natural drying. This process takes a long time and has low efficiency. At the same time, there is also a problem of a large degree of damage to fine samples.

[0022] Therefore, please refer to Figure 1 , the present invention provides a method for detecting the shrinkage qualification rate of textiles based on dual data model processing, which is characterized by including the following steps:

[0023] S1: Randomly select a sample from the textiles to be detected, evenly cut several detection samples with the same size using an automatic cutting machine, and record the initial size A1 and weight H1 of the detection samples.

[0024] It should be noted that the sizes and textures of several detection samples cut by the automatic cutting machine can ensure the maximum consistency. Of course, there will definitely be slight differences. At this time, for the data processing of subsequent comparison operations, record the initial size A1 and weight H1 of each detection sample.

[0025] S2: Set corresponding humidities for several humidity machines of the same model. After the humidity is constant, place the detection samples in different humidity machines with different humidities for humidity infiltration.

[0026] Specifically, when setting corresponding humidities for several humidity machines of the same model, set the humidities to RH30%, RH50%, RH70%, and RH100%.

[0027] Among them, when the detection sample is placed in the humidity machine for humidity infiltration, the infiltration time is not less than 30 minutes.

[0028] Select several humidity machines of the same model, set them into different humidity environments, and obtain shrinkage comparison data for drying in different humidity environments.

[0029] An infiltration time of not less than 30 minutes can ensure that the detection sample in the humidity environment is completely infiltrated in the current environment, achieving the completeness of infiltration.

[0030] S3: After the infiltration is completed, take out the test sample and measure the size A2 and weight H2 of the test sample at this time respectively;

[0031] S4: Place each test sample in a constant temperature heater for drying. Take out the dried test sample and measure the size A3 and weight H3 of the test sample at this time respectively;

[0032] Furthermore, place each test sample in the air in the constant temperature heater for drying;

[0033] Among them, the drying temperature T and drying time t set by the heater are respectively: Among them, T is the drying temperature, °C; t is the total drying duration, min; ρ is the fiber density of the test sample, g / cm³; A2 is the size of the test sample after infiltration is completed, cm 2 ; H1 is the weight of the test sample before infiltration, g; H2 is the weight of the test sample after infiltration, g.

[0034] It should be noted that the basic mapping standard adopted in the present invention is: 10 cm 2 The drying temperature of the test sample is set to 35 °C and the total drying duration is set to 60 min; the drying temperature of the 50 g infiltrated test sample is set to 45 °C and the total drying duration is set to 40 min; the drying temperature of the infiltrated test sample with a fiber density of 1 g / cm³ is set to 40 °C and the total drying duration is set to 45 min.

[0035] Please refer to Table 1 below, which is a comparison table of the effects of the drying method of the present invention and the existing air drying:

[0036] Table 1: Comparison table of effects

[0037]

[0038] S5: Obtain the shrinkage rate S of the test sample under different humidity infiltration conditions respectively;

[0039] It should be noted that: the shrinkage rate S (%) = (original size A1 - current size A3) / original size A1 × 100%.

[0040] S6: Construct a shrinkage data model, input the shrinkage rate S under different humidity infiltration conditions, and obtain the first shrinkage influencing factor of the test sample;

[0041] Furthermore, the constructed shrinkage data model is specifically:

[0042]

[0043] Among them, δ is the first shrinkage influencing factor, S 30%Shrinkage rate obtained by soaking at humidity RH30%, S 50% Shrinkage rate obtained by soaking at humidity RH50%, S 70% Shrinkage rate obtained by soaking at humidity RH70%, S 100% Shrinkage rate obtained by soaking at humidity RH100%, 1.32, 1.47, 1.41, 1.65, 1.66 are dynamic adjustment constants, dx is an integral operation and the integral constant is 0.

[0044] It should be noted that when introducing this model into a computer, the present invention first takes into account that there are 4 basic influencing factors involved in the present invention, namely S 30% 、S 50% 、S 70% and S 100% . Focusing on the first output of the model, the second-order norm of the 4 influencing factors is adopted. In the fields of machine learning and data analysis, the second-order norm is often used to calculate the distance between two data points. Here, the first item actually obtains the "distance" of the 4 influencing factors, that is, how much the difference in the degree of mutual influence is. Since the present invention adopts the comprehensive situation under 4 different humidities, it is not difficult to understand that the first thing to consider is the "difference" of the 4 items; then focusing on the 2nd, 3rd, 4th, and 5th outputs, the present invention obtains the shrinkage rate comparison values under 4 different environments. The meanings expressed by these 4 values are actually the same. Under the condition of not considering accuracy, they can all be directly used to express the shrinkage rate of the test sample. Therefore, the average value of the 4 values can essentially also be used to directly express the shrinkage rate of the test sample. At the same time, this expression also comprehensively considers the mutual influence in 4 different situations. Then, in integral form, the maximum influence degree under different situations is obtained. Taking the second item as an example, the integral within (0 - S 30% ) is adopted, that is, the average shrinkage rate is a constant term. On this constant expression term, the maximum shrinkage influence expression under soaking at humidity RH30% is obtained, and then by analogy, the subsequent several outputs can be obtained.

[0045] Additionally, for each adjustment constant introduced in the above model of the present invention, the user can, on the premise of adopting the basic architecture of the model of the present invention, perform calculations through a computer to obtain other constant adjustment values that best suit the usage environment. What the present invention considers are the basic constant examples in these 4 environments of S 30% 、S 50% 、S 70% and S 100% . The user can make corresponding modifications to improve the current accuracy.

[0046] S7: Construct a weight influence data model, and obtain a weight influence factor based on weight H1 and weight H3, that is, the second shrinkage influence factor of the test sample;

[0047] Furthermore, the specifically constructed weight influence data model is as follows:

[0048]

[0049] where η is the second shrinkage influence factor; H 1，RH30% is the initial weight of the test sample selected under the RH30% infiltration condition, in g; H 1，RH50% is the initial weight of the test sample selected under the RH50% infiltration condition, in g; H 1，RH70% is the initial weight of the test sample selected under the RH70% infiltration condition, in g; H 1，RH100% is the initial weight of the test sample selected under the RH100% infiltration condition, in g; H 3，RH30% is the weight of the test sample after drying under the RH30% infiltration condition, in g; H 3，RH50% is the weight of the test sample after drying under the RH50% infiltration condition, in g; H 3，RH70% is the weight of the test sample after drying under the RH70% infiltration condition, in g; H 3，RH100% is the weight of the test sample after drying under the RH100% infiltration condition, in g; 1.07, 1.24, 1.18, 1.181, 1.30 are dynamic adjustment constants, dx is an integral operation and the integral constant is 0.

[0050] It should be noted that when introducing this model into a computer in the present invention, first, considering that weight occupies a certain influence degree in the shrinkage rate detection process, therefore, the present invention takes it as the second influence factor. Focusing on the first item output of the model, the second-order norm of the 4-item weight difference is adopted. In the fields of machine learning and data analysis, the second-order norm is often used to calculate the distance between two data points. Here, the first item actually obtains the "distance" of the 4-item weight difference. Because the present invention adopts the combination of 4 situations under different humidities, it is not difficult to understand that first, the "gap" of the 4-item weight difference needs to be considered; then focusing on the 2nd, 3rd, 4th, and 5th item outputs, the present invention obtains the weight difference comparison values under 4 different environments. The meanings expressed by these 4 items are actually the same. Under the condition of not considering accuracy, they can all be directly used to express the shrinkage rate of the test sample. Therefore, here, the same integral function x can be directly used for direct expression, which also simplifies the operation. This expression comprehensively considers the mutual influence under 4 different situations, and then adopts the integral form to obtain the maximum influence degree under different situations. Taking the 2nd item as an example, the integral within (0 - H 1，RH30% - H 3，RH30% ) is adopted to obtain the expression of the maximum weight difference influence under the RH30% infiltration of humidity, and then loop and analogize to obtain the subsequent item outputs.

[0051] Additionally, for each adjustment constant introduced in the above model of the present invention, on the premise of adopting the basic framework of the model of the present invention, the user can perform calculations through a computer to obtain other constant adjustment values that best suit the usage environment. What the present invention considers is S 30% 、S 50% 、S 70% and S 100% These are examples of the basic constants of the weight difference in these 4 environments. The user can make corresponding modifications to improve the current accuracy.

[0052] S8: Construct a double-model shrinkage rate acquisition model, input the first shrinkage influence factor and the second shrinkage influence factor, and obtain the comprehensive shrinkage rate S of the test sample 综 ;

[0053] Furthermore, the constructed double-model shrinkage rate acquisition model is specifically:

[0054]

[0055] where γ is the comprehensive shrinkage rate S 综 ; δ is the first shrinkage influence factor; η is the second shrinkage influence factor; 1.32, 0.87, 1.380, 1.381 are dynamic adjustment constants, and dx is an integral operation with an integral constant of 0.

[0056] It should be noted that when introducing this model on a computer, the present invention first considers that there are 2 specific factors affecting the shrinkage rate. Therefore, the basic model structure is a product. The main focus is on explaining the third output. In the third output, the overall influence degree of the first shrinkage influence factor and the second shrinkage influence factor is obtained, and integration is performed on (0 - 1) to obtain the influence degree of (δ + η) to the greatest extent under a certain reasonable degree.

[0057] Additionally, for each adjustment constant introduced in the above model of the present invention, on the premise of adopting the basic framework of the model of the present invention, the user can perform calculations through a computer to obtain other constant adjustment values that best suit the usage environment;

[0058] Additionally, the basic framework adopted in the third output of the present invention is (0 - 1) integration. The user can make corresponding modifications to improve the current accuracy.

[0059] S9: Compare the comprehensive shrinkage rate S 综 and the shrinkage qualification rate parameter to determine whether the shrinkage rate of the current sample is qualified.

[0060] It should be noted that when the error between the comprehensive shrinkage rate S 综 and the shrinkage qualification rate parameter is within (0, 0.05), it is determined that the shrinkage rate of the current sample is qualified;

[0061] Among them, the comprehensive shrinkage rate S 综 and the error of the shrinkage qualification rate parameter are obtained through the following formula:

[0062] Among them, γ is the error, S 综 is the comprehensive shrinkage rate, S 参 is the shrinkage qualification rate parameter.

[0063] In order to verify the technical effect of the present invention, effect verification is carried out on a simulation machine, and some of the obtained data tables are shown in Table 2 below:

[0064] Table 2: Data Table

[0065]

[0066] Based on the above Table 2, it can be clearly seen that the accuracy of the shrinkage rate obtained by using the present invention is higher, and the detection of samples is more stringent.

[0067] The present invention provides a method for detecting the shrinkage qualification rate of textiles based on dual data model processing. A shrinkage data model is constructed to obtain the shrinkage rate under different humidity environments, and the first shrinkage influencing factor of the test sample is obtained. Then, a weight influence data model is constructed to obtain the weight influence factor. By constructing a dual-model influence shrinkage rate acquisition model and inputting the first shrinkage influencing factor and the second shrinkage influencing factor, the comprehensive shrinkage rate of the test sample is obtained. Compared with the prior art, the present invention first obtains the preliminary shrinkage rate under different humidity environments, which is more accurate than the shrinkage rate obtained by the prior art's direct complete immersion method, and comprehensively considers the influence under different humidity environments. In particular, the present invention also constructs a weight influence data model, and obtains the final shrinkage rate through the comprehensive consideration of the dual models, further improving the accuracy of the obtained test results. At the same time, compared with the prior art's air-drying method, the present invention uses a drying method for replacement, and sets the drying temperature and drying time according to different situations, greatly improving the detection efficiency, and solving the problems that on the one hand, the accuracy of the detection results of the existing textile shrinkage rate detection method is difficult to guarantee, and on the other hand, it takes a long time, has low efficiency, and causes great damage to fine samples.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A textile shrinkage qualified rate detection method based on dual data model processing, characterized in that: The steps include: S1: Randomly select a sample from the textile to be tested, use an automatic cutting machine to evenly cut several test samples of the same size, and record the initial size A1 and weight H1 of the test sample; S2: Several humidity machines of the same type are set to corresponding humidity. After the humidity is constant, the test samples are placed in humidity machines with different humidity levels for humidity infiltration; S3: After the infiltration is completed, the test sample is taken out and the size A2 and weight H2 of the test sample are measured respectively; S4: placing each test sample in a constant-current heating machine for drying, taking out the dried test sample, and measuring the size A3 and weight H3 of the test sample at this time; S5: Obtain the shrinkage rate S of the test sample under different humidity infiltration conditions respectively; S6: construct a shrinkage data model, input the shrinkage rate S under different humidity infiltration conditions, and obtain the first shrinkage influencing factor of the test sample; S7: construct a weight influence data model, and obtain a weight influence factor based on the weight H1 and the weight H3, that is, the second shrinkage influence factor of the test sample; S8: Construct a dual-model shrinkage rate acquisition model, input the first shrinkage impact factor and the second shrinkage impact factor, and obtain the comprehensive shrinkage rate S of the test sample. 综 ; S9: Compare the comprehensive shrinkage rate S 综 and shrinkage qualified rate parameters to determine whether the current sample shrinkage rate is qualified; Among them, each test sample is suspended in a constant heater to be dried; Among them, the drying temperature and drying time set by the heater are: Where T is the drying temperature, °C; t is the total drying time, min; ρ is the fiber density of the test sample, g / cm 3 ; A2 is the size of the test sample after infiltration, cm 2 ; H1 is the weight of the test sample before infiltration, g; H2 is the weight of the test sample after infiltration, g; Among them, the basic mapping standard for setting the drying temperature and drying time of the heater is: 10cm 2 The drying temperature of the test sample was set to 35°C and the total drying time was set to 60 minutes; the drying temperature of the 50g soaked test sample was set to 45°C and the total drying time was set to 40 minutes; the fiber density was 1g / cm 3 The drying temperature of the infiltration test sample is set to 40°C and the total drying time is set to 45 minutes; The shrinkage data model constructed is specifically: Among them, δ is the first shrinkage impact factor, S 30％ The shrinkage rate obtained by infiltration at humidity RH30%, S 50％ The shrinkage rate obtained by infiltration at humidity RH50%, S 70％ The shrinkage rate obtained by infiltration at humidity RH70%, S 100％ is the shrinkage rate obtained by infiltration at humidity RH100%, 1.32, 1.47, 1.41, 1.65, 1.66 are dynamic adjustment constants, dx is the integral operation and the integral constant is 0; The weight impact data model constructed is specifically: Where η is the second shrinkage impact factor; H 1，RH30％ Initial weight of the test sample selected for RH30% infiltration condition, g; H 1，RH50％ Initial weight of the test sample selected for RH50% infiltration condition, g; H 1，RH70％ Initial weight of the test sample selected for RH70% infiltration condition, g; H 1，RH100％ Initial weight of the test sample selected for RH100% infiltration condition, g; H 3，RH30％ is the weight of the sample after drying under RH30% infiltration condition, g; H 3，RH50％ is the weight of the sample after drying under RH50% infiltration conditions, g; H 3，RH70％ is the weight of the sample after drying under RH70% infiltration condition, g; H 3，RH100％ is the weight of the test sample after drying under RH100% infiltration conditions, g; 1.07, 1.24, 1.18, 1.181, 1.30 are dynamic adjustment constants, dx is the integral operation and the integral constant is 0; The dual-model influence shrinkage rate acquisition model constructed is specifically: Among them, γ is the comprehensive shrinkage rate S 综 ; δ is the first shrinkage influence factor; η is the second shrinkage influence factor; 1.32, 0.87, 1.380, 1.381 are dynamic adjustment constants, dx is the integral operation and the integral constant is 0.

2. The method for detecting the qualified rate of textile shrinkage based on dual data model processing according to claim 1 is characterized in that: When several humidifiers of the same type are set to corresponding humidity, the humidity is set to RH30%, RH50%, RH70% and RH100%; Among them, when the test sample is placed in a humidity machine for humidity immersion, the immersion time shall not be less than 30 minutes.

3. The textile shrinkage qualified rate detection method based on dual data model processing according to claim 2 is characterized in that: When the comprehensive shrinkage rate S 综 When the error of the shrinkage qualified rate parameter is (0, 0.05), the shrinkage rate of the current sample is judged to be qualified; Among them, the comprehensive shrinkage rate S 综 The error of the shrinkage qualification rate parameter is obtained by the following formula: Among them, γ is the error, S 综 is the comprehensive shrinkage rate, S 参 It is the shrinkage qualification rate parameter.

Images