A multi-parameter sensor-based clothing fabric performance comprehensive detection method and system

Abstract

This application provides a method and system for comprehensive performance testing of clothing fabrics based on multi-parameter sensing. A dynamic testing environment is constructed within the testing area. A multi-parameter sensor array integrated using MEMS technology synchronously collects multi-dimensional change data of the clothing fabric under test within this dynamic testing environment. This multi-dimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. Based on the three-dimensional deformation data, fabric compression data, and heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the clothing fabric under test during the testing process are determined respectively. A comprehensive evaluation is performed based on the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance, thereby outputting the comprehensive performance test result of the clothing fabric under test. This application can achieve comprehensive testing of the multi-dimensional performance of clothing fabrics by relying on MEMS integrated sensing technology, thereby improving the accuracy and comprehensiveness of the test results.

Description

Technical Field

[0001] This application relates to the field of textile material performance testing technology, and more specifically, to a comprehensive testing method and system for the performance of clothing fabrics based on multi-parameter sensing. Background Technology

[0002] With the increasing demands for comfort, functionality, and durability in clothing, the performance evaluation of clothing fabrics has become a core focus in textile research and development and quality control. In practical applications, fabrics may simultaneously withstand multiple mechanical loads such as tension, compression, and bending, accompanied by dynamic changes in temperature and humidity, resulting in complex and varied service conditions. In recent years, to objectively quantify the mechanical properties and thermal and moisture comfort indicators of fabrics, various sensing and detection technologies have been gradually applied to the field of textile testing. Among them, micro-sensors based on Micro-Electro-Mechanical Systems (MEMS) microfabrication technology, with their advantages of small size, high integration, fast response speed, and high measurement point density, are gradually replacing traditional split sensors and becoming the mainstream development direction for multi-parameter synchronous detection. They can simultaneously collect multi-dimensional physical and thermodynamic parameters of fabrics using micro-sensor chips.

[0003] However, most existing multi-parameter sensing methods equipped with MEMS sensing components employ static or uniaxial loading modes, which cannot simultaneously excite multiple deformation modes of the fabric, such as thickness compression and surface bending. This results in the collected data failing to comprehensively reflect the fabric performance under complex stress conditions. Furthermore, while some studies have attempted to combine mechanical and thermal sensors, these typically only achieve simple data overlay, neglecting the coupling interference of fabric deformation on pressure and heat flow measurements, and failing to establish a correction mechanism for deformation signals on other sensing signals. This leads to significant errors in the detection data. Therefore, how to leverage MEMS integrated sensing technology to achieve comprehensive detection of the multi-dimensional properties of clothing fabrics, thereby improving the accuracy and comprehensiveness of the detection results, remains a challenge for current technologies. Summary of the Invention

[0004] This application provides a method and system for comprehensive testing of the performance of clothing fabrics based on multi-parameter sensing. It can rely on MEMS integrated sensing technology to achieve comprehensive testing of the multi-dimensional performance of clothing fabrics, thereby improving the accuracy and comprehensiveness of the test results.

[0005] In a first aspect, this application provides a method for comprehensive testing of the performance of clothing fabrics based on multi-parameter sensing, comprising the following steps: A dynamic detection environment is constructed within the detection area, and multi-dimensional change data of the garment fabric under test is synchronously collected by a multi-parameter sensor group integrated based on MEMS technology. The multi-dimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. Based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test during the testing process are determined respectively. The overall performance test results of the garment fabric under test are then output based on a comprehensive evaluation of the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance.

[0006] In some embodiments, constructing a dynamic testing environment within the testing area refers to applying a multi-mode composite dynamic mechanical load of periodic stretching, compression, and bending to the garment fabric to be tested, which is fixed within the testing area, and establishing a preset temperature and humidity difference.

[0007] In some embodiments, the multi-parameter sensor group integrated based on MEMS technology includes: a structured light imaging system for acquiring the three-dimensional morphology of the surface of clothing fabric, a pressure sensing array for acquiring the pressure distribution on the surface of clothing fabric, and a heat flow sensing array for acquiring the heat flux density on both sides of clothing fabric.

[0008] In some embodiments, determining the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test during the testing process based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data specifically includes: Based on the three-dimensional deformation data, a deformation feature sequence of the garment fabric under test is generated during the testing process, and the deformation recovery performance is determined through the deformation feature sequence. Based on the fabric compression data and the deformation characteristic sequence, mechanical inversion is performed to determine the mechanical response performance of the garment fabric under test. Based on the heat flow distribution data and combined with the preset temperature and humidity difference, the heat flow and moisture flow balance relationship on both sides of the fabric is obtained, and then the heat and moisture transfer performance of the clothing fabric under test is obtained.

[0009] In some embodiments, determining the deformation recovery performance through the deformation feature sequence specifically includes: The deformation feature sequence is decoupled in time to identify the thickness recovery process and wrinkle flattening process of the garment fabric under test during the detection process. The thickness recovery characteristics of the garment fabric under test are determined based on the thickness recovery process, and the wrinkle recovery characteristics of the garment fabric under test are determined based on the wrinkle flattening process. The thickness recovery characteristics and the wrinkle recovery characteristics are used as deformation recovery performance.

[0010] In some embodiments, determining the mechanical response performance of the garment fabric under test by performing mechanical inversion based on the fabric compression data and the deformation characteristic sequence specifically includes: Based on the corrected fabric compression data and the local thickness change time sequence in the deformation feature sequence, the stress-strain correspondence of the tested garment fabric during the stress process is established. Based on the stress-strain relationship, the dynamic elastic modulus and stress relaxation characteristics of the garment fabric under test are determined during the testing process. Based on the temporal sequence of surface curvature changes in the deformation feature sequence, the elastic hysteresis characteristics and deformation recovery ability of the garment fabric under test during the testing process are extracted. The dynamic elastic modulus, stress relaxation characteristics, elastic hysteresis characteristics, and deformation recovery ability are used as mechanical response properties.

[0011] In some embodiments, the comprehensive performance test results of the garment fabric under test are output by comprehensively evaluating the deformation recovery performance, the mechanical response performance, and the heat and moisture transfer performance. Specifically, this includes: After normalizing the deformation recovery performance, mechanical response performance and heat and moisture transfer performance respectively, they are weighted and fused according to preset weight coefficients to obtain the comprehensive performance index of the clothing fabric to be tested. Based on the comparison results between the comprehensive performance index and the preset performance level threshold, the comprehensive performance level of the garment fabric to be tested is determined. The overall performance test results of the garment fabric to be tested are output based on the overall performance level.

[0012] Secondly, this application provides a comprehensive performance testing system for clothing fabrics based on multi-parameter sensing, used to perform a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, including: The acquisition module is used to construct a dynamic detection environment within the detection area. It synchronously acquires multidimensional change data of the garment fabric under test through a multi-parameter sensor group integrated based on MEMS technology. The multidimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. The detection module is used to determine the deformation recovery performance, mechanical response performance and heat and moisture transfer performance of the garment fabric under test during the detection process based on the three-dimensional deformation data, the fabric compression data and the heat flow distribution data, respectively. The evaluation module is used to comprehensively evaluate the deformation recovery performance, mechanical response performance and heat and moisture transfer performance, and then output the comprehensive performance test results of the garment fabric to be tested.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described method for comprehensive detection of clothing fabric performance based on multi-parameter sensing.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for comprehensive detection of clothing fabric performance based on multi-parameter sensing.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: This application provides a method and system for comprehensive performance testing of clothing fabrics based on multi-parameter sensing. A dynamic testing environment is constructed within the testing area. A multi-parameter sensor array integrated using MEMS technology synchronously collects multi-dimensional change data of the clothing fabric under test. This multi-dimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. Based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the clothing fabric under test during the testing process are determined, respectively. A comprehensive evaluation is performed based on the deformation recovery performance, the mechanical response performance, and the heat and moisture transfer performance, thereby outputting the comprehensive performance test result of the clothing fabric under test.

[0016] Therefore, this application firstly utilizes a multi-parameter sensor array integrated with MEMS technology to simultaneously acquire three-dimensional deformation, compression, and heat flow distribution data of the garment fabric under test within a detection environment coupled with dynamic mechanical loading and a preset temperature and humidity difference. This overcomes the shortcomings of traditional uniaxial tension or static compression methods, which cannot simultaneously excite multi-mode deformation and pressure response of the fabric. Secondly, the compression data and heat flow distribution data of the fabric are corrected time-by-time based on the deformation feature sequence to eliminate spurious responses in pressure and heat flow measurements caused by fabric deformation, thereby improving the extraction accuracy of intrinsic mechanical and thermo-hygroscopic performance parameters. Furthermore, the deformation feature sequence is decoupled in time to identify... The thickness recovery process and the wrinkle flattening process independently evaluate the compression resilience and wrinkle resistance of the fabric, achieving a multi-dimensional and refined characterization of deformation recovery performance. Simultaneously, the total heat flux density is decomposed into sensible heat conduction and latent heat phase change components, and a balance relationship between heat flux and moisture flow is established. This allows for the acquisition of thermal resistance, moisture resistance, and the thermal-moisture coupling coefficient, quantifying dynamic thermal-moisture coupling characteristics and providing a more comprehensive basis for assessing the thermal and moisture comfort of the fabric. Finally, by weighted fusion of performance indicators from three dimensions—deformation recovery, mechanical response, and heat and moisture transfer—a comprehensive performance index is generated and mapped to a comprehensive performance level, providing an objective decision-making basis for fabric quality grading and targeted development.

[0017] In summary, the technical solution adopted in this application can rely on MEMS integrated sensing technology to achieve comprehensive detection of the multi-dimensional properties of clothing fabrics, thereby improving the accuracy and comprehensiveness of the detection results. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. Figure 2 This is a schematic diagram of an application scenario architecture for a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, as shown in some embodiments of this application. Figure 3 This is an exemplary flowchart illustrating the determination of the mechanical response properties of the garment fabric to be tested, according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a comprehensive testing system for the performance of clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. Figure 5 This is a schematic diagram of the structure of a computer device for implementing a comprehensive testing method for the performance of clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. Detailed Implementation

[0020] 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 the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a method and system for comprehensive performance testing of clothing fabrics based on multi-parameter sensing. The core of this method is to construct a dynamic testing environment within the testing area. A multi-parameter sensor array integrated using MEMS technology synchronously collects multi-dimensional change data of the clothing fabric under test. This multi-dimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. Based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the clothing fabric under test during the testing process are determined, respectively. A comprehensive evaluation is then performed based on the deformation recovery performance, the mechanical response performance, and the heat and moisture transfer performance, thereby outputting the comprehensive performance test result of the clothing fabric under test. This approach leverages MEMS integrated sensing technology to achieve comprehensive testing of the multi-dimensional performance of clothing fabrics, thereby improving the accuracy and comprehensiveness of the test results.

[0022] To better understand the above technical solutions, a detailed description of the technical solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. (Refer to...) Figure 1 The figure is an exemplary flowchart of a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. The figure mainly includes the following steps: In step S101, a dynamic detection environment is constructed within the detection area. Multidimensional change data of the garment fabric to be tested are synchronously collected by a multi-parameter sensor group integrated based on MEMS technology. The multidimensional change data includes three-dimensional deformation data, fabric pressure data, and heat flow distribution data.

[0023] It should be noted that constructing a dynamic testing environment within the testing area refers to applying a multi-mode composite dynamic mechanical load of periodic stretching, compression, and bending to the garment fabric to be tested, which is fixed within the testing area, and establishing a preset temperature and humidity difference.

[0024] refer to Figure 2This figure is a schematic diagram of an application scenario architecture for a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. The upper part of the diagram shows the process of fixing the clothing fabric to be tested onto the clamping ring built into the portal dynamic mechanical loading device and applying dynamic mechanical loading. The clamping ring is centrally symmetrically distributed around the center of the ring body and has four sets of clamping ends for locking and fixing the clothing fabric to be tested across the entire boundary. Relying on the vertical lead screw lifting drive and the left and right push rod lateral tensioning drive of the clamping ring, the clothing fabric to be tested is subjected to multi-directional composite dynamic forces of periodic stretching, compression, and bending. The upper left shows the process of acquiring the three-dimensional morphology of the fabric surface through a structured light imaging system deployed above the clothing fabric to be tested. The lower left shows the temperature and humidity control unit equipped with independent temperature adjustment. The module and humidity control module independently regulate the ambient temperature and relative humidity parameters of the space above and below the fabric being tested, respectively, to create a controllable and stable temperature and humidity difference between the upper and lower sides of the fabric. This establishes a preset temperature and humidity difference, with a range of 5℃~20℃ for temperature and 10%RH~50%RH for humidity, to meet the routine requirements of heat and moisture transfer testing of fabrics and obtain the heat and moisture exchange environment on both sides of the fabric. The upper right shows the process of recording the heat flux density of the fabric by a heat flow sensor array that is attached to the upper and lower surfaces of the fabric. The lower right shows the pressure sensor array integrated on the clamping contact surface of the clamping ring, which is evenly arranged in a regular discrete grid to completely cover the force clamping area of ​​the fabric. It is used to collect the contact pressure signal of the fabric and generate the corresponding pressure data.

[0025] It should be noted that the dynamic mechanical loading adopts a multi-directional composite force mode of tension, compression, and bending, which enables the fabric to withstand multiple force modes simultaneously, producing three-dimensional deformation including thickness compression, surface bending, and in-plane tension; the preset temperature and humidity difference forms a controllable thermal and humidity gradient on both sides of the fabric, thereby putting the fabric under test in a dynamic use state with a high degree of coupling between mechanical deformation and thermal and humidity interaction.

[0026] In specific implementation, under the dynamic detection environment, a multi-parameter sensor group integrated based on MEMS technology synchronously collects multi-dimensional change data of the garment fabric under test. It should be noted that the multi-parameter sensor group integrated based on MEMS technology includes: a structured light imaging system for collecting the three-dimensional morphology of the garment fabric surface, a pressure sensing array for collecting the pressure distribution on the garment fabric surface, and a heat flow sensing array for collecting the heat flux density on both sides of the garment fabric. In actual implementation, the structured light imaging system projects an coded grating onto the fabric surface, captures the distortion features of the grating stripes caused by fabric deformation, and combines this with a three-dimensional reconstruction algorithm to obtain the three-dimensional spatial coordinates of all sampling points on the fabric surface. Temporal morphology data is continuously collected at a fixed time step, and the three-dimensional morphology point clouds at all times are summarized to form three-dimensional deformation data, which is used to characterize the surface. The dynamic evolution of the fabric's geometric deformation under combined loads is illustrated. The structured light imaging system, pressure sensor array, and heat flow sensor array all employ the same acquisition time step, set based on the fabric's dynamic response characteristics and minimum resolvable time scale under combined loads. The heat flow sensor array acquires heat flux density data from the upper and lower sides of the fabric, outputting heat flux distribution data under the combined effects of a preset temperature and humidity difference and dynamic mechanical loading, including upper and lower heat flux densities. The pressure sensor array acquires real-time contact pressure data from discrete grid nodes across the entire domain. At the same detection moment, the arithmetic mean of the pressure values ​​from all grid nodes is calculated as the overall average contact pressure value of the fabric at that moment. The overall average contact pressure values ​​from all moments are then summarized in a time series to form complete fabric pressure data.

[0027] It should be noted that the pressure sensing array and the heat flow sensing array have built-in MEMS micro-sensing chips. They achieve high-density integration of multiple types of micro-sensing units by relying on MEMS micro-machining technology, and simultaneously deploy a large number of measuring points in a narrow detection space. Together with the structured light imaging system, they form an integrated multi-parameter acquisition component. At the same time, the multi-parameter acquisition component is started synchronously by the unified acquisition command issued by the central control unit. The output data of various sensors are all appended with the same standard timestamp to complete the time sequence alignment, ensuring that the three-dimensional deformation data, fabric pressure data, and heat flow distribution data are accurately matched in the time dimension.

[0028] In addition, it should be noted that by constructing a dynamic detection environment coupled with dynamic mechanical action and thermal-humidity gradient within the detection area, and simultaneously establishing a preset temperature and humidity difference, and with the acquisition method of multi-sensor synchronous triggering and timestamp binding registration, the synergy and consistency of multi-source detection data are ensured from both temporal and spatial dimensions. At the same time, the multi-dimensional change data composed of three-dimensional deformation data, fabric compression data, and heat flow distribution data reflects the physical state changes of the tested clothing fabric under composite stress and thermal-humidity coupling conditions.

[0029] In step S102, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test are determined based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, respectively.

[0030] In some embodiments, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test during the testing process can be determined based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, respectively, using the following methods: Based on the three-dimensional deformation data, a deformation feature sequence of the garment fabric under test is generated during the testing process, and the deformation recovery performance is determined through the deformation feature sequence. Based on the fabric compression data and the deformation characteristic sequence, mechanical inversion is performed to determine the mechanical response performance of the garment fabric under test. Based on the heat flow distribution data and combined with the preset temperature and humidity difference, the heat flow and moisture flow balance relationship on both sides of the fabric is obtained, and then the heat and moisture transfer performance of the clothing fabric under test is obtained.

[0031] In specific implementation, a deformation feature sequence of the garment fabric under test during the detection process is generated based on the three-dimensional deformation data. That is, the three-dimensional shape point cloud at different times in the three-dimensional deformation data is unified to a preset fixed world coordinate system. Taking the three-dimensional shape point cloud in the initial unloaded state as the only reference benchmark, the three-dimensional shape point cloud at each time is rigidly registered using an iterative nearest point algorithm. The registration process only eliminates the overall displacement and rotation interference of the garment fabric under test caused by the movement of the support platform, and strictly preserves the local deformation information of the garment fabric itself. Then, for each time moment, based on the registered three-dimensional shape point cloud, the displacement vector of each spatial point relative to the initial position of the surface of the garment fabric under test at that time is calculated point by point. The displacement vectors of all spatial points together constitute the displacement field at that time according to the spatial coordinate correspondence. Based on the spatial gradient distribution of the displacement field, the strain tensor corresponding to each spatial point at that time is calculated using the finite difference method. The strain tensors of all spatial points correspond one-to-one according to the spatial coordinates and together constitute the strain field at that time.

[0032] It should be noted that the displacement field refers to the set of displacement vectors of each spatial point of the garment fabric under test relative to its initial position during the testing process, which is used to quantitatively characterize the deformation displacement process of each part of the fabric; the strain field refers to the set of strain tensors of each spatial point of the garment fabric under test during the testing process, which is used to quantitatively reflect the degree of local deformation of the garment fabric under different stress modes such as tension and compression.

[0033] In specific implementation, for the displacement field and strain field at each moment, the normal displacement component in the displacement field is extracted along the fabric thickness direction (parallel to the z-axis of the spatial coordinate system); simultaneously, combined with the normal compressive strain in the strain field, an adaptive weighted fusion algorithm is used to perform collaborative calculation on the normal displacement component and the normal compressive strain to obtain the comprehensive deformation value in the fabric thickness direction. The difference between this comprehensive deformation value and the original thickness of the fabric in the initial unloaded state is calculated as the thickness change of the fabric under test at that moment. The thickness changes at all moments are arranged by timestamp to obtain the local thickness change time series. A quadratic surface fitting algorithm is used to perform local surface fitting on each spatial point of the displacement field at each moment. The fitting window size is preset according to the fabric point cloud density. The local average curvature value of each spatial point at that moment is calculated, and then the overall average value of the local average curvature values ​​of all spatial points at that moment is determined as the global average curvature at that moment. The global average curvature at all moments is extracted by timestamp to obtain the surface curvature change time series characterizing the dynamic changes in the fabric surface morphology. In addition, in specific implementation, based on the displacement field at each moment, the point cloud of the lower surface of the fabric is spatially registered with the 3D model of the support platform through an iterative nearest-point algorithm. The normal distance from each spatial point on the lower surface of the fabric to the surface of the support platform at that moment is obtained. A fixed distance threshold is preset as the contact determination criterion. This distance threshold can be determined according to actual detection needs and the accuracy of the detection equipment. When the normal distance is less than the distance threshold, the spatial point is determined to be a contact point; otherwise, it is a non-contact point. The proportion of the number of contact points to the total number of points on the lower surface of the fabric at that moment is counted as the contact area proportion at that moment. For each moment, the normal distance from each non-contact point to the surface of the support platform is determined as the gap value. The arithmetic mean of the gap values ​​of all non-contact points is then obtained. The average contact gap at each moment should be noted. When the fabric is in complete contact, the average contact gap is zero. The contact area ratio and the average contact gap at each moment are used together as the contact state parameter at that moment. The contact state parameters at all moments are extracted according to the timestamp to form the contact state change sequence that characterizes the dynamic changes in the contact relationship between the fabric and the support platform. The local thickness change sequence, the surface curvature change sequence, and the contact state change sequence are aligned according to the timestamp and then spliced ​​together moment by moment. The splicing method is to combine the four feature parameters of thickness change, global average curvature, contact area ratio, and average contact gap at the same moment in a fixed order to finally form a deformation feature sequence that characterizes the dynamic deformation process of the garment fabric under test.

[0034] It should be noted that the local thickness change time series reflects the normal volume change law of the tested garment fabric during the testing process, providing key underlying parameters for subsequent identification of the thickness recovery process and construction of stress-strain correspondence; the surface curvature change time series is used to determine the wrinkle flattening process of the tested garment fabric at the end of dynamic mechanical loading, providing geometric topological judgment basis for quantifying the deformation hysteresis characteristics and deformation recovery ability of the tested garment fabric during the testing process; the contact state change time series is used to identify the external force interference and the extension state of the contact area between the fabric and the support platform.

[0035] In some embodiments, after generating the deformation feature sequence of the garment fabric under test during the detection process based on the three-dimensional deformation data, the method further includes: Based on the local thickness change time sequence and surface curvature change time sequence in the deformation feature sequence, the fabric pressure data is subjected to deformation-pressure coupling compensation correction to eliminate pressure measurement spurious response. Based on the contact state change sequence in the deformation feature sequence, the heat flux distribution data is subjected to deformation-heat flux coupling compensation correction to eliminate spurious responses in heat flux measurement.

[0036] In specific implementation, firstly, for each moment in the detection process, based on the local thickness change time sequence and the surface curvature change time sequence, the thickness variation and average curvature value corresponding to that moment are substituted into a preset deformation-pressure compensation equation to calculate the pressure measurement pseudo-response value caused by fabric deformation at that moment. Subsequently, the pressure measurement pseudo-response value is subtracted from the fabric pressure data corresponding to that moment to obtain the fabric pressure data after eliminating deformation interference at that moment. The above compensation operation is performed sequentially for all moments to finally form a corrected fabric pressure sequence. Secondly, for each moment in the detection process, the contact state parameters corresponding to that moment are extracted from the contact state change time sequence, and a preset deformation-heat flux compensation function is called according to the specific value of the contact state parameters. Through the deformation-heat flux compensation function, the heat flux measurement pseudo-response value caused by fabric deformation and contact state change at that moment is determined, and the heat flux measurement pseudo-response value is subtracted from the heat flux distribution data at that moment to obtain the corrected heat flux distribution data at that moment. After completing the compensation processing for all moments in sequence, a corrected heat flux distribution sequence is generated.

[0037] It should be noted that the deformation-pressure compensation equation was obtained through prior calibration experiments on a standard elastic fabric. Specifically, on the experimental platform, a standard pressure of known magnitude was applied to the standard elastic fabric at each stage. Under each pressure loading condition, three sets of data were simultaneously collected, including the fabric's thickness variation, average curvature value, and the original output signal of the pressure sensor array. Based on multiple sets of measured data, a linear fitting algorithm was used to construct a quantitative mapping relationship between the fabric deformation parameters, including the thickness variation and average curvature value, and the pressure measurement error, thereby uniquely determining the deformation-pressure compensation equation. The deformation-heat flux compensation function was also obtained through calibration experiments. That is, under a constant steady-state heat flux excitation environment, the output deviation of the heat flux sensor was measured under different degrees of fabric deformation and different contact states. Based on multiple sets of measured results, a nonlinear fitting algorithm was used to construct a quantitative functional relationship between the fabric contact state parameters and the pseudo-response of heat flux measurement, thereby uniquely obtaining the deformation-heat flux compensation function.

[0038] It should be noted that by establishing a compensation and correction relationship between deformation parameters and measurement pseudo-response, the coupling interference of fabric deformation on pressure measurement and heat flow measurement can be effectively eliminated, thereby obtaining a pure signal that truly reflects the intrinsic mechanical properties and heat and moisture transfer properties of the fabric. This pure signal characterizes the true stress state inside the fabric and the transient heat exchange intensity on the fabric surface, providing a reliable data foundation for subsequent mechanical inversion and heat and moisture coupling solution.

[0039] In some embodiments, the deformation recovery performance can be determined by the deformation feature sequence in the following manner: The deformation feature sequence is decoupled in time to identify the thickness recovery process and wrinkle flattening process of the garment fabric under test during the detection process. The thickness recovery characteristics of the garment fabric under test are determined based on the thickness recovery process, and the wrinkle recovery characteristics of the garment fabric under test are determined based on the wrinkle flattening process. The thickness recovery characteristics and the wrinkle recovery characteristics are used as deformation recovery performance.

[0040] In specific implementation, firstly, the deformation feature sequence is time-aligned and normalized. Taking the end of dynamic mechanical loading as the zero point, the normalized deformation feature sequence is divided into a loading stage and an unloading recovery stage. The loading stage is the time period from the start to the end of dynamic mechanical loading, and the unloading recovery stage is the time period from the end of loading to the fabric deformation stabilization. Within the unloading recovery stage, a monotonic rebound segment where the deformation feature values ​​regress to the initial state is extracted as the deformation rebound segment of the fabric recovery process. Within the deformation rebound segment, the thickness recovery process and the wrinkle flattening process are identified based on the physical evolution characteristics of the local thickness change time sequence and the surface curvature change time sequence. Specifically, for The time derivative and rebound amplitude of local thickness changes are analyzed synchronously. When the time derivative changes from negative to positive (indicating that the thickness begins to rebound from the compressed state) and the rebound amplitude reaches a preset amplitude threshold, it is determined that the thickness recovery process has begun. The preset amplitude threshold can be determined by conducting a pre-experiment on the fabric to be tested, and the pre-experiment procedure is consistent with the formal testing procedure. The time derivative and rebound amplitude of surface curvature changes are also analyzed. When the time derivative changes from positive to negative (indicating that the fabric wrinkles begin to flatten and the curvature decreases) and the curvature falls back to the preset threshold range, it is determined that the fabric wrinkle flattening process has begun. The preset threshold range can be set according to the allowable degree of residual wrinkles after the fabric is flattened.

[0041] It should be noted that, for each moment, the deformation feature value has a dual corresponding meaning: in the identification of the thickness recovery process, the deformation feature value refers to the thickness change amount corresponding to the local thickness change sequence at that moment; in the identification of the wrinkle flattening process, the deformation feature value refers to the average curvature value corresponding to the surface curvature change sequence at the same moment.

[0042] In addition, in the specific implementation, during the thickness recovery process, the relative rebound ratio between the stable thickness of the fabric after unloading and the reference thickness before compression is used as the thickness recovery rate, calculated according to the formula "Thickness Recovery Rate = (Stable Thickness After Unloading - Extreme Compression Thickness) / (Reference Thickness Before Compression - Extreme Compression Thickness)". Here, the stable thickness after unloading is the thickness value when the fabric thickness no longer changes during the unloading recovery stage, the extreme compression thickness is the minimum fabric thickness during the loading stage, and the reference thickness before compression is the fabric thickness in the initial unloaded state. Simultaneously, the time required for the thickness of the garment fabric to rebound from the extreme compression value to a preset threshold range is used as the thickness recovery time, where the preset threshold range is ±3% of the reference thickness before compression. The thickness recovery rate and the thickness recovery time together constitute... The thickness recovery characteristics of the tested garment fabric during the testing process are determined by tracking the decay trajectory of the average curvature value of the fabric surface over time. The ratio of the curvature decrease after unloading to the curvature increase during loading is defined as the curvature decrease rate. The curvature increase during loading refers to the difference between the maximum average curvature at the end of loading and the baseline curvature before compression, while the curvature decrease after unloading refers to the difference between the maximum average curvature at the end of loading and the average curvature after unloading stabilization. The time required for the average curvature value to decay to a preset decay threshold is defined as the fold flattening time, where the preset decay threshold is predetermined based on the type of garment fabric. This yields the fold recovery characteristics composed of the curvature decrease rate and the fold flattening time. Finally, the thickness recovery characteristics and the fold recovery characteristics are fused at the feature level. The fusion method involves combining the thickness recovery rate, thickness recovery time, curvature decrease rate, and fold flattening time in a fixed order to construct a deformation recovery performance that comprehensively characterizes the overall performance of the tested garment fabric.

[0043] It should be noted that, based on the physical evolution characteristics of local thickness change time sequence and surface curvature change time sequence, the two different mechanisms of thickness recovery and wrinkle flattening can be automatically separated, avoiding the shortcomings of traditional uniaxial tension or static compression testing that cannot fully obtain multi-mode response information of fabrics; the thickness recovery rate and thickness recovery time are extracted to comprehensively evaluate the degree and speed of elasticity of the tested garment fabric, avoiding the one-sidedness of a single indicator; the curvature fallback rate and wrinkle flattening time are used to comprehensively evaluate the thoroughness and rate of wrinkle resistance, providing a quantitative basis for evaluating the shape retention of fabrics.

[0044] Preferably, in some embodiments, reference is made to Figure 3 As shown in the figure, this is an exemplary flowchart illustrating the determination of the mechanical response performance of the garment fabric under test according to some embodiments of this application. In this embodiment, the determination of the mechanical response performance of the garment fabric under test can be achieved by performing mechanical inversion based on the fabric compression data and the deformation characteristic sequence using the following steps: In step S10221, based on the corrected fabric compression data and the local thickness change time sequence in the deformation feature sequence, the stress-strain correspondence of the tested garment fabric during the stress process is established. In step S10222, the dynamic elastic modulus and stress relaxation characteristics of the garment fabric under test are determined according to the stress-strain correspondence. In step S10223, the elastic hysteresis characteristics and deformation recovery ability of the garment fabric under test are extracted according to the time sequence of surface curvature changes in the deformation feature sequence. In step S10224, the dynamic elastic modulus, stress relaxation characteristics, elastic hysteresis characteristics, and deformation recovery ability are used as mechanical response performance.

[0045] In specific implementation, firstly, the corrected fabric compression data at each moment is obtained from the fabric compression sequence, and the local thickness change time sequence is extracted from the deformation feature sequence; based on the corrected fabric compression data at each moment, the overall average contact pressure value of the fabric stress area is taken as the equivalent pressure value of the overall stress state of the fabric at that moment, and then the equivalent pressure value is converted according to the actual area of ​​the fabric stress area to obtain the equivalent pressure per unit area and define it as the stress value of the fabric at that moment; the thickness change in the compression direction at each moment in the local thickness change time sequence is recorded as the thickness compression amount at that moment, and the ratio of the thickness compression amount to the fabric reference thickness in the initial unloaded state is regarded as the strain value at that moment; traversing all moments corresponding to the loading stage, a series of discrete stress-strain data pairs are constructed by using the same timestamp for the stress value and strain value at each moment, thereby forming the stress-strain correspondence of the garment fabric under test during the detection process.

[0046] In addition, in specific implementation, an elastic deformation segment is selected from the stress-strain correspondence. This elastic deformation segment is clearly defined as a linear change segment in the loading stage where the strain value is less than an empirical strain threshold. The empirical strain threshold can be determined through pre-experimentation, and the pre-experimentation procedure is consistent with the formal testing procedure. Within the elastic deformation segment, the stress and strain values ​​corresponding to two discrete data points with uniformly increasing strain values ​​are selected. The difference between these two sets of stress values ​​is taken as the stress increment, and the difference between these two sets of strain values ​​is taken as the strain increment. The ratio of the stress increment to the strain increment is taken as the dynamic elastic modulus of the garment fabric under test during the testing process. For the loading stage, the stage where the strain value remains constant while the stress value decays over time is taken as the holding stage. The data sequence of stress value decaying over time within this holding stage is extracted from the stress-strain correspondence. The data sequence is fitted using an exponential decay fitting algorithm. The fitting iteration terminates when the fitting error is less than 0.005, obtaining the time constant required for the stress value to decay from the initial peak to a preset ratio. The preset ratio can be determined according to industry-standard testing requirements. The time constant is taken as the stress relaxation characteristic of the garment fabric under test.

[0047] It should be noted that the stress-strain relationship directly reflects the elastic deformation, plastic deformation, and energy dissipation characteristics of the tested garment fabric during the stress process, providing a basis for the subsequent extraction of mechanical parameters; the dynamic elastic modulus characterizes the ability of the tested garment fabric to resist deformation under dynamic mechanical loading conditions, and the larger the value, the stiffer the fabric; the stress relaxation characteristics characterize the ability of the tested garment fabric to maintain stress under constant deformation, and the larger the time constant, the better the fabric's anti-relaxation performance.

[0048] In specific implementation, based on the temporal sequence of surface curvature changes in the deformation feature sequence, the average curvature value of the surface of the garment fabric under test at each moment is obtained, and the average curvature value is paired one-to-one with the stress value at the corresponding moment to construct curvature-stress data pairs; according to the time sequence of the detection process, the data pairs within the period from the start of dynamic mechanical loading to the peak load are classified as loading stage curvature-stress data pairs, and the data pairs within the period from the peak load to the complete unloading load are classified as unloading stage curvature-stress data pairs; the loading stage curvature-stress data pairs are then compared with the unloading stage curvature-stress data pairs. Curvature-stress data are plotted as distribution curves in the same curvature-stress coordinate system. The closed region enclosed by the two curves is defined as the elastic hysteresis loop. The area of ​​the elastic hysteresis loop is calculated using a numerical integration algorithm, and this area represents the elastic hysteresis characteristic of the surface of the garment fabric under test. The elastic hysteresis characteristic characterizes the energy loss of the garment fabric under test due to internal friction and internal loss during dynamic stress. The larger the area, the greater the energy loss. Simultaneously, after the load is completely removed, the ratio of the residual average curvature value to the initial average curvature value of the fabric surface is determined as the deformation recovery capacity. Finally, the dynamic elastic modulus, stress relaxation characteristics, elastic hysteresis characteristics, and deformation recovery capacity are collectively used as the mechanical response performance of the garment fabric under test. These four indicators describe the comprehensive mechanical behavior of the garment fabric under test under dynamic mechanical loading from four dimensions: stiffness, relaxation resistance, energy dissipation, and recovery integrity, providing a quantitative basis for subsequent comprehensive performance evaluation.

[0049] It should be noted that by correlating the corrected fabric compression data with the local thickness change time series and surface curvature change time series in the deformation characteristic sequence, the reverse deduction from the original sensor signal to the intrinsic mechanical parameters of the fabric is realized. This avoids the complicated process of testing multiple mechanical indicators separately in traditional testing, and at the same time eliminates the coupling interference of deformation on pressure measurement, ensuring the accuracy and objectivity of mechanical response performance testing.

[0050] In some embodiments, the heat flow distribution data is coupled with a preset temperature and humidity difference for solution to obtain the heat flow and moisture flow balance relationship on both sides of the fabric, thereby obtaining the heat and moisture transfer performance of the garment fabric under test. Specifically, this can be achieved in the following manner: Obtain the corrected heat flow distribution data, and based on the preset temperature and humidity difference, analyze the heat transfer process and moisture diffusion process of the clothing fabric under test during the testing process. Based on the heat transfer process and the moisture diffusion process, the heat flow balance relationship and the moisture flow balance relationship on both sides of the fabric are established respectively. Based on the heat flow balance relationship and the moisture flow balance relationship, the thermal resistance, moisture resistance and heat-moisture coupling coefficient of the garment fabric to be tested are determined respectively, and then the thermal resistance, moisture resistance and heat-moisture coupling coefficient are used as heat and moisture transfer performance.

[0051] It should be noted that the heat transfer process is represented by a heat flux density time series curve that varies with dynamic mechanical loading and temperature and humidity boundary conditions. This heat flux density time series curve reflects the thermal insulation capacity and thermal response characteristics of the fabric at different times and under different stress states. The moisture diffusion process is used to describe the temporal evolution of water vapor migration across the fabric under dynamic mechanical loading, characterizing the moisture permeability and air permeability and moisture response characteristics of the fabric at different times and under different stress states. Its evolution law is quantified by the moisture diffusion flux time series curve.

[0052] In specific implementation, the temperature difference and humidity difference between the two sides of the fabric to be tested are directly obtained based on the preset temperature and humidity difference; the corrected heat flow distribution data for each moment is extracted from the heat flow distribution sequence; based on the corrected heat flow distribution data, the area-weighted average method is used to take the average of the heat flow density on the upper side and the heat flow density on the lower side of the fabric to be tested as the total heat flow density passing through the fabric at that moment. It should be noted that the total heat flow density is composed of sensible heat conduction component and latent heat phase change component; then, with the temperature difference and humidity difference as known boundary conditions, the least squares fitting is used to separate the sensible heat conduction component and latent heat phase change component corresponding to each moment from the total heat flow density. The fitting iteration termination condition is that the fitting error is less than 0.005; a heat flow density time series curve is generated by timestamping the sensible heat conduction components of all moments; by calculating the first and second derivatives of the heat flow density time series curve, the rising start point, peak point and decay termination point of the curve are identified, and the interval between adjacent feature points is defined as different stages of heat transfer, thereby completely describing the heat transfer process.

[0053] In addition, in actual implementation, the moisture diffusion flux at each time point is solved by inversely according to the relationship of "latent heat phase change component = latent heat of vaporization constant of water × moisture diffusion flux". The latent heat of vaporization constant of water is taken as the latent heat of vaporization value of pure water under standard atmospheric pressure and normal temperature range, specifically 2450~2460 J / g, which is clearly selected and recorded before detection. Based on the moisture diffusion flux at all times, the time series curve of moisture diffusion flux on both sides of the fabric is obtained according to the timestamp. By determining the derivative change and amplitude attenuation ratio of the time series curve of moisture diffusion flux, the initiation diffusion stage, stable migration stage and equilibrium tendency stage are divided in sequence, thus completely describing the moisture diffusion process.

[0054] It should be noted that the sensible heat conduction component refers to the heat transfer portion driven solely by the temperature difference between the two sides of the tested garment fabric, without accompanying moisture phase change; the latent heat phase change component refers to the heat absorbed or released during evaporation or condensation of water vapor inside or on the surface of the fabric, driven by the humidity difference between the two sides of the fabric, and is directly related to the moisture diffusion flux, reflecting the phase change heat transfer characteristics of the fabric under a heat-humidity coupling environment; the moisture diffusion flux refers to the mass of water vapor passing through a unit area of ​​the fabric per unit time, driven by the water vapor partial pressure difference between the two sides of the fabric, and this moisture diffusion flux quantifies the rate of moisture transfer in the fabric.

[0055] In specific implementation, based on the sensible heat conduction component in the heat transfer process, and according to the one-dimensional steady-state thermal conduction law, the temperature field equations at both ends of the fabric are established according to the formula "temperature difference = sensible heat conduction component × thermal resistance + edge heat loss". This temperature field equation is used as the heat flow balance relationship of the garment fabric under test during the testing process, where thermal resistance is the parameter to be calculated, and edge heat loss is obtained through instrument baseline pre-calibration. Through the moisture diffusion flux in the moisture diffusion process, combined with Fick's diffusion law, the moisture flow balance relationship of the garment fabric under test during the testing process is established: "humidity difference = moisture resistance × moisture diffusion flux + system pressure drop", where moisture resistance is the parameter to be calculated, and system pressure drop is obtained through instrument baseline pre-calibration. The calibration process is consistent with the formal testing process. Finally, based on the temperature difference, humidity difference, sensible heat conduction component, and moisture diffusion flux, as well as the edge heat loss and system pressure drop obtained from pre-calibration, the heat flow balance relationship and the moisture flow balance relationship are calculated respectively to obtain the thermal resistance and moisture resistance of the garment fabric under test. The partial derivative of the thermal resistance with the change of moisture diffusion flux is defined as the heat-moisture coupling coefficient. The physical meaning of the heat-moisture coupling coefficient is the degree of influence of the change of moisture diffusion flux on the thermal resistance, quantifying the heat-moisture synergistic transfer effect. The thermal resistance, moisture resistance, and heat-moisture coupling coefficient are used as the heat-moisture transfer performance indicators of the garment fabric under test. Among them, the thermal resistance reflects the thermal insulation ability of the fabric. The larger the value, the better the thermal insulation performance of the fabric. The moisture resistance reflects the moisture permeability and breathability of the fabric. The smaller the value, the better the moisture permeability and breathability performance of the fabric. The heat-moisture coupling coefficient reflects the heat-moisture synergistic transfer characteristics of the fabric under the condition of coexistence of temperature and humidity gradients. The smaller the value, the weaker the heat-moisture coupling effect and the better the heat-moisture transfer stability of the fabric.

[0056] It should be noted that by directly decomposing the mixed total heat flux density into independent heat transfer and moisture diffusion processes, the implicit moisture migration patterns can be dynamically captured, improving the system's data response speed and hardware reliability. By constructing heat flux balance and moisture flux balance relationships, the inherent heat loss and pressure drop in the dynamic detection environment are taken into account, ensuring that the physical parameters calculated subsequently are free from the inherent interference of the testing instrument, thereby guaranteeing the scientific nature, objectivity, and repeatability of the extrapolation results. The introduction of a heat-moisture coupling coefficient forms a multi-dimensional and quantifiable comprehensive evaluation system for the heat and moisture transfer performance of fabrics.

[0057] In step S103, a comprehensive evaluation is performed based on the deformation recovery performance, the mechanical response performance, and the heat and moisture transfer performance, and then the comprehensive performance test result of the garment fabric to be tested is output.

[0058] In some embodiments, the comprehensive performance test results of the garment fabric under test are output by comprehensively evaluating the deformation recovery performance, the mechanical response performance, and the heat and moisture transfer performance. Specifically, this can be achieved in the following manner: After normalizing the deformation recovery performance, mechanical response performance and heat and moisture transfer performance respectively, they are weighted and fused according to preset weight coefficients to obtain the comprehensive performance index of the clothing fabric to be tested. Based on the comparison results between the comprehensive performance index and the preset performance level threshold, the comprehensive performance level of the garment fabric to be tested is determined. The overall performance test results of the garment fabric to be tested are output based on the overall performance level.

[0059] In specific implementation, firstly, the extreme value normalization method is used to map the actual values ​​of each index of deformation recovery performance, mechanical response performance, and heat and moisture transfer performance to the interval [0, 1]. Specifically, for positive indices, positive Min-Max normalization is used to directly map the actual values ​​to the interval [0, 1], and the normalization calculation benchmark is the historical measured extreme value of the positive index. For negative indices, complementary transformation is performed first, followed by normalization, where the transformation formula is "transformed value = historical measured maximum value of the index - actual detected value". Then, the normalized deformation recovery performance score, mechanical response performance score, and heat and moisture transfer performance score are obtained. Based on the preset weight coefficients, a linear weighted fusion algorithm is used to weight and fuse the normalized deformation recovery performance score, mechanical response performance score, and heat and moisture transfer performance score to obtain the comprehensive performance index of the garment fabric to be tested. The sum of the weight coefficients of the three performance dimensions is 1, and a multiple linear regression algorithm is used for fitting to obtain the weight coefficients of each performance dimension. Secondly, based on the general standards of the apparel fabric testing industry, multiple performance grades and their corresponding threshold ranges are pre-defined. For example, performance grades can be divided into four levels: superior, first-class, qualified, and unqualified, with corresponding threshold ranges of ≥0.90, 0.75~0.90, 0.60~0.75, and <0.60, respectively. The comprehensive performance index is compared one by one with the threshold ranges; if it falls within the corresponding threshold range, it is determined to be the corresponding comprehensive performance grade. Finally, based on the determined comprehensive performance grade, the comprehensive performance test results of the apparel fabric to be tested are generated. The test results are output in the form of a structured report, including: the sample identification of the apparel fabric to be tested, the test date, the comprehensive performance index, the comprehensive performance grade, the normalized score of each performance dimension, and the original measured values, facilitating traceability and verification.

[0060] It should be noted that the positive indicators refer to those with larger actual values, indicating better performance in that aspect, including: thickness recovery rate in deformation recovery performance and stress relaxation characteristics in mechanical response performance; the negative indicators refer to those with smaller actual values, indicating better performance in that aspect, including: thickness recovery time, curvature fall-off rate, and wrinkle flattening time in deformation recovery performance; elastic hysteresis characteristics and deformation recovery capability in mechanical response performance; and moisture resistance and thermal-moisture coupling coefficient in heat and moisture transfer performance. The direction of the advantages and disadvantages of dynamic elastic modulus in mechanical response performance and thermal resistance in heat and moisture transfer performance are related to the specific application scenario of the fabric, and their positive and negative attributes can be adjusted according to the preset scenario.

[0061] Therefore, this application firstly utilizes a multi-parameter sensor array integrated with MEMS technology to simultaneously acquire three-dimensional deformation, compression, and heat flow distribution data of the garment fabric under test within a detection environment coupled with dynamic mechanical loading and a preset temperature and humidity difference. This overcomes the shortcomings of traditional uniaxial tension or static compression methods, which cannot simultaneously excite multi-mode deformation and pressure response of the fabric. Secondly, the compression data and heat flow distribution data of the fabric are corrected time-by-time based on the deformation feature sequence to eliminate spurious responses in pressure and heat flow measurements caused by fabric deformation, thereby improving the extraction accuracy of intrinsic mechanical and thermo-hygroscopic performance parameters. Furthermore, the deformation feature sequence is decoupled in time to identify... The thickness recovery process and the wrinkle flattening process independently evaluate the compression resilience and wrinkle resistance of the fabric, achieving a multi-dimensional and refined characterization of deformation recovery performance. Simultaneously, the total heat flux density is decomposed into sensible heat conduction and latent heat phase change components, and a balance relationship between heat flux and moisture flow is established. This allows for the acquisition of thermal resistance, moisture resistance, and the thermal-moisture coupling coefficient, quantifying dynamic thermal-moisture coupling characteristics and providing a more comprehensive basis for assessing the thermal and moisture comfort of the fabric. Finally, by weighted fusion of performance indicators from three dimensions—deformation recovery, mechanical response, and heat and moisture transfer—a comprehensive performance index is generated and mapped to a comprehensive performance level, providing an objective decision-making basis for fabric quality grading and targeted development.

[0062] In summary, the technical solution adopted in this application can rely on MEMS integrated sensing technology to achieve comprehensive detection of the multi-dimensional properties of clothing fabrics, thereby improving the accuracy and comprehensiveness of the detection results.

[0063] Furthermore, in another aspect of this application, in some embodiments, this application provides a comprehensive performance testing system for clothing fabrics based on multi-parameter sensing, referring to... Figure 4 The figure is a schematic diagram of a comprehensive testing system for the performance of clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. This comprehensive testing system for the performance of clothing fabrics based on multi-parameter sensing includes: The acquisition module 201 is used to construct a dynamic detection environment within the detection area and synchronously acquire multidimensional change data of the garment fabric under test through a multi-parameter sensor group integrated based on MEMS technology. The multidimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. The detection module 202 is used to determine the deformation recovery performance, mechanical response performance and heat and moisture transfer performance of the garment fabric under test during the detection process based on the three-dimensional deformation data, the fabric compression data and the heat flow distribution data, respectively. The evaluation module 203 is used to comprehensively evaluate the deformation recovery performance, the mechanical response performance and the heat and moisture transfer performance, and then output the comprehensive performance test results of the garment fabric to be tested.

[0064] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described comprehensive detection method for clothing fabric performance based on multi-parameter sensing.

[0065] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing a comprehensive performance testing method for clothing fabrics based on multi-parameter sensing, according to some embodiments of this application. The comprehensive performance testing method for clothing fabrics based on multi-parameter sensing in the above embodiments can be achieved through... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0066] The processor 301 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the comprehensive detection method for the performance of clothing fabrics based on multi-parameter sensing in this application.

[0067] The communication bus 302 can be used to transmit information between the aforementioned components.

[0068] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0069] The memory 303 stores program code for executing the solution of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the determination of the comprehensive detection method for clothing fabric performance based on multi-parameter sensing can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0070] Communication interface 304 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0071] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0072] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0073] In addition, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned comprehensive detection method for clothing fabric performance based on multi-parameter sensing.

[0074] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0075] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A comprehensive testing method for the performance of clothing fabrics based on multi-parameter sensing, characterized in that, Includes the following steps: A dynamic detection environment is constructed within the detection area, and multi-dimensional change data of the garment fabric under test is synchronously collected by a multi-parameter sensor group integrated based on MEMS technology. The multi-dimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. Based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test during the testing process are determined respectively. The overall performance test results of the garment fabric under test are then output based on a comprehensive evaluation of the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance.

2. The method for comprehensive performance testing of clothing fabrics based on multi-parameter sensing as described in claim 1, characterized in that, Constructing a dynamic testing environment within the testing area refers to applying a multi-mode composite dynamic mechanical load of periodic stretching, compression, and bending to the garment fabric to be tested, which is fixed within the testing area, and establishing a preset temperature and humidity difference.

3. The method for comprehensive performance testing of clothing fabrics based on multi-parameter sensing as described in claim 1, characterized in that, The multi-parameter sensor group integrated based on MEMS technology includes: a structured light imaging system for acquiring the three-dimensional morphology of the surface of clothing fabric, a pressure sensing array for acquiring the pressure distribution on the surface of clothing fabric, and a heat flow sensing array for acquiring the heat flux density on both sides of clothing fabric.

4. The method for comprehensive performance testing of clothing fabrics based on multi-parameter sensing as described in claim 1, characterized in that, Based on the three-dimensional deformation data, the fabric compression data, and the heat flow distribution data, the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance of the garment fabric under test during the testing process are determined, specifically including: Based on the three-dimensional deformation data, a deformation feature sequence of the garment fabric under test is generated during the testing process, and the deformation recovery performance is determined through the deformation feature sequence. Based on the fabric compression data and the deformation characteristic sequence, mechanical inversion is performed to determine the mechanical response performance of the garment fabric under test. Based on the heat flow distribution data and combined with the preset temperature and humidity difference, the heat flow and moisture flow balance relationship on both sides of the fabric is obtained, and then the heat and moisture transfer performance of the clothing fabric under test is obtained.

5. The method for comprehensive testing of clothing fabric performance based on multi-parameter sensing as described in claim 4, characterized in that, Determining deformation recovery performance through the deformation feature sequence specifically includes: The deformation feature sequence is decoupled in time to identify the thickness recovery process and wrinkle flattening process of the garment fabric under test during the detection process. The thickness recovery characteristics of the garment fabric under test are determined based on the thickness recovery process, and the wrinkle recovery characteristics of the garment fabric under test are determined based on the wrinkle flattening process. The thickness recovery characteristics and the wrinkle recovery characteristics are used as deformation recovery performance.

6. The method for comprehensive performance testing of clothing fabrics based on multi-parameter sensing as described in claim 4, characterized in that, Based on the fabric compression data and the deformation characteristic sequence, mechanical inversion is performed to determine the mechanical response performance of the tested garment fabric, specifically including: Based on the corrected fabric compression data and the local thickness change time sequence in the deformation feature sequence, the stress-strain correspondence of the tested garment fabric during the stress process is established. Based on the stress-strain relationship, the dynamic elastic modulus and stress relaxation characteristics of the garment fabric under test are determined during the testing process. Based on the temporal sequence of surface curvature changes in the deformation feature sequence, the elastic hysteresis characteristics and deformation recovery ability of the garment fabric under test during the testing process are extracted. The dynamic elastic modulus, stress relaxation characteristics, elastic hysteresis characteristics, and deformation recovery ability are used as mechanical response properties.

7. The method for comprehensive performance testing of clothing fabrics based on multi-parameter sensing as described in claim 1, characterized in that, The comprehensive performance test results of the tested garment fabric are output based on a comprehensive evaluation of the deformation recovery performance, mechanical response performance, and heat and moisture transfer performance. Specifically, these results include: After normalizing the deformation recovery performance, mechanical response performance and heat and moisture transfer performance respectively, they are weighted and fused according to preset weight coefficients to obtain the comprehensive performance index of the clothing fabric to be tested. Based on the comparison results between the comprehensive performance index and the preset performance level threshold, the comprehensive performance level of the garment fabric to be tested is determined. The overall performance test results of the garment fabric to be tested are output based on the overall performance level.

8. A comprehensive performance testing system for clothing fabrics based on multi-parameter sensing, characterized in that, The steps for implementing the comprehensive performance testing method for clothing fabrics based on multi-parameter sensing as described in any one of claims 1 to 7 include: The acquisition module is used to construct a dynamic detection environment within the detection area. It synchronously acquires multidimensional change data of the garment fabric under test through a multi-parameter sensor group integrated based on MEMS technology. The multidimensional change data includes three-dimensional deformation data, fabric compression data, and heat flow distribution data. The detection module is used to determine the deformation recovery performance, mechanical response performance and heat and moisture transfer performance of the garment fabric under test during the detection process based on the three-dimensional deformation data, the fabric compression data and the heat flow distribution data, respectively. The evaluation module is used to comprehensively evaluate the deformation recovery performance, mechanical response performance and heat and moisture transfer performance, and then output the comprehensive performance test results of the garment fabric to be tested.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the comprehensive testing method for the performance of clothing fabrics based on multi-parameter sensing as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the comprehensive detection method for the performance of clothing fabrics based on multi-parameter sensing as described in any one of claims 1 to 7.

Images