A functional fabric moisture permeability detection method and system

Abstract

The application discloses a kind of functional fabric moisture permeability detection method and system, it is related to textile performance detection technical field, method includes: the application environment of fabric moisture permeability is excavated, and environment scene set is constructed;Then based on environment scene set, the moisture permeability of target functional fabric is detected, generates M group moisture permeability detection parameter and M aggregate environment mark;Then extract target dynamic sweat feature sequence, combine parameter simulation and generate M moisture permeability simulation sequence;Finally, correlation mapping M aggregate environment mark, M moisture permeability simulation sequence and target sweat scene are used as moisture permeability detection result.The application solves the technical problem that the detection mode of traditional functional fabric is difficult to comprehensively and accurately reflect the related performance of material under different actual scenes and dynamic conditions, achieves to comprehensively and accurately detect the related performance of material under different actual scenes and dynamic conditions, meets the technical effect of precise evaluation and application demand.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of textile performance detection, in particular to a moisture permeability detection method and system for functional fabric. BACKGROUND

[0002] The moisture permeability of functional fabric directly affects the wearing comfort and human health, and its accurate detection is crucial for product research and application. In the prior art, moisture permeability detection is mostly carried out in a single or fixed environment, and traditional equipment is used to measure water vapor transmission rate and other parameters. These methods have played a certain role in stable laboratory environment, but with the improvement of performance requirements for functional fabric, the traditional detection technology has exposed limitations in application: as the actual diverse application scenarios and dynamic sweat characteristics are not considered, the moisture permeability of the fabric under different environments and sweat states cannot be fully reflected, resulting in incomplete and inaccurate data, which is difficult to meet the requirements of accurate evaluation and effective application of fabric moisture permeability. SUMMARY

[0003] The present application provides a moisture permeability detection method and system for functional fabric, which solves the technical problem that the traditional detection method of functional fabric cannot fully and accurately reflect the performance of the material under different actual scenarios and dynamic conditions.

[0004] In a first aspect, the present application provides a moisture permeability detection method for functional fabric, which comprises: performing application environment mining of fabric moisture permeability, and constructing an environment scenario set; performing moisture permeability performance detection and result aggregation marking on a target functional fabric based on the environment scenario set, generating M groups of moisture permeability performance detection parameters and M aggregation environment markers; extracting a target dynamic sweat feature sequence from a sweat feature mode set, and combining the M groups of moisture permeability performance detection parameters to perform dynamic visualization simulation of moisture permeability, generating M moisture permeability simulation sequences; and establishing a correlation mapping between the M aggregation environment markers, the M moisture permeability simulation sequences and a target sweat scenario, as a moisture permeability detection result.

[0005] In a second aspect of the present application, a moisture permeability detection system for functional fabric is provided, which comprises: an environmental scenario set construction module configured to perform application environment mining of fabric moisture permeability and construct an environmental scenario set; a moisture permeability performance detection execution module configured to perform moisture permeability performance detection on a target functional fabric based on the environmental scenario set and generate M sets of moisture permeability performance detection parameters and M aggregated environmental markers; a moisture permeability simulation sequence acquisition module configured to extract a target dynamic sweat feature sequence from a sweat feature mode set, perform dynamic visual simulation of moisture permeability in combination with the M sets of moisture permeability performance detection parameters, and generate M moisture permeability simulation sequences; and a moisture permeability detection result acquisition module configured to associate and map the M aggregated environmental markers with the M moisture permeability simulation sequences and a target sweat scenario as a moisture permeability detection result.

[0006] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] In the present application, the environmental scenario set is constructed, the target fabric is detected for moisture permeability performance based on the scenario, parameters and aggregated markers are generated, the dynamic sweat feature sequence is extracted, the dynamic visual simulation of moisture permeability is performed in combination with the detection parameters, and the aggregated environmental markers, the simulation sequences and the target sweat scenario are associated and mapped, so as to accurately detect the moisture permeability performance of the functional fabric under different environments and sweat scenarios, make the moisture permeability detection result of the functional fabric more accurate and reliable, and achieve the technical effect of comprehensively and accurately detecting the related performance of the material under different actual scenarios and dynamic conditions, and meet the precise evaluation and application requirements. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0009] Figure 1 is a flowchart of a moisture permeability detection method for functional fabric provided by the embodiments of the present application.

[0010] Figure 2 is a structural schematic diagram of a moisture permeability detection system for functional fabric provided by the embodiments of the present application.

[0011] Marked: environmental scenario set construction module 1, moisture permeability performance detection execution module 2, moisture permeability simulation sequence acquisition module 3, moisture permeability detection result acquisition module 4. DETAILED DESCRIPTION

[0012] This application provides a method and system for testing the moisture permeability of functional fabrics, which solves the technical problem that traditional testing methods for functional fabrics are difficult to comprehensively and accurately reflect the relevant performance of materials under different actual scenarios and dynamic conditions.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, a method for testing the moisture permeability of a functional fabric, wherein the method includes:

[0016] Step A100: Perform application environment mining for fabric moisture permeability and construct a set of environmental scenarios.

[0017] In this embodiment, fabric permeability refers to the performance of a functional fabric in allowing water vapor to pass through. Specifically, it is the ability of water vapor generated by sweat to be transferred from the inside to the outside of the fabric. It can be measured by parameters such as the amount of water vapor passing through the fabric per unit time. It is an important indicator reflecting the dryness and comfort of the skin when wearing the fabric.

[0018] Specifically, when exploring the application environment of fabric breathability, those skilled in the art first need to investigate the actual use scenarios of functional fabrics, covering environmental characteristics under different scenarios such as daily wear, sports, and work, focusing on collecting key parameters such as temperature, humidity, and airflow velocity. Specifically, when collecting parameter data, temperature sensors, humidity sensors, and airflow velocity sensors need to be deployed. Sensors are deployed on both the inner and outer sides of the fabric, with the inner side corresponding to areas prone to sweating, such as the armpits and back, which are in contact with the skin, and the outer side representing the outer surface of the fabric at the corresponding locations.

[0019] Meanwhile, in the key areas of typical scenarios such as living room, office and other indoor spaces, gym, outdoor running track and other sports scenes, workshop, outdoor work area and other working places, temperature sensors, humidity sensors and air flow speed sensors are arranged in the main range of human activities and near the ventilation openings to collect the temperature, humidity and air flow speed data of the inside and outside of the fabric and the surrounding environment in real time. For example, the temperature in the daily indoor scene is usually between 18-26℃, and the humidity is between 40-60%; the temperature in the outdoor sports scene may reach 25-35℃, the humidity is between 30-70%, and there is a certain air flow; the temperature in the outdoor scene in winter may be as low as -5-10℃, and the humidity is between 20-50%.

[0020] Next, based on the above collected key parameter data, representative environmental parameter combinations are selected to construct an environmental scene set. Specifically, first, the collected key parameter data such as the temperature, humidity and air flow speed of the inside and outside of the fabric are sorted, and the distribution range of each parameter and the frequency of occurrence in different daily, sports, work and other application scenarios are counted; then, based on the correlation between parameters, typical combinations are identified, such as 20℃, 50% humidity, 0.2m / s air flow in daily indoor scene, 30℃, 60% humidity, 0.8m / s air flow in sports, 10℃, 40% humidity, 0.5m / s air flow in low temperature environment, etc.; then, through clustering analysis, combinations with too high similarity are eliminated, and samples with significant differences are retained, and finally a plurality of environmental parameter combinations covering the main application scenarios are determined to construct the environmental scene set, so as to ensure that the subsequent detection can fully reflect the moisture permeability of the fabric in different actual environments.

[0021] By mining the environmental characteristics of actual application scenarios, the abstract use scenarios are converted into specific environmental parameter combinations that can be quantified and adjusted, and the environmental scene set formed provides a standardized test basis for subsequent detection of fabric moisture permeability in different environments.

[0022] Step A200: moisture permeability performance detection and result aggregation marking of target functional fabric based on the environmental scene set, generating M groups of moisture permeability performance detection parameters and M aggregated environmental markers.

[0023] Optionally, based on the obtained environmental scene set, then obtain the fabric test sample and fix it to the test platform, configure a unified sweat test sample, then traverse and adjust the environment and detect the moisture permeability, cluster the results to generate M groups of moisture permeability performance detection parameters, and combine the corresponding environmental parameters to generate M aggregated environmental markers, which are described in detail in A210-A250.

[0024] Step A300: extracting target dynamic sweat feature sequence in the sweat feature mode set, combining the M groups of moisture permeability performance detection parameters to perform dynamic visualization simulation of moisture permeability, and generating M moisture permeability simulation sequences.

[0025] In the embodiments of the present application, the sweat feature mode set is configured by collecting a plurality of sweat discharge data samples, generating a plurality of clustered sample clusters through similarity clustering, extracting any one of the clustered sample clusters, and performing mean value calculation on the data in the clustered sample cluster.

[0026] In an embodiment of the present application, first, sweat discharge data samples are collected and clustered to generate sample clusters, and a sweat feature mode set is configured through mean value calculation, and then modes are extracted therefrom and a target dynamic sweat feature sequence is configured under a preset time length, which is described in detail in A310-A340.

[0027] Next, based on the moisture permeability detection parameter, the water vapor transmission rate is analyzed, a simulation platform is constructed to generate a sweat discharge-evaporation simulation sequence, and a moisture permeability simulation sequence is generated after dryness evaluation and marking, which is described in detail in A350-A380.

[0028] Step A400: mapping the M aggregated environment markers to the M moisture permeability simulation sequences and the target sweat scenario as a moisture permeability detection result.

[0029] In the embodiments of the present application, the target sweat scenario is a scenario with specific sweat discharge characteristics obtained based on a plurality of sweat discharge data samples after similarity clustering, such as light sweating, moderate sweating, heavy sweating, and intermittent sweating. These scenarios correspond to different sweat discharge laws and are used to establish a correlation with the aggregated environment markers and the moisture permeability simulation sequence.

[0030] Specifically, first, the core parameters in the M aggregated environment markers are extracted, including environmental temperature, humidity, etc. These parameters are directly related to the formation logic of the exercise intensity parameter and the target sweat scenario. Exercise intensity determines the initial rate of sweat secretion, and exercise intensity is obtained by collecting sweat discharge data samples under different activity states, such as sitting, walking, and running. These samples cover sweat discharge conditions corresponding to different exercise intensities, and the unit is usually MET (metabolic equivalent). Environmental temperature and humidity affect the external conditions of sweat evaporation, and both define the dynamic characteristics of sweating, such as secretion amount and evaporation efficiency. Based on this, through the matching rules of exercise intensity interval and environmental parameter threshold, each aggregated environment marker is classified into the corresponding target sweat scenario, establishing a preliminary correlation between the environment and the scenario.

[0031] Next, trace back the construction premise of M moisture permeability simulation sequences: during simulation, preset environmental parameters temperature, humidity and exercise intensity input consistent with the aggregated environment label, corresponding to the sweat rate of the target sweat scenario. Therefore, taking environmental parameters + exercise intensity as the matching dimension, associate the aggregated environment label with the moisture permeability simulation sequence, and when the environmental temperature deviation of the two is ≤1℃, the relative humidity deviation is ≤5%, and the exercise intensity deviation is ≤0.2 MET, it is determined that it is the simulation result under the same condition. By traversing all labels and sequences, the pairing of environment label-simulation sequence is completed.

[0032] Finally, the target sweat scenario is used as the scene classification label of the association result, the aggregated environment label is used as the environment feature carrier, and the moisture permeability simulation sequence is used as the performance simulation data. The three are bound through the logical chain of scene definition-environment condition-performance, forming a complete moisture permeability detection result.

[0033] Through parameter matching and scene alignment, the abstract simulation data is directly associated with the actual use scene and environment condition, realizing the landing mapping of fabric moisture permeability performance from laboratory simulation to real application, and providing a complete basis for multi-dimensional association of scene-based performance evaluation of fabrics.

[0034] Further, the step A200 in the method provided by the embodiment of the present application comprises:

[0035] A210: Obtain a fabric test sample of the target functional fabric.

[0036] A220: Fix the fabric test sample to a test platform and configure a uniform sweat test sample.

[0037] A230: Traverse a plurality of groups of environment scenes in the environment scene set, and after adjusting the environment on the test platform, configure sweat on the first surface of the fabric test sample with the uniform sweat test sample, perform moisture permeability performance detection, and generate a plurality of groups of moisture permeability performance detection results.

[0038] A240: Cluster the plurality of groups of moisture permeability performance detection results according to a preset consistent deviation threshold, and respectively calculate the mean value of the moisture permeability performance parameters in the M clustering clusters obtained by clustering, to generate M groups of moisture permeability performance detection parameters.

[0039] A250: Merge the environment parameter ranges of all environment scenes corresponding to each clustering cluster in the M clustering clusters, to generate the M aggregated environment labels.

[0040] In the embodiment of the present application, the test platform is a device for fixing the fabric test sample, which can adjust the temperature, humidity, air flow speed and other environmental parameters, and is equipped with a steam generator and a water collection system to complete the fabric moisture permeability performance detection under different environment scenes.

[0041] Specifically, first, a sample with uniform specifications is cut from the target functional fabric as a fabric test sample, for example, a 10 cm x 10 cm flawless piece is selected to ensure that the fabric test sample can represent the overall material and structural characteristics of the fabric. The cut fabric test sample is fixed to the clamping device of the test platform to ensure that the sample is flat and wrinkle-free, and a uniform sweat test sample is configured, using a 0.9% sodium chloride solution to simulate human sweat, with the amount of each test controlled at 0.1 ml per square centimeter to ensure consistency of the sweat conditions.

[0042] Next, when traversing multiple sets of environmental scenarios in the environmental scenario set, the test platform adjusts to the parameters of each set of scenarios in turn, for example, first adjusting to a temperature of 20°C, a humidity of 50%, and an air flow speed of 0.2 m / s. After the environment stabilizes, the steam generator simulates the discharge of a uniform sweat test sample on the first side (the inner side) of the fabric test sample, while the water collection system on the second side (the outer side) begins to collect water vapor that has passed through the fabric. After 1 hour of continuous detection, the moisture permeability data under this scenario is recorded in g / h, and the specific steps are described in detail in A231. Then, follow the same process to complete the detection of the remaining sets of environmental scenarios, and finally generate multiple sets of moisture permeability detection results.

[0043] Then, the multiple sets of moisture permeability detection results are clustered according to a preset consistent deviation threshold of 5%: first, determine the specific values of the multiple sets of moisture permeability detection results, which are the moisture permeability data measured under different environmental scenarios in the above steps. Then, taking each result as a reference, calculate the deviation of each result from the reference value, which is the absolute value of the difference between the two values divided by the reference value. If the deviation of a certain result from the reference value is ≤5%, then the result and the reference value are classified into the same preliminary clustering group. Then, repeat the above calculation for all results in the preliminary clustering group to determine whether there are results with a deviation exceeding 5%, if so, remove them and match them with other groups. In this way, gradually merge all results with a deviation within 5%, and finally form multiple clustering clusters, with the moisture permeability detection results in each cluster having a mutual deviation of no more than 5%.

[0044] For example, assume that the environmental scenario set contains 15 sets of environmental scenarios, and that 6 of them have results in the range of 4.8-5.2 g / h, with a deviation of ≤5%, and are clustered into the first clustering cluster; 5 sets of results are in the range of 7.5-8.0 g / h, and are clustered into the second clustering cluster; and the remaining 4 sets of results are in the range of 2.1-2.3 g / h, and are clustered into the third clustering cluster, i.e. M=3. Calculate the mean value of the moisture permeability parameters in each clustering cluster, if the mean value of the first clustering cluster is 5.0 g / h, the second clustering cluster is 7.8 g / h, and the third clustering cluster is 2.2 g / h, then generate M=3 sets of moisture permeability detection parameters.

[0045] Finally, for each cluster, the environmental parameters of all the environmental scenes it contains are collected, including temperature, humidity, air flow speed, etc. Then, each environmental parameter is processed separately: the minimum and maximum values of the environmental parameter in all corresponding environmental scenes are extracted to determine the range of the parameter. For example, in the three environmental scenes corresponding to a cluster, the temperatures are 18℃, 20℃, and 22℃, respectively, so the temperature range is combined as 18-22℃; the humidities are 45%, 50%, and 55%, respectively, so the humidity range is combined as 45-55%. Finally, the combined ranges of all environmental parameters in the same cluster are integrated to form the aggregated environmental marker corresponding to the cluster. In this way, the processing of all M clusters is completed, and M aggregated environmental markers are generated. The above example combines the environmental parameter ranges of three clusters to generate M=3 aggregated environmental markers.

[0046] Through standardization sample processing, multi-scene detection, cluster analysis, and environmental parameter merging, representative moisture permeability detection parameters and aggregated environmental markers are obtained, providing a reliable foundation for subsequent moisture permeability analysis.

[0047] Further, step A230 in the method provided by the embodiments of the present application includes:

[0048] A231: After the environmental adjustment on the test platform, a steam generator on the test platform is used to simulate the uniform sweat test sample on the first side of the fabric test sample, and a water collection system is arranged on the second side of the fabric test sample, and water vapor passing through the fabric test sample is collected through the water collection system.

[0049] In the embodiments of the present application, the steam generator is a device on the test platform, which is used to simulate the uniform sweat test sample on the first side of the fabric test sample by releasing steam to simulate the state of human sweat discharge. The water collection system is a system arranged on the second side of the fabric test sample, which is equipped with a water amount sensor, a water amount to water vapor amount conversion unit, and an automatic cleaning module.

[0050] Optionally, after the test platform completes the environmental adjustment, the parameters are stable at the current scene setting values, such as temperature 28℃, humidity 65%, and air flow speed 0.5m / s. At this time, the steam generator on the test platform is started, which stores a solution consistent with the composition of the uniform sweat test sample, i.e. 0.9% sodium chloride solution, in its internal storage. By precisely controlling the heating temperature and the spraying rate, the steam is continuously applied to the first side (inner side) of the fabric test sample at a flow rate of 0.08ml / h per square centimeter, simulating the state of human sweat discharge in this environment, ensuring the stability and authenticity of the sweat simulation.

[0051] At the same time, the second side (outer side) of the fabric test sample starts to run the water collection system. The condensation component of the water collection system is set to 20℃, which is 8℃ lower than the current ambient temperature, to efficiently condense the water vapor that permeates the fabric. The water vapor that permeates the fabric quickly liquefies after contacting the condensation component, and the liquid water drops into the lower measuring container. The sealing structure of the water collection system prevents evaporation or external moisture from mixing, ensuring the accuracy of the collection process.

[0052] During the 1-hour test, the steam generator maintains stable output, and the water collection system continuously collects liquid water. For example, in a 28℃, 65% humidity scenario, the water collection system collects 4.2g of water in 1 hour, which directly reflects the amount of water vapor that permeates the fabric in this environment. By repeating the above operation in different environmental scenarios, the water vapor permeation data corresponding to the environmental scenario can be obtained, providing a real measurement basis for subsequent aggregation analysis of test results.

[0053] By simulating sweat discharge through the steam generator and collecting water vapor that permeates the fabric through the water collection system, the water vapor permeation data of the fabric in different environmental scenarios is accurately obtained, providing a reliable real measurement basis for water vapor permeation performance testing.

[0054] Further, the step A231 in the method provided by the embodiment of the present application comprises:

[0055] A231-1: The first side of the fabric test sample is the inner side surface of the fabric, which contacts the skin of the wearer; the second side is the outer side surface of the fabric, which directly contacts the external environment.

[0056] Specifically, first, before testing the water vapor permeation performance of the fabric test sample, the physical positions of the two sides need to be clearly distinguished. During the weaving and processing of the fabric, there are usually structural differences between the inner side and the outer side, such as the use of skin-friendly knitted texture on the inner side and plain weave structure on the outer side to enhance wear resistance. Such differences directly affect the transmission path of sweat and water vapor. During testing, according to the original design and use scenario of the fabric, the inner side surface (first side) that contacts the skin and the outer side surface (second side) that contacts the external environment are accurately identified by observing the texture direction or referring to the cutting marks on the edges of the fabric, to ensure that the sample is installed in the correct direction, such as the inner side of a batch of sports fabric with a density of 20 roots / mm² and the outer side with a density of 5 roots / mm², which can be quickly distinguished by a microscope.

[0057] Next, when fixing the fabric test sample to the test platform, it needs to be strictly installed in the way that the first side faces the steam generator and the second side faces the water collection system. The simulated sweat steam released by the steam generator first acts on the first side, simulating the contact state of sweat secreted by the human body skin with the inside of the fabric; and the water vapor passing through the fabric is emitted from the second side and collected by the outside water collection system. For example, in a test scene of 30°C and 60% humidity, if the first side is facing the wrong way, the steam needs to penetrate the dense outer layer that should face outward, which will cause the measured value of the moisture permeability to be lower within 1 hour than when it is correctly installed, and after correctly distinguishing and installing, the standard deviation of the measured value can be controlled within 3%.

[0058] Through the above-mentioned clear definition of the two sides of the fabric test sample, it is ensured that the sweat transmission path in the detection process is consistent with that in actual wearing. When the first side corresponds to the side in contact with the skin and the second side corresponds to the side in contact with the external environment, the resistance and speed of the steam passing through the fabric can truly reflect the actual moisture permeability of the fabric, thereby providing accurate basic data for subsequent moisture permeability calculation and environment scene correlation.

[0059] Further, step A231 in the method provided by the embodiment of the application comprises:

[0060] A231-2: The water collection system is provided with a water amount sensor and a water amount to water vapor amount conversion unit, the water amount sensor is used to detect and record the amount of water evaporated and condensed in real time, and the water amount to water vapor amount conversion unit is used to calculate the amount of water vapor passing through the fabric per unit time, so as to complete the moisture permeability detection.

[0061] A231-3: The water collection system is further provided with an automatic cleaning module, which automatically removes the accumulated water in the water collection system after each test.

[0062] Specifically, when the water collection system is running, the water amount sensor in the water collection system starts to monitor the amount of liquid water in the measuring container in real time, and the detection accuracy can reach 0.01 g, which can capture each tiny condensation water drop. For example, in a certain group of environment scene detection, the water amount recorded by the sensor gradually increases from 0 g to 1.8 g in the first 30 minutes, and increases to 3.5 g in the last 30 minutes, which records the accumulation process of the condensed water over time.

[0063] At the same time, the water amount to water vapor amount conversion unit also works synchronously, and based on the density of water 1 g / cm³ and the detection time, the accumulated water amount is converted into the water vapor amount per unit time. If the total water amount recorded by the sensor in 1 hour is 3.6 g, the water amount to water vapor amount conversion unit will calculate that the water vapor passing through the fabric per hour is 3.6 g / h, which is directly used as the core detection parameter of the moisture permeability.

[0064] After each environmental scenario detection, the automatic cleaning module of the water collection system is started. First, the residual water in the metering container is discharged to the waste liquid collection through the built-in pipeline, and then a small amount of clean water is released to flush the inner wall of the container to ensure that there is no water droplet residue, avoiding the influence of residual water of the previous detection on the next group of test data. After cleaning, the automatic cleaning module is automatically reset, waiting for the next environmental scenario detection to start.

[0065] Through the cooperative work of the water quantity sensor and the water quantity and water vapor quantity conversion unit and the assistance of the automatic cleaning module, the water vapor transmission amount per unit time is accurately obtained, and the continuity and data accuracy of multiple detections are ensured.

[0066] Further, the step A300 in the method provided by the embodiment of the application comprises:

[0067] A310: Collect a plurality of sweat discharge data samples.

[0068] A320: Perform similarity clustering on the plurality of sweat discharge data samples to generate N groups of clustered sample clusters.

[0069] A330: Extract any one of the N groups of clustered sample clusters, perform mean value calculation on the data in any one of the clustered sample clusters, and configure the sweat feature mode set.

[0070] A340: Extract any sweat feature mode from the sweat feature mode set, and configure the target dynamic sweat feature sequence under a preset test duration.

[0071] Specifically, first, the sweat discharge of different groups of people in various scenarios is collected, for example, 200 samples are selected, including people of different ages such as teenagers, adults, and the elderly, and sweat discharge amount, discharge rate, and duration data under different activity intensities such as sitting, walking, and running, and then a plurality of sweat discharge data samples are integrated to ensure that the samples are widely representative.

[0072] Further, at the time of collection, a flexible sweat sensor is attached to the axillary, back, and other parts of the subject prone to sweating, and a portable data recorder and timer are used in synchronization, wherein the sensor collects the sweat discharge amount and rate in real time, the timer records the duration of sweating, and an environmental monitor records the scene temperature, humidity, and other parameters. Select 60-70 people from each of the youth, adults, and the elderly, a total of 200 people, covering different genders, and test them in different scenarios such as sitting, walking, and running. Each scenario lasts for 1 hour, and the test is repeated 3 times to reduce errors. During integration, first, remove invalid data under sensor failure or abnormal state of the subject, then classify by age and activity intensity, and then aggregate the data in the same category after uniting, to finally form 200 sweat discharge data samples containing discharge amount, rate, duration, and corresponding scene information, ensuring that the typical sweating characteristics of different populations and scenes are covered.

[0073] Then, the 200 sweat discharge data samples are clustered by similarity, and the K-means clustering algorithm is used. First, select the discharge rate fluctuation (unit: g / h²) and total discharge amount range (unit: g) as the core features, and standardize the two feature values of each sweat discharge data sample to convert the data to the 0-1 interval and eliminate the dimension difference. Then, calculate the similarity clustering by calculating the Euclidean distance between the samples to measure the feature similarity: for the rate fluctuation a1 and total discharge amount b1 in sample A and the rate fluctuation a2 and total discharge amount b2 in sample B, the Euclidean distance is , the smaller the distance, the higher the similarity. When clustering, N=4 is preset, and 4 samples are randomly selected as the initial cluster centers. Calculate the Euclidean distance of all samples to the 4 centers, and assign each sample to the cluster with the nearest center. Then, recalculate the feature mean of each cluster, i.e., the new cluster center, and repeat the distance calculation and sample assignment steps until the change in the cluster center in the last two iterations is less than 0.01, reaching the convergence threshold. Finally, 4 groups of clustered sample clusters are generated, corresponding to light, moderate, severe, and intermittent sweating types, as shown in Table 1.

[0074] Table 1: Corresponding scene and feature table of different types of sweating

[0075]

[0076] After that, extract any one of the 4 clustered sample clusters, for example, the moderate sweating group, and calculate the mean of 60-70 data in the 200 samples in the group to obtain the average discharge rate, average duration, and other feature values of the group. Integrate these feature values into one mode in the sweat feature mode set, and similarly process the other 3 groups, so that the sweat feature mode set contains the above 4 typical sweat feature modes.

[0077] Finally, in the sweat feature mode set, any mode is extracted, such as heavy sweating mode, and in a preset test duration (such as 2 hours), a target dynamic sweat feature sequence is configured according to the dynamic change rule of the mode, such as rapid rise to a peak of 6g / h in the first 30 minutes, then 1 hour of peak maintenance, and finally gradual decline to 2g / h in the last 30 minutes. Here, only one mode is extracted for example illustration, and in actual operation, all 4 modes in the sweat feature mode set are executed with the same steps to cover various sweating characteristics of different populations.

[0078] By collecting multiple samples, clustering grouping, mean configuration mode, and dynamic sequence generation, different sweating characteristics are comprehensively covered, providing a realistic sweat dynamic basis for subsequent simulation combined with moisture permeability parameters.

[0079] Further, the method provided in the embodiment of the application comprises the following steps A300:

[0080] A350: Based on the M groups of moisture permeability detection parameters, water vapor transmission rate analysis is performed to generate M water vapor transmission rates.

[0081] A360: A moisture permeability visualization simulation platform is constructed, and the M water vapor transmission rates and the target dynamic sweat feature sequence are visualized for sweat discharge and evaporation process to generate M sweat discharge-evaporation simulation sequences.

[0082] A370: The M sweat discharge-evaporation simulation sequences are executed to evaluate the dryness of the human skin surface at each time node to generate M dryness evaluation index sequences.

[0083] A380: The M dryness evaluation index sequences are marked to the M sweat discharge-evaporation simulation sequences according to the time sequence correspondence relationship to generate the M moisture permeability simulation sequences.

[0084] In one embodiment, after the M groups of moisture permeability detection parameters are obtained in step A240, each group of parameters is first arranged, and the core data in each group of parameters is determined as the water vapor amount passing through the fabric test sample per unit time. For example, if M=3, the 3 groups of parameters are 5.0g / h, 7.8g / h, and 2.2g / h, which correspond to the moisture permeability results under different aggregation environment labels.

[0085] Then, the water vapor permeability is converted based on the area of the fabric test sample. Assuming the area of the fabric test sample is 10 cm x 10 cm = 0.01 m2, the water vapor permeability corresponding to each group of moisture permeability detection parameters is the moisture permeability divided by the sample area. Calculation shows that the first group is 5.0 g / h ÷ 0.01 m2 = 500 g / (m2·h), the second group is 7.8 g / h ÷ 0.01 m2 = 780 g / (m2·h), and the third group is 2.2 g / h ÷ 0.01 m2 = 220 g / (m2·h).

[0086] During the conversion process, data verification is performed simultaneously to exclude abnormal values caused by sample installation deviation or environmental fluctuations. For example, if the single detection value of a certain group of parameters deviates from the group average by more than 8%, the group average is recalculated after excluding the abnormal value to ensure that the generated water vapor permeability accurately reflects the moisture permeability of the fabric under the corresponding environment. Finally, M water vapor permeabilities corresponding to M moisture permeability detection parameters are generated, providing standardized performance indicators for subsequent visualization simulation of moisture permeability combined with dynamic sweat characteristic sequences.

[0087] Next, the fabric and the human body are integrated and virtually modeled to generate an initial simulation model. After loading the target dynamic sweat characteristic sequence for sweat discharge simulation, the M water vapor permeabilities are combined for evaporation process simulation to generate M sweat discharge-evaporation simulation sequences, which are described in detail in A361-A362.

[0088] Then, based on the M sweat discharge-evaporation simulation sequences, the skin surface humidity at each time node is calculated to generate a humidity sequence, and M dryness evaluation index sequences are obtained through conversion and calculation, which are described in detail in A371-A372.

[0089] After that, the M sweat discharge-evaporation simulation sequences and the M dryness evaluation index sequences are both based on the same time axis, such as recording data with a unified time step of 1 minute. Based on this time sequence consistency, each time node is iterated: for a certain time t, the sweat distribution state at time t is extracted from the sweat discharge-evaporation simulation sequence, such as the sweat residue area on the inside of the fabric, the thickness distribution, and the evaporation dynamics such as evaporation rate, humidity gradient, and other simulation data; at the same time, the dryness value corresponding to time t is extracted from the dryness evaluation index sequence.

[0090] Subsequently, the extracted dryness value is marked as attribute information to the time t data set of the sweat discharge-evaporation simulation sequence. For example, a dryness index field is added in the simulation data structure at time t, and the corresponding dryness value is filled in to realize the correlation between the sweat evaporation physical process and the dry body sensation of the human body at the same time. Through successive matching and marking of all time nodes, the M sweat discharge-evaporation simulation sequences all incorporate the dryness evaluation results corresponding to the time sequence.

[0091] Finally, M moisture permeability simulation sequences are generated, which not only retain the dynamic simulation information of the sweat discharge and evaporation process, but also incorporate the quantitative evaluation of the dryness of the human skin, realizing integrated simulation expression of the moisture permeability of the functional fabric from the physical process to the body sensation feedback.

[0092] Through the correlation marking of the time sequence correspondence, the dryness evaluation is coupled with the sweat evaporation simulation data, providing a complete data carrier for multi-dimensional analysis of the moisture permeability of functional fabrics.

[0093] Further, the step A360 in the method provided by the embodiment of the application comprises:

[0094] A361: integrally virtually integrating modeling of the target functional fabric and the human body to generate an initialization simulation model.

[0095] A362: loading the target dynamic sweat feature sequence to the initialization simulation model to perform sweat discharge simulation, and based on the sweat discharge simulation result, performing sweat evaporation process simulation with the M water vapor transmission rates to generate the M sweat discharge-evaporation simulation sequences.

[0096] Optionally, when integrally virtually integrating modeling of the target functional fabric and the human body, first, the physical parameters of the target functional fabric are collected, such as thickness, fiber density, porosity, etc., and a standard human body upper body virtual model is constructed, with the skin surface basic temperature set to 34℃, and the main sweating areas set to the back area of about 0.15m² and the single-side underarm area of about 0.02m². The fabric is virtually modeled into a clothing form that fits the human skin by a three-dimensional modeling tool, ensuring that the gap between the inner side of the fabric and the skin surface is controlled within 0.5mm, and finally generating an initialization simulation model containing the fabric structure, human skin features and fitting relationship.

[0097] Then, the target dynamic sweat feature sequence is loaded to initialize the simulation model, and an example is selected as follows: the discharge amount linearly increases from 0 to 5 g / h in 0-10 minutes, maintains 5 g / h in 10-30 minutes, and linearly decreases to 2 g / h in 30-60 minutes. The simulation model simulates sweat secretion in the back and armpit areas of the virtual human body according to the sequence, and records the sweat distribution state every 5 minutes, for example, the sweat coverage area of the back is 80% and the cumulative amount is 0.8 g at 10 minutes; the cumulative amount of sweat in the armpit is 0.5 g at 30 minutes, and the sweat discharge simulation is completed.

[0098] Then, based on the sweat discharge simulation result, the evaporation process simulation is performed in combination with M=3 water vapor permeabilities of 220 g / (m²·h), 500 g / (m²·h), and 780 g / (m²·h), respectively. In the scenario of a permeability of 780 g / (m²·h), the simulation shows that sweat starts to significantly evaporate in the inner side of the fabric at 15 minutes, the evaporation amount of the back is 1.2 g at 25 minutes, and the remaining sweat is 0.3 g; and in the scenario of a permeability of 220 g / (m²·h), the evaporation amount of the back is only 0.4 g at 30 minutes, and the remaining sweat is 1.1 g. The sweat evaporation rate and the humidity difference between the inner and outer sides of the fabric are recorded at time nodes, and finally M=3 sweat discharge-evaporation simulation sequences corresponding to different water vapor permeabilities are generated.

[0099] Through integrated virtual modeling, dynamic sweat discharge simulation, and evaporation simulation in combination with water vapor permeability, M simulation sequences reflecting the sweat change process under different moisture permeability are generated, which provides a dynamic visual basis for subsequent moisture permeability evaluation.

[0100] Further, step A370 in the method provided in the embodiments of the application includes:

[0101] A371: Based on the M sweat discharge-evaporation simulation sequences, skin surface humidity calculation is performed at each time node to generate M skin surface humidity sequences.

[0102] A372: Dryness conversion calculation is performed according to the M skin surface humidity sequences to obtain the M dryness evaluation index sequences.

[0103] In one embodiment, first, based on the M sweat discharge-evaporation simulation sequences, the sweat discharge rate and the evaporation rate of each time node in each sweat discharge-evaporation simulation sequence are extracted. and evaporation rate data, wherein may be different according to factors such as exercise intensity, temperature and humidity, and individual differences, and can be represented by a time function: wherein t is time, I is exercise intensity, T is environmental temperature, and H is environmental humidity. According to the humidity of the skin surface, the ambient temperature and humidity, and the moisture permeability of the fabric, the evaporation rate also changes over time, which is specifically represented by the formula , wherein k is a coefficient related to the moisture permeability of the fabric and the heat conduction constant in contact with the skin, is the humidity of the skin surface, is the evaporation rate.

[0104] Then, the initial skin surface humidity is set, which is used to simulate the skin basic humidity in a resting state of the human body, at a time step Δt=5 minutes, i.e., 1 / 12 hours, the skin humidity change equation is used to perform numerical integral calculation by Euler method: if a simulation sequence corresponds to a moderate sweating scenario, i.e., is 2 g / h on average, at t=10 minutes, if =2.2 g / h, =1.5 g / h, then , and after Δt calculation, , wherein is the humidity of the skin surface, and the lower it is, the higher the dryness is, and vice versa. After traversing all time nodes, M skin surface humidity sequences are generated.

[0105] Next, for each skin surface humidity sequence, point-by-point conversion is performed according to the dryness formula Dryness(t)=1- : taking the above moderate sweating scenario as an example, at t=10 minutes, Dryness(10)=1-0.417=0.583; if at t=40 minutes, =0.55, then Dryness(40)=0.45. Through batch calculation, finally, M dryness evaluation index sequences are obtained, which completely depict the dryness change law of different moisture permeable fabrics under dynamic sweating.

[0106] Through dynamic calculation of skin humidity and formula conversion, quantitative evaluation of the moisture permeability of functional fabrics on human dryness in multiple scenarios is realized, which provides intuitive time sequence basis for fabric performance comparison.

[0107] In summary, the functional fabric moisture permeability detection method provided by the embodiments of the present application has the following technical effects:

[0108] ​This application constructs an environmental scenario set by mining the application environment of fabric moisture permeability, and conducts moisture permeability testing on target functional fabrics. It extracts target dynamic sweat feature sequences from the sweat feature modality set and performs dynamic visualization simulation in conjunction with moisture permeability testing parameters. Through clustering, mean calculation, and dryness evaluation, it obtains data such as moisture permeability testing parameters, aggregated environmental labels, and moisture permeability simulation sequences. It calculates information such as water vapor transmission rate and dryness evaluation index sequences, and establishes an association mapping between the aggregated environmental labels, the moisture permeability simulation sequences, and the target sweat scenarios for adjustment. This allows for accurate detection of the moisture permeability of functional fabrics, making the moisture permeability testing results more precise and reliable. It achieves the technical effect of comprehensively and accurately detecting the relevant performance of materials under different actual scenarios and dynamic conditions, meeting the needs of precise evaluation and application.

[0109] Example 2, as Figure 2 As shown, based on the same inventive concept as in Embodiment 1 above, this application provides a moisture permeability testing system for functional fabrics, the system comprising:

[0110] Environment scene set construction module 1 is used to perform application environment mining of fabric moisture permeability and construct an environment scene set.

[0111] The moisture permeability testing execution module 2 performs moisture permeability testing on the target functional fabric based on the set of environmental scenarios and aggregates and marks the results, generating M sets of moisture permeability testing parameters and M aggregated environmental markers.

[0112] The moisture permeability simulation sequence acquisition module 3 is used to extract the target dynamic sweat feature sequence from the sweat feature mode set, and combine it with the M sets of moisture permeability detection parameters to perform dynamic visualization simulation of moisture permeability, generating M moisture permeability simulation sequences.

[0113] The moisture permeability test result acquisition module 4 is used to establish an association mapping between the M aggregated environmental markers, the M moisture permeability simulation sequences, and the target sweat scene, as the moisture permeability test result.

[0114] Furthermore, the moisture permeability simulation sequence acquisition module 3 is used to perform the following steps:

[0115] Collect a plurality of sweat discharge data samples; perform similarity clustering on the plurality of sweat discharge data samples to generate N groups of clustered sample clusters; extract any one of the N groups of clustered sample clusters, perform mean value calculation on the data in any one of the clustered sample clusters, and configure the sweat feature modal set; extract any sweat feature mode from the sweat feature modal set, and configure the target dynamic sweat feature sequence under a preset test duration.

[0116] Further, the moisture permeability simulation sequence acquisition module 3 is configured to perform the following steps:

[0117] Based on the M moisture permeability detection parameters, perform water vapor transmission rate analysis to generate M water vapor transmission rates; construct a moisture permeability visualization simulation platform, perform visualization of sweat discharge and evaporation process on the M water vapor transmission rates and the target dynamic sweat feature sequence to generate M sweat discharge-evaporation simulation sequences; perform dryness evaluation of the human skin surface at each time node based on the M sweat discharge-evaporation simulation sequences to generate M dryness evaluation index sequences; mark the M dryness evaluation index sequences to the M sweat discharge-evaporation simulation sequences according to the time sequence correspondence relationship to generate the M moisture permeability simulation sequences.

[0118] Further, the moisture permeability simulation sequence acquisition module 3 is configured to perform the following steps:

[0119] Perform integrated virtual integrated modeling of the target functional fabric and the human body to generate an initialization simulation model; load the target dynamic sweat feature sequence to the initialization simulation model to perform sweat discharge simulation, and based on the sweat discharge simulation result, perform sweat evaporation process simulation on the M water vapor transmission rates to generate the M sweat discharge-evaporation simulation sequences.

[0120] Further, the moisture permeability simulation sequence acquisition module 3 is configured to perform the following steps:

[0121] Based on the M sweat discharge-evaporation simulation sequences, respectively perform skin surface humidity calculation at each time node to generate M skin surface humidity sequences; and perform dryness conversion calculation according to the M skin surface humidity sequences to obtain the M dryness evaluation index sequences.

[0122] Further, the moisture permeability detection execution module 2 is configured to perform the following steps:

[0123] obtaining a fabric test sample of the target functional fabric; fixing the fabric test sample to a test platform, configuring a uniform sweat test sample; traversing a plurality of sets of environmental scenarios in the set of environmental scenarios, after environmental adjustment of the test platform, configuring the first surface of the fabric test sample with the uniform sweat test sample, performing moisture permeability detection, and generating a plurality of sets of moisture permeability detection results; clustering the plurality of sets of moisture permeability detection results according to a preset consistent deviation threshold, performing mean value calculation on the moisture permeability parameters in the M clusters obtained by clustering, and generating M sets of moisture permeability detection parameters; merging the environmental parameter ranges of all environmental scenarios corresponding to each cluster in the M clusters, and generating the M aggregated environmental markers.

[0124] Further, the moisture permeability detection execution module 2 is configured to perform the following steps:

[0125] After environmental adjustment of the test platform, a steam generator on the test platform is used to simulate the uniform sweat test sample on the first surface of the fabric test sample, and a water collection system is arranged on the second surface of the fabric test sample, and water vapor passing through the fabric test sample is collected through the water collection system.

[0126] Further, the moisture permeability detection execution module 2 is configured to perform the following steps:

[0127] The first surface of the fabric test sample is the inner surface of the fabric, which is in contact with the skin of the wearer, and the second surface is the outer surface of the fabric, which is in direct contact with the external environment.

[0128] Further, the moisture permeability detection execution module 2 is configured to perform the following steps:

[0129] The water collection system is equipped with a water quantity sensor and a water quantity and water vapor quantity conversion unit, which detects and records the amount of water evaporated and condensed in real time through the water quantity sensor, and calculates the amount of water vapor passing through the fabric per unit time through the conversion unit, thereby completing the moisture permeability detection; the water collection system is also equipped with an automatic cleaning module to automatically remove the accumulated water in the water collection system after each test.

[0130] The moisture permeability detection system for functional fabric provided by the embodiment of the application can perform the moisture permeability detection method for functional fabric provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0131] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, the various units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific name of each functional unit is only for the convenience of mutual differentiation, and does not serve to limit the protection scope of the present application.

[0132] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application. In some cases, the actions or steps described in the present application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A method for detecting the moisture permeability of a functional fabric, characterized by, include: Explore the application environment of fabric moisture permeability and construct a set of environmental scenarios; Based on the set of environmental scenarios, the moisture permeability of the target functional fabric is tested and the results are aggregated and labeled to generate M sets of moisture permeability test parameters and M aggregated environmental labels. Extract the target dynamic sweat feature sequence from the sweat feature modality set, and combine it with the M sets of moisture permeability detection parameters to perform dynamic visualization simulation of moisture permeability, generating M moisture permeability simulation sequences. The M aggregated environmental markers are associated with the M moisture permeability simulation sequences and the target sweat scene to form a mapping, which is used as the moisture permeability detection result; The extraction of target dynamic sweat feature sequences from the sweat feature modality set includes: Collect several samples of sweat discharge data; Similarity clustering is performed on the aforementioned sweat emission data samples to generate N clusters of samples; Extract any one of the N clustered sample clusters, calculate the mean of the data in any one clustered sample cluster, and configure the sweat feature mode set; Extract any sweat feature mode from the sweat feature mode set, and configure the target dynamic sweat feature sequence under a preset test duration; The method involves combining the M sets of moisture permeability test parameters to perform dynamic visualization simulation of moisture permeability, generating M moisture permeability simulation sequences, including: Based on the M sets of moisture permeability test parameters, water vapor transmission rate analysis was performed to generate M water vapor transmission rates. A moisture permeability visualization simulation platform is constructed to visualize the sweat emission and evaporation process of the M water vapor transmission rates and the target dynamic sweat characteristic sequence, and to generate M sweat emission-evaporation simulation sequences. The dryness of human skin surface at each time point is evaluated using the M sweat emission-evaporation simulation sequences, generating M dryness evaluation index sequences; The M dryness evaluation index sequences are labeled to the M sweat emission-evaporation simulation sequences according to the time sequence correspondence, thereby generating the M moisture permeability simulation sequences.

2. The method for testing the moisture permeability of a functional fabric as described in claim 1, characterized in that, A moisture permeability visualization simulation platform is constructed to visualize the sweat emission and evaporation process of the M water vapor transmission rates and the target dynamic sweat characteristic sequence, generating M sweat emission-evaporation simulation sequences, including: The target functional fabric is modeled as an integrated virtual model of the fabric and the human body to generate an initial simulation model; The initialization simulation model is loaded with the target dynamic sweat feature sequence to simulate sweat emission. Based on the sweat emission simulation results, the sweat evaporation process is simulated using the M water vapor permeability rates to generate the M sweat emission-evaporation simulation sequences.

3. The method for testing the moisture permeability of a functional fabric as described in claim 1, characterized in that, The dryness of human skin surface at each time point is evaluated using the M sweat emission-evaporation simulation sequences, generating M dryness evaluation index sequences, including: Based on the M sweat emission-evaporation simulation sequences, the skin surface humidity at each time point is calculated to generate M skin surface humidity sequences; Based on the M skin surface humidity sequences, a dryness conversion calculation is performed to obtain the M dryness evaluation index sequences.

4. The method for testing the moisture permeability of a functional fabric as described in claim 1, characterized in that, Based on the aforementioned set of environmental scenarios, the moisture permeability of the target functional fabric is tested and the results are aggregated and labeled, generating M sets of moisture permeability test parameters and M aggregated environmental labels, including: Obtain fabric test samples of the target functional fabric; The fabric test sample was fixed to the test platform, and a uniform sweat test sample was configured. After traversing several sets of environmental scenarios in the set of environmental scenarios and adjusting the environment on the test platform, the first side of the fabric test sample is configured with sweat using the uniform sweat test sample, and the moisture permeability is tested to generate several sets of moisture permeability test results. The several groups of moisture permeability test results are clustered according to a preset consistency deviation threshold. The mean value of the moisture permeability parameters in the M clusters obtained by clustering is calculated to generate M groups of moisture permeability test parameters. The environmental parameter ranges of all environmental scenarios corresponding to each of the M clusters are merged to generate the M aggregated environmental tags.

5. The method for testing the moisture permeability of a functional fabric as described in claim 4, characterized in that, After environmental conditioning is performed on the testing platform, a steam generator on the testing platform is used to simulate the uniform sweat test sample on the first side of the fabric test sample. A water collection system is set on the second side of the fabric test sample to collect water vapor passing through the fabric test sample.

6. The method for testing the moisture permeability of a functional fabric as described in claim 5, characterized in that, The first side of the fabric test sample is the inner surface of the fabric, which is in contact with the wearer's skin; the second side is the outer surface of the fabric, which is in direct contact with the external environment.

7. The method for testing the moisture permeability of a functional fabric as described in claim 5, characterized in that, The water collection system is equipped with a water volume sensor and a water volume to water vapor conversion unit. The water volume sensor detects and records the amount of water that evaporates and condenses in real time, and the conversion unit calculates the amount of water vapor passing through the fabric per unit time to complete the moisture permeability test. The water collection system is also equipped with an automatic cleaning module that automatically removes water from the system after each test.

8. A moisture permeability testing system for functional fabrics, characterized in that, A method for testing the moisture permeability of a functional fabric according to any one of claims 1-7, the system comprising: The environmental scenario set construction module is used to perform application environment mining for fabric moisture permeability and construct an environmental scenario set. The moisture permeability testing execution module performs moisture permeability testing and result aggregation marking on the target functional fabric based on the set of environmental scenarios, generating M sets of moisture permeability testing parameters and M aggregated environmental markers; The moisture permeability simulation sequence acquisition module is used to extract the target dynamic sweat feature sequence from the sweat feature mode set, and combine it with the M sets of moisture permeability detection parameters to perform dynamic visualization simulation of moisture permeability, generating M moisture permeability simulation sequences. The moisture permeability test result acquisition module is used to establish an association mapping between the M aggregated environmental markers, the M moisture permeability simulation sequences, and the target sweat scene, as the moisture permeability test result.

Images