Garment fabric stretching detection method and system

Abstract

The invention relates to the technical field of material detection, and discloses a garment fabric stretching detection method and system, and the method comprises the steps: setting a multi-mode stretching detection sequence of a fabric sample according to the attributes of a garment fabric under the condition of simulating a dynamic stress state in an actual wearing process; performing stress detection on the fabric sample to obtain a stretching process data set of the fabric sample; performing tensile characteristic evaluation on the fabric sample to obtain a tensile property index of the fabric sample; performing acoustic emission event response on the fabric sample, and identifying microscopic damage information of the fabric sample according to an acoustic emission event response result; performing time sequence correlation analysis on the stretching process data set and the microscopic damage information to construct a damage evolution graph of the fabric sample; performing structured integration on the tensile property index and the damage evolution graph to obtain a tensile detection report of the fabric sample; the stretching detection efficiency of the garment fabric can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material detection, and in particular to a garment fabric tensile detection method and system. BACKGROUND

[0002] The existing garment fabric tensile detection technology mostly sets the detection scheme based on a single static force mode, which fails to fully simulate the complex dynamic force state of the fabric in the actual wearing process, resulting in insufficient adaptability of the detection sequence to the real application scene, difficulty in fully capturing the tensile response characteristics of the fabric under different force modes, and inability of the detection results to accurately reflect the actual use performance of the fabric.

[0003] Meanwhile, the traditional detection method lacks systematic integration in the data processing and analysis link, can only obtain the macro tensile performance parameters of the fabric, cannot effectively associate the mechanical changes and micro damage evolution law in the tensile process, and has low analysis efficiency of the detection data, making it difficult to quickly generate a structured and high-precision detection report, thereby affecting the overall efficiency and evaluation accuracy of the fabric tensile detection, and failing to meet the timeliness and comprehensiveness requirements of the industry on the detection results. SUMMARY

[0004] The present application provides a garment fabric tensile detection method and system to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides a garment fabric tensile detection method, comprising:

[0006] S1, under the dynamic force state simulating the actual wearing process, setting a multi-mode tensile detection sequence of a fabric sample according to the fabric properties;

[0007] S2, based on the multi-mode tensile detection sequence, performing stress detection on the fabric sample to obtain a tensile process data set of the fabric sample;

[0008] S3, based on the tensile process data set, performing tensile characteristic evaluation on the fabric sample to obtain a tensile performance index of the fabric sample;

[0009] S4, performing acoustic emission event response on the fabric sample, and identifying the micro damage information of the fabric sample according to the acoustic emission event response result;

[0010] S5, performing time sequence correlation analysis on the tensile process data set and the micro damage information to construct a damage evolution map of the fabric sample;

[0011] S6, structurally integrating the tensile performance index and the damage evolution map to obtain a tensile detection report of the fabric sample.

[0012] In a preferred embodiment, the multi-mode tensile detection sequence of the fabric sample is set according to the fabric attribute of the fabric sample in the dynamic stress state simulating the actual wearing process, including:

[0013] Based on the fabric attribute of the fabric sample, an initial mechanical parameter set of the fabric sample is extracted;

[0014] In the dynamic stress state simulating the actual wearing process, the initial mechanical parameter set is subjected to stress mode recognition to obtain a typical stress mode of the fabric sample;

[0015] Based on the typical stress mode, the initial mechanical parameter set is subjected to multi-dimensional coupling iterative optimization to obtain a primary detection sequence of the fabric sample;

[0016] The primary detection sequence is subjected to buffer detection stage embedding to obtain a transition detection sequence of the fabric sample;

[0017] The transition detection sequence is subjected to loading rate adaptive modulation to obtain a multi-mode tensile detection sequence of the fabric sample.

[0018] In a preferred embodiment, the stress detection of the fabric sample based on the multi-mode tensile detection sequence obtains a tensile process data set of the fabric sample, including:

[0019] Based on the multi-mode tensile detection sequence, multi-axial tensile load is loaded on the fabric sample to obtain a real-time stress response signal of the fabric sample;

[0020] The real-time stress response signal is subjected to multi-channel synchronous collection to obtain a synchronous stress signal set of the fabric sample;

[0021] The synchronous stress signal set is subjected to baseline correction to obtain a clean stress signal sequence of the fabric sample;

[0022] The clean stress signal sequence is subjected to time domain feature analysis to obtain a tensile process data set of the fabric sample.

[0023] In a preferred embodiment, the tensile feature evaluation of the fabric sample based on the tensile process data set obtains a tensile performance index of the fabric sample, including:

[0024] The stress-strain relationship curve in the tensile process data set is subjected to feature inflection point analysis to obtain elastic response parameters, plasticity starting parameters and fracture limit parameters of the fabric sample;

[0025] The elastic response parameter, the plastic initiation parameter, and the fracture limit parameter are normalized to obtain the normalized feature vector set of the fabric sample.

[0026] Based on the normalized feature vector set, the tensile performance index of the fabric sample is calculated, wherein the formula for calculating the tensile performance index is as follows: ;

[0027] In the formula, This indicates the tensile property index. This indicates the contribution weight of the elasticity stage of the fabric sample. This represents the elastic modulus in the normalized eigenvector set. This represents the reference elastic modulus of the fabric sample. This indicates the contribution weight of the yield stage of the fabric sample. This represents the yield stress in the normalized eigenvector set. This represents the reference yield stress of the fabric sample. This indicates the contribution weight of the fracture stage of the fabric sample. This represents the elongation at break in the normalized feature vector set. This represents the baseline elongation at break of the fabric sample.

[0028] The tensile performance index is mapped and matched with a preset performance level boundary to obtain the tensile performance index of the fabric sample.

[0029] In a preferred embodiment, the step of performing acoustic emission event response on the fabric sample and identifying the microscopic damage information of the fabric sample based on the acoustic emission event response results includes: Based on the multi-mode tensile stress state of the fabric sample, the original acoustic emission signal of the fabric sample is collected by an acoustic emission sensor array.

[0030] Perform time-frequency domain joint noise reduction on the original acoustic emission signal to obtain the noise-reduced acoustic emission signal of the fabric sample;

[0031] Event trigger detection is performed on the noise-reduced acoustic emission signal to obtain the event trigger time sequence of the fabric sample;

[0032] Based on the event triggering time series, independent acoustic emission event features are extracted from the denoised acoustic emission signal to obtain the acoustic emission event feature parameters of the denoised acoustic emission signal.

[0033] The acoustic emission event feature parameters are mapped to a preset typical damage mode feature library to obtain the microscopic damage information of the fabric sample.

[0034] In a preferred embodiment, mapping the acoustic emission event feature parameters to a preset typical damage pattern feature library to obtain the microscopic damage information of the fabric sample includes:

[0035] Based on the acoustic emission event feature parameters, the feature library of typical damage modes is projected into a multi-dimensional feature space to obtain the feature projection vector of the fabric sample.

[0036] Nearest neighbor pattern search is performed on the feature projection vector to obtain the damage pattern category of the fabric sample;

[0037] The damage pattern categories are correlated and integrated in a spatiotemporal manner to obtain the damage event sequence of the fabric sample;

[0038] The severity of the damage event sequence is assessed to obtain the microscopic damage information of the fabric sample.

[0039] In a preferred embodiment, the step of performing a time-series correlation analysis between the stretching process dataset and the microscopic damage information to construct a damage evolution map of the fabric sample includes:

[0040] The mechanical state sequence in the stretching process dataset and the damage event sequence in the micro-damage information are fused with temporal information to obtain the fused temporal data stream of the fabric sample;

[0041] By performing association rule mining on the fused time-series data stream, the symbiotic relationship between specific mechanical state parameters and specific micro-damage types of the fabric sample under different stretching stages is analyzed.

[0042] Based on the symbiotic relationship, a damage dynamic correlation matrix for the fabric sample is constructed;

[0043] The damage dynamic correlation matrix is ​​visualized and topologically reconstructed to obtain the damage evolution map of the fabric sample.

[0044] In a preferred embodiment, the step of visually reconstructing the damage dynamic correlation matrix to obtain the damage evolution map of the fabric sample includes:

[0045] The nodes and associated edges in the damage dynamic correlation matrix are visualized and mapped to obtain the preliminary topological structure of the fabric sample.

[0046] Hierarchical clustering is performed on the preliminary topology, and edge weight optimization is performed on the clustered preliminary topology to obtain the optimized topology network of the fabric sample.

[0047] Key nodes are identified in the temporal paths of the optimized topology network to obtain the key evolution path of the fabric sample;

[0048] The key evolution path is overlaid with multidimensional information to obtain the damage evolution map of the fabric sample.

[0049] In a preferred embodiment, the step of structurally integrating the tensile performance indicators with the damage evolution map to obtain a tensile test report for the fabric sample includes:

[0050] Based on a preset report template framework, an information association index is established between the tensile performance index and the damage evolution map;

[0051] Based on the information association index, key damage evolution stages and corresponding mechanical states are extracted from the damage evolution map;

[0052] The key damage evolution stages and corresponding mechanical states are associated with the tensile performance indicators to obtain the damage association labeling information of the fabric sample.

[0053] According to the damage development sequence and performance degradation logic of the fabric sample, the damage association annotation information is filled into the report template frame to obtain the initial structured report of the fabric sample.

[0054] A key conclusion summary is generated from the initial structured report to obtain the tensile test report of the fabric sample.

[0055] To address the above problems, the present invention also provides a garment fabric stretch testing system, the system comprising:

[0056] The detection sequence setting module is used to set a multi-mode stretch detection sequence for fabric samples based on the properties of the clothing fabric under dynamic stress conditions during the simulation of actual wearing process.

[0057] The stress detection module is used to perform stress detection on the fabric sample based on the multi-mode tensile detection sequence to obtain a dataset of the tensile process of the fabric sample.

[0058] The performance index evaluation module is used to evaluate the tensile characteristics of the fabric sample based on the tensile process dataset to obtain the tensile performance index of the fabric sample.

[0059] The micro-damage identification module is used to perform acoustic emission event response on the fabric sample and identify the micro-damage information of the fabric sample based on the acoustic emission event response results.

[0060] The damage map construction module is used to perform time-series correlation analysis between the stretching process dataset and the micro-damage information to construct a damage evolution map of the fabric sample.

[0061] The test report generation module is used to structurally integrate the tensile performance indicators and the damage evolution map to obtain a tensile test report for the fabric sample.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] 1. This invention simulates the complex dynamic stress state of actual wear, sets up a multi-mode tensile testing sequence based on fabric properties, and accurately identifies microscopic damage information using acoustic emission technology. At the same time, it constructs a damage evolution map to realize the temporal correlation between tensile mechanical data and microscopic damage, comprehensively capturing the performance changes and damage patterns of the entire fabric stretching process. This makes the test results more consistent with actual application scenarios and significantly improves the accuracy of the assessment.

[0064] 2. This invention efficiently processes test data through multi-channel synchronous acquisition and time-domain feature analysis. By using a structured integration process, it merges tensile performance indicators with damage evolution maps to quickly generate test reports containing key information. This simplifies the data processing and report preparation process, improving overall testing efficiency while ensuring complete and logically clear report information, thus meeting the industry's needs for timeliness and practicality in testing. Attached Figure Description

[0065] Figure 1 This is a schematic flowchart of a method for testing the tensile strength of clothing fabrics according to an embodiment of the present invention.

[0066] Figure 2 This is a functional block diagram of a garment fabric stretch testing system provided in an embodiment of the present invention;

[0067] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0068] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0069] This application provides a method for testing the tensile strength of clothing fabrics. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, or other similar device. In other words, the method for testing the tensile strength of clothing fabrics can be executed by software or hardware installed on a terminal device or a server-side device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0070] Reference Figure 1 The diagram shown is a flowchart illustrating a method for testing the tensile strength of clothing fabrics according to an embodiment of the present invention. In this embodiment, the method for testing the tensile strength of clothing fabrics includes:

[0071] S1. Under the dynamic stress state of simulating actual wearing process, set the multi-mode stretching detection sequence of the fabric sample according to the properties of the clothing fabric.

[0072] In this embodiment of the invention, the step of setting a multi-mode stretching detection sequence for fabric samples based on the fabric properties under dynamic stress conditions during simulated actual wearing includes:

[0073] Based on the fabric properties of the fabric sample, the initial set of mechanical parameters of the fabric sample is extracted.

[0074] Under the dynamic stress state during the simulation of actual wearing process, the initial set of mechanical parameters is subjected to stress mode identification to obtain the typical stress mode of the fabric sample.

[0075] Based on the typical stress mode, the initial set of mechanical parameters is optimized through multi-dimensional coupling iterative optimization to obtain the primary detection sequence of the fabric sample;

[0076] The primary detection sequence is embedded in a buffer detection stage to obtain the transition detection sequence of the fabric sample;

[0077] The transition detection sequence is subjected to adaptive loading rate modulation to obtain the multi-mode stretch detection sequence of the fabric sample.

[0078] Based on the fabric properties of the fabric sample, an initial set of mechanical parameters is extracted from the fabric sample. The operator selects the fabric sample to be tested and determines the testing dimensions according to the basic properties of the fabric. These testing dimensions cover tensile properties, tear properties, bursting properties, and bending properties. For each testing dimension, a corresponding mechanical testing device is used to carry out basic testing. For tensile property testing, the two ends of the fabric sample are fixed and a constant pretension is applied to keep the sample flat. Then, it is stretched at a uniform speed to a set deformation and the force data is recorded. For tear property testing, a single-slit tearing method is used. A slit of a specified length is cut on the fabric sample, the two ends of the sample are clamped and a tensile force is applied in the direction of the slit expansion, and the force change during the tearing process is recorded. For bursting property testing, a spherical pressure head is applied perpendicularly to the surface of the fabric sample. The pressure head is pressed down at a uniform speed until the fabric breaks and the bursting force and bursting displacement are recorded. For bending property testing, the fabric sample is bent to a specified angle and held for a fixed time. After release, the elasticity angle of the fabric is measured. All the data obtained from the above-mentioned testing dimensions are integrated to form the initial set of mechanical parameters of the fabric sample.

[0079] Under the dynamic stress conditions simulating actual wearing, the initial set of mechanical parameters is subjected to stress pattern identification to obtain the typical stress pattern of the fabric sample. The operator constructs a dynamic stress scenario simulating actual wearing, which includes the tensile force during human walking, the compressive force during sitting, the torsional force during limb movement, and the shear force during daily friction. Each data in the initial set of mechanical parameters is mapped to a different dynamic stress scenario. The mechanical response data of the fabric sample under different stress scenarios are compared, and the stress response feature that appears most frequently and has the most significant impact on the performance of the clothing is selected. The stress state corresponding to the stress response feature is summarized and determined as the typical stress pattern of the fabric sample.

[0080] Based on the typical stress patterns, the initial set of mechanical parameters is subjected to multi-dimensional coupling iterative optimization to obtain the primary detection sequence of the fabric sample. Operators use the typical stress patterns as the core basis, associating and coupling the parameters in the initial set of mechanical parameters according to the action rules of the typical stress patterns. Mechanical parameters that highly match the typical stress patterns are retained first, while redundant parameters unrelated to the typical stress patterns are eliminated. The retained parameters are then iteratively optimized. The first round of optimization adjusts the parameter values ​​based on the stress intensity of the typical stress patterns. The second round of optimization verifies the parameter stability based on the action duration of the typical stress patterns. Each subsequent round of optimization is based on the results of the previous round, adjusting the parameter association method in conjunction with the dynamic change characteristics of the typical stress patterns, until all parameters accurately reflect the mechanical properties of the fabric under the typical stress patterns. The parameters after multiple rounds of optimization are arranged according to the order of detection dimensions to form the primary detection sequence of the fabric sample.

[0081] The primary detection sequence is embedded with a buffer detection stage to obtain a transition detection sequence for the fabric sample. The operator analyzes the variation law of mechanical parameters between adjacent detection dimensions in the primary detection sequence, determines the transition interval with large parameter fluctuations, and embeds the buffer detection stage within this transition interval. The specific operation of the buffer detection stage is to apply a low-intensity, slow-rate force to the fabric sample, continuously monitor the mechanical response data of the fabric under this force, and supplement the transition interval of the primary detection sequence with the monitored buffer mechanical data to make the parameter transition between adjacent detection dimensions more stable. At the same time, it is ensured that the supplemented buffer mechanical data maintains the same detection standard and data format as the original data in the primary detection sequence. After the buffer detection stage is embedded, the transition detection sequence of the fabric sample is formed.

[0082] The transition detection sequence is adaptively modulated with a loading rate to obtain a multi-mode tensile detection sequence for the fabric sample. Based on the fabric's mechanical properties at different detection stages in the transition detection sequence, the operator determines the optimal loading rate for each detection stage. For detection stages with stable fabric mechanical properties, a higher loading rate is used to improve detection efficiency; for detection stages with sensitive fabric mechanical properties, a lower loading rate is used to ensure detection accuracy. During modulation, the stress and deformation state of the fabric sample is monitored in real time. When abnormal fluctuations occur in the detection data, the loading rate is automatically adjusted to a suitable range to ensure that the loading rate of each detection stage can adapt to the real-time mechanical response of the fabric. All detection data after adaptive loading rate modulation are integrated according to the sequence of the detection process to form the multi-mode tensile detection sequence for the fabric sample.

[0083] The beneficial effects are that by conducting full-process fabric mechanical parameter testing and optimization, a multi-mode tensile testing sequence that accurately matches the actual wearing stress is formed. This ensures the comprehensiveness, continuity and accuracy of the test data, while also improving the targeting and efficiency of the testing. It provides a reliable basis for the research and development, selection and quality control of clothing fabrics, and helps to improve the comfort and durability of clothing.

[0084] S2. Based on the multi-mode stretching detection sequence, stress detection is performed on the fabric sample to obtain the stretching process dataset of the fabric sample.

[0085] In this embodiment of the invention, the step of performing stress detection on the fabric sample based on the multi-mode tensile detection sequence to obtain a tensile process dataset of the fabric sample includes:

[0086] Based on the multi-mode tensile testing sequence, the fabric sample is subjected to multiaxial tensile load to obtain the real-time stress response signal of the fabric sample.

[0087] The real-time stress response signal is acquired synchronously through multiple channels to obtain a set of synchronous stress signals for the fabric sample.

[0088] Baseline correction is performed on the synchronous stress signal set to obtain the clean stress signal sequence of the fabric sample;

[0089] The time-domain feature analysis of the clean stress signal sequence is performed to obtain the stretching process dataset of the fabric sample.

[0090] Based on the multi-mode tensile testing sequence, the fabric sample is subjected to multi-axial tensile load to obtain the real-time stress response signal of the fabric sample. The operator fixes the fabric sample flat on the clamping device of the multi-axis tensile testing platform to ensure that the fabric sample is subjected to uniform force in all directions and has no initial wrinkles. According to the loading rate and force direction requirements of different testing stages in the multi-mode tensile testing sequence, the driving component of the multi-axis tensile testing platform is controlled to apply corresponding tensile loads from the warp and weft directions and diagonal directions of the fabric sample. During the loading process, the stress deformation of the fabric sample is continuously monitored, and the stress change information generated by the fabric sample under different loads is recorded synchronously. These real-time recorded stress change information are integrated to form the real-time stress response signal of the fabric sample.

[0091] The real-time stress response signal is synchronously acquired through multiple channels to obtain a set of synchronous stress signals for the fabric sample. Operators deploy multiple stress sensing units in different areas of the fabric sample, each corresponding to a signal acquisition channel. The acquisition time reference for all signal acquisition channels is kept consistent. The signal acquisition device is then activated, allowing each channel to simultaneously receive and record the real-time stress response signal for its corresponding area. During the acquisition process, the signal transmission rate of each channel is ensured to be the same to avoid signal delays or loss. After the load loading process corresponding to the multi-mode tensile testing sequence is completed, the real-time stress response signals acquired by each channel are categorized and integrated according to the acquisition area to form a set of synchronous stress signals for the fabric sample.

[0092] The synchronous stress signal set is baseline-corrected to obtain the clean stress signal sequence of the fabric sample. The operator selects the signal data of the synchronous stress signal set in the stage before the tensile load is applied as the baseline reference standard. Each group of signal data in the synchronous stress signal set is compared with the baseline reference standard, and the deviation value between the signal data and the baseline reference standard is calculated. Then, the corresponding deviation value is uniformly deducted from all signal data in the synchronous stress signal set to eliminate the signal deviation caused by the initial error of the sensing unit and environmental interference factors. After the deviation correction is completed, all the corrected signal data are arranged in the order of the tensile load application time to form the clean stress signal sequence of the fabric sample.

[0093] The clean stress signal sequence is analyzed in the time domain to obtain the tensile process dataset of the fabric sample. The operator divides the clean stress signal sequence according to the load loading stage of the multi-mode tensile detection sequence. For the signal data of each stage, the peak and valley value change trend and the duration characteristics of the signal are analyzed. Key feature information such as the initial stress value, stable stress value and termination stress value of the signal in each stage are extracted. These key feature information are associated with the corresponding load loading stage. At the same time, the deformation state information of the fabric sample in each stage is recorded. The key feature information and deformation state information of all stages are summarized and organized to form the tensile process dataset of the fabric sample.

[0094] The beneficial effects include accurately simulating the actual stress state of the fabric, ensuring the timeliness and consistency of signal acquisition, eliminating signal interference, improving data accuracy, uncovering key characteristics of fabric stretching, and providing reliable support for the evaluation of fabric mechanical properties through the resulting dataset.

[0095] S3. Based on the stretching process dataset, evaluate the stretching characteristics of the fabric sample to obtain the stretching performance index of the fabric sample.

[0096] In this embodiment of the invention, the step of evaluating the tensile characteristics of the fabric sample based on the tensile process dataset to obtain the tensile performance index of the fabric sample includes:

[0097] The stress-strain relationship curves in the tensile process dataset are analyzed for characteristic inflection points to obtain the elastic response parameters, plastic initiation parameters, and fracture limit parameters of the fabric sample.

[0098] The elastic response parameter, the plastic initiation parameter, and the fracture limit parameter are normalized to obtain the normalized feature vector set of the fabric sample.

[0099] Based on the normalized feature vector set, the tensile performance index of the fabric sample is calculated, wherein the formula for calculating the tensile performance index is as follows:

[0100] ;

[0101] In the formula, This indicates the tensile property index. This indicates the contribution weight of the elasticity stage of the fabric sample. This represents the elastic modulus in the normalized eigenvector set. This represents the reference elastic modulus of the fabric sample. This indicates the contribution weight of the yield stage of the fabric sample. This represents the yield stress in the normalized eigenvector set. This represents the reference yield stress of the fabric sample. This indicates the contribution weight of the fracture stage of the fabric sample. This represents the elongation at break in the normalized feature vector set. This represents the baseline elongation at break of the fabric sample.

[0102] The tensile performance index is mapped and matched with a preset performance level boundary to obtain the tensile performance index of the fabric sample.

[0103] The stress-strain relationship curves in the tensile process dataset are analyzed for characteristic inflection points to obtain the elastic response parameters, plastic initiation parameters, and fracture limit parameters of the fabric sample. The operator retrieves the stress-strain relationship curves from the tensile process dataset, observes the curve's changing trend, and identifies the point where the slope remains stable and the point where the slope begins to change. The parameter corresponding to this point is the elastic response parameter. Continuing to observe along the curve's extension direction, the operator identifies the starting point where the stress no longer increases significantly with increasing strain. The parameter corresponding to this starting point is the plastic initiation parameter. The curve is further tracked until a critical point where the stress suddenly drops. The parameter corresponding to this critical point is the fracture limit parameter. These three parameters are then organized and aggregated to obtain the elastic response parameters, plastic initiation parameters, and fracture limit parameters of the fabric sample.

[0104] The elastic response parameter, the plasticity initiation parameter, and the fracture limit parameter are normalized to obtain a normalized feature vector set for the fabric sample. The operator selects a commonly used performance parameter benchmark value in the fabric testing field and compares the elastic response parameter, plasticity initiation parameter, and fracture limit parameter with their corresponding benchmark values. The scale of each parameter is adjusted according to a unified reference standard to ensure that the adjusted parameters are within the same order of magnitude, eliminating comparison barriers caused by dimensional differences between different parameters. The adjusted elastic response parameter, plasticity initiation parameter, and fracture limit parameter are then combined in a fixed order to form the normalized feature vector set for the fabric sample.

[0105] Based on the normalized feature vector set, the tensile performance index of the fabric sample is calculated. The operator integrates the elastic response parameter, plasticity initiation parameter, and breaking limit parameter according to the influence weight of each parameter in the normalized feature vector set on the tensile performance of the fabric. The operator highlights the influence ratio of the elastic response parameter on the fabric's resilience, emphasizes the influence ratio of the plasticity initiation parameter on the fabric's resistance to deformation, and pays attention to the influence ratio of the breaking limit parameter on the fabric's resistance to tearing. The parameters are comprehensively considered according to their influence weights to form a comprehensive index that can fully reflect the overall tensile performance of the fabric. This comprehensive index is the tensile performance index of the fabric sample.

[0106] In the formula for calculating the tensile property index, the tensile property index formula contains... The tensile performance index is the result of this step, which is a quantitative indicator obtained by integrating the parameters and weights of each stage through a formula.

[0107] The contribution weight of the elastic stage is derived from the impact of the elastic response of fabric samples on fit and rebound comfort in actual wearing scenarios. This is achieved by collecting elastic performance feedback data on similar garment fabrics in daily wear, as well as application case data of this type of fabric in garment production. By statistically summarizing this data, the proportion of the elastic stage parameter in the overall tensile performance is determined, thus obtaining... The specific value.

[0108] The elastic modulus in the normalized eigenvector set is derived by first analyzing the characteristic inflection points of the stress-strain relationship curve in the tensile process dataset to obtain the elastic response parameters of the fabric sample. Then, these elastic response parameters are normalized in dimension to the reference elastic modulus of the fabric sample. The resulting parameter is the elastic modulus in the normalized eigenvector set. .

[0109] The baseline elastic modulus of the fabric sample is derived from the general performance standards of this type of fabric in the fabric testing field. A large amount of elastic modulus test data of qualified fabrics in this category is collected, outliers are removed from these data, and the statistically typical stable value is taken as the baseline. .

[0110] The yield stage contribution weight is derived from the impact of plastic deformation on garment shape retention and durability during daily wear of the fabric. This is achieved by collecting feedback data on plastic deformation of the fabric after long-term wear, as well as yield performance quality assessment data of the fabric in garment production. By summarizing and analyzing this data, the proportion of yield stage parameters in the overall tensile properties is determined, thus obtaining... The specific value.

[0111] The yield stress in the normalized eigenvector set is derived by first analyzing the characteristic inflection points of the stress-strain relationship curve in the tensile process dataset to obtain the plastic initiation parameter of the fabric sample. Then, this plastic initiation parameter is normalized in dimension along with the reference yield stress of the fabric sample. The resulting parameter is the yield stress in the normalized eigenvector set. .

[0112] The baseline yield stress of the fabric sample is derived from the general performance standards for this type of fabric in the fabric testing field. A large amount of yield stress test data from qualified fabrics of this type is collected, outliers are removed from these data, and the statistically typical stable value is taken as the baseline. .

[0113] The contribution weight of the fracture stage is derived from the impact of fabric breakage on wearing safety and garment lifespan during actual use. This is achieved by collecting data on breakage cases of this type of fabric during use, as well as quality test data on the fabric's fracture performance. By statistically summarizing this data, the proportion of fracture stage parameters in the overall tensile properties is determined, thus obtaining... The specific value.

[0114] The breaking elongation in the normalized feature vector set is derived by first analyzing the characteristic inflection points of the stress-strain relationship curve in the tensile process dataset to obtain the breaking limit parameter of the fabric sample. Then, this breaking limit parameter is normalized in dimension to the reference breaking elongation of the fabric sample. The resulting parameter is the breaking elongation in the normalized feature vector set. .

[0115] The baseline breaking elongation of the fabric sample is derived from the general performance standards for this type of fabric in the fabric testing field. A large amount of breaking elongation test data for qualified fabrics of this type is collected, outliers are removed from this data, and the statistically stable value obtained is used as the baseline. .

[0116] The significance of this formula lies in calculating the ratios of the normalized elastic modulus, yield stress, and elongation at break to their corresponding benchmark parameters. This reflects the actual performance of the fabric parameters relative to the benchmark. Furthermore, a weighted sum is applied, incorporating the contribution weights of each stage, thereby integrating the fabric's performance in the elastic, yield, and breaking stages into a quantified tensile performance index. This enables a comprehensive quantitative assessment of the overall tensile properties of the fabric. This index is the core basis for subsequently mapping and matching it with the preset performance level boundary to obtain the fabric tensile performance index. This transforms the assessment of fabric tensile performance from scattered parameters into a unified quantitative index, improving the convenience and intuitiveness of the assessment.

[0117] The tensile performance index is mapped and matched with the preset performance level boundary to obtain the tensile performance index of the fabric sample. The operator retrieves the preset fabric tensile performance level boundary, which covers the range of tensile performance indices corresponding to different grades of fabric. The calculated tensile performance index of the fabric sample is compared with the index range of each level boundary one by one to determine the level interval to which the tensile performance index belongs. The fabric tensile performance level corresponding to the level interval is determined as the final result, which is the tensile performance index of the fabric sample.

[0118] The beneficial effects include the ability to accurately extract three core parameters of the fabric—elastic response, plastic initiation fracture limit, and tensile strength—by analyzing the characteristic inflection points of the stress-strain relationship curve, thus comprehensively characterizing the mechanical properties of the fabric during tensile testing. Dimensional normalization of these three parameters eliminates differences in magnitude between parameters, ensuring the fairness and accuracy of subsequent performance evaluations. The tensile performance index, calculated based on the normalized feature vector set, comprehensively reflects the overall tensile performance of the fabric, avoiding the bias of single-parameter evaluation. Mapping and matching the tensile performance index with preset grade boundaries allows for the rapid determination of fabric tensile performance indicators, providing an intuitive and reliable basis for fabric grading, selection, and quality assessment.

[0119] S4. Perform acoustic emission event response on the fabric sample, and identify the microscopic damage information of the fabric sample based on the acoustic emission event response results.

[0120] In this embodiment of the invention, the step of performing acoustic emission event response on the fabric sample and identifying the microscopic damage information of the fabric sample based on the acoustic emission event response results includes:

[0121] Based on the multi-mode tensile stress state of the fabric sample, the original acoustic emission signal of the fabric sample is collected by an acoustic emission sensor array.

[0122] Perform time-frequency domain joint noise reduction on the original acoustic emission signal to obtain the noise-reduced acoustic emission signal of the fabric sample;

[0123] Event trigger detection is performed on the noise-reduced acoustic emission signal to obtain the event trigger time sequence of the fabric sample;

[0124] Based on the event triggering time series, independent acoustic emission event features are extracted from the denoised acoustic emission signal to obtain the acoustic emission event feature parameters of the denoised acoustic emission signal.

[0125] The acoustic emission event feature parameters are mapped to a preset typical damage mode feature library to obtain the microscopic damage information of the fabric sample.

[0126] The step of mapping the acoustic emission event feature parameters to a preset typical damage pattern feature library to obtain the microscopic damage information of the fabric sample includes:

[0127] Based on the acoustic emission event feature parameters, the feature library of typical damage modes is projected into a multi-dimensional feature space to obtain the feature projection vector of the fabric sample.

[0128] Nearest neighbor pattern search is performed on the feature projection vector to obtain the damage pattern category of the fabric sample;

[0129] The damage pattern categories are correlated and integrated in a spatiotemporal manner to obtain the damage event sequence of the fabric sample;

[0130] The severity of the damage event sequence is assessed to obtain the microscopic damage information of the fabric sample.

[0131] Based on the multi-mode tensile stress state of the fabric sample, the original acoustic emission signal of the fabric sample is collected by an acoustic emission sensor array. The operator evenly attaches each sensor in the acoustic emission sensor array to different areas of the fabric sample surface, ensuring that the sensor and the fabric sample are in close contact without gaps. During the process of the fabric sample being under multi-mode tensile stress, the signal acquisition function of the sensor array is activated, so that each sensor synchronously captures the acoustic emission signal generated inside the fabric due to tensile force, and continuously records the waveform and generation time of these signals. The signals collected by all sensors are integrated into a set containing the signals of each area, and this set is the original acoustic emission signal of the fabric sample.

[0132] The original acoustic emission signal is subjected to time-frequency domain joint noise reduction to obtain the noise-reduced acoustic emission signal of the fabric sample. The operator first performs time-domain processing on the original acoustic emission signal to identify and remove interference signals with extremely short duration and no significant amplitude change. Then, the time-domain processed signal is processed in the frequency domain to determine the inherent frequency range of the acoustic emission signal generated by the fabric stretching. Signal components outside this frequency range are filtered out. Subsequently, the signals after time-domain and frequency-domain processing are integrated to retain the effective signal part that conforms to the acoustic emission characteristics of the fabric, forming the noise-reduced acoustic emission signal of the fabric sample.

[0133] Event trigger detection is performed on the denoised acoustic emission signal to obtain the event trigger time sequence of the fabric sample. The operator sets an amplitude threshold for the acoustic emission signal, which is determined based on the background signal amplitude in the undamaged state of the fabric. The denoised acoustic emission signal is scanned one by one. When the signal amplitude exceeds the set threshold, the generation time of the signal is recorded. The times corresponding to all signals that exceed the threshold are arranged in chronological order, and the resulting ordered time set is the event trigger time sequence of the fabric sample.

[0134] Based on the event triggering time series, independent acoustic emission event features are extracted from the denoised acoustic emission signal to obtain the acoustic emission event feature parameters of the denoised acoustic emission signal. According to the time points in the event triggering time series, the operator divides the denoised acoustic emission signal into multiple independent signal segments. The signal segment corresponding to each time point is an independent acoustic emission event. For each independent acoustic emission event, the duration of its maximum amplitude and the rising slope of the waveform are extracted. These extracted information are associated with the corresponding independent acoustic emission event. The integration of this information from all independent acoustic emission events is the acoustic emission event feature parameter of the denoised acoustic emission signal.

[0135] Based on the acoustic emission event feature parameters, a multi-dimensional feature space projection is performed on the typical damage mode feature library to obtain the feature projection vector of the fabric sample. The operator first determines the feature dimensions included in the typical damage mode feature library, which are consistent with the type of acoustic emission event feature parameters. Each piece of information in the acoustic emission event feature parameters is mapped to a different dimension of the feature library. The expression scale of the parameters is adjusted according to the feature range of each dimension so that the parameters can adapt to the spatial structure of the feature library. The adjusted parameters are combined into a vector corresponding to the spatial position of the feature library. This vector is the feature projection vector of the fabric sample.

[0136] Nearest neighbor pattern search is performed on the feature projection vector to obtain the damage pattern category of the fabric sample. The operator searches for the preset damage pattern feature vector that is closest to the feature projection vector in the multidimensional feature space of the typical damage pattern feature library, determines the damage pattern corresponding to the preset feature vector, and determines the damage pattern as the damage pattern category of the fabric sample.

[0137] The damage pattern categories are spatiotemporally correlated and integrated to obtain the damage event sequence of the fabric sample. The operator associates the damage pattern categories with the time information in the event trigger time sequence to determine the occurrence time corresponding to each damage pattern. At the same time, combined with the attachment area information of the acoustic emission sensor array, the fabric area corresponding to each damage pattern is determined. The time areas and pattern types corresponding to the damage patterns are arranged in chronological order, and the resulting ordered set is the damage event sequence of the fabric sample.

[0138] The severity of the damage event sequence is assessed to obtain the microscopic damage information of the fabric sample. The operator determines the severity level of each damage pattern in the damage event sequence by comparing it with the severity standards corresponding to each damage pattern in the typical damage pattern feature library. At the same time, the operator combines the occurrence area and time of the damage pattern, integrates the information of damage pattern type, severity level, occurrence area and occurrence time, and forms a set containing microscopic damage details, which is the microscopic damage information of the fabric sample.

[0139] The beneficial effects are that the acoustic emission sensor array comprehensively collects the acoustic signals of the fabric, the time and frequency domain noise reduction ensures the effectiveness of the signal, the event time is located and the feature parameters are extracted, the damage pattern is matched with the typical damage library, the damage sequence is formed by associating spatiotemporal information, and the severity is assessed to obtain microscopic damage information, providing a precise basis for fabric durability assessment and quality improvement.

[0140] S5. Perform time-series correlation analysis on the stretching process dataset and the micro-damage information to construct a damage evolution map of the fabric sample;

[0141] In this embodiment of the invention, the step of performing a time-series correlation analysis between the stretching process dataset and the microscopic damage information to construct a damage evolution map of the fabric sample includes:

[0142] The mechanical state sequence in the stretching process dataset and the damage event sequence in the micro-damage information are fused with temporal information to obtain the fused temporal data stream of the fabric sample;

[0143] By performing association rule mining on the fused time-series data stream, the symbiotic relationship between specific mechanical state parameters and specific micro-damage types of the fabric sample under different stretching stages is analyzed.

[0144] Based on the symbiotic relationship, a damage dynamic correlation matrix for the fabric sample is constructed;

[0145] The damage dynamic correlation matrix is ​​visualized and topologically reconstructed to obtain the damage evolution map of the fabric sample.

[0146] The step of visualizing and topologically reconstructing the damage dynamic correlation matrix to obtain the damage evolution map of the fabric sample includes:

[0147] The nodes and associated edges in the damage dynamic correlation matrix are visualized and mapped to obtain the preliminary topological structure of the fabric sample.

[0148] Hierarchical clustering is performed on the preliminary topology, and edge weight optimization is performed on the clustered preliminary topology to obtain the optimized topology network of the fabric sample.

[0149] Key nodes are identified in the temporal paths of the optimized topology network to obtain the key evolution path of the fabric sample;

[0150] The key evolution path is overlaid with multidimensional information to obtain the damage evolution map of the fabric sample.

[0151] The mechanical state sequence in the stretching process dataset and the damage event sequence in the micro-damage information are fused in time series to obtain the fused time series data stream of the fabric sample. The operator retrieves the mechanical state sequence in the stretching process dataset, which contains the fabric mechanical parameters at different time points. At the same time, the operator retrieves the damage event sequence in the micro-damage information, which contains the fabric damage type and location information at different time points. Using time as a unified benchmark, the mechanical state parameters and damage event information corresponding to the same time point are bound together. All the bound information is arranged in chronological order to form an ordered data set containing the correspondence between mechanical states and damage events. This set is the fused time series data stream of the fabric sample.

[0152] Association rule mining is performed on the fused time-series data stream to analyze the symbiotic relationship between specific mechanical state parameters and specific micro-damage types of the fabric sample at different stretching stages. The operator divides the fused time-series data stream according to the elastic stage, plastic stage, and fracture stage of the stretching process. For all data in each stage, the frequency of occurrence of the corresponding micro-damage type when the specific mechanical state parameter appears is counted. Combinations of mechanical state parameters and micro-damage types with frequencies that meet the set standard are selected, and the correspondence between mechanical state parameters and micro-damage types in the combination is clarified. All correspondences that meet the standard are integrated to form the symbiotic relationship between specific mechanical state parameters and specific micro-damage types of the fabric sample at different stretching stages.

[0153] Based on the symbiotic relationship, a damage dynamic correlation matrix of the fabric sample is constructed. The operator uses specific mechanical state parameters in the symbiotic relationship as row identifiers of the matrix and specific micro-damage types as column identifiers of the matrix. At the intersection of the corresponding rows and columns of the matrix, the correlation strength between the mechanical state parameter and the micro-damage type is marked. The correlation strength is determined based on the corresponding frequency of the two in the fused time-series data stream. The correlation strengths corresponding to all symbiotic relationships are filled into the matrix, and the complete matrix formed is the damage dynamic correlation matrix of the fabric sample.

[0154] The nodes and associated edges in the damage dynamic correlation matrix are visualized and mapped to obtain the preliminary topology of the fabric sample. The operator sets the mechanical state parameters and micro-damage types in the damage dynamic correlation matrix as nodes of the topology, and sets the associated edges between nodes according to the correlation strength at the intersection positions in the matrix. The higher the correlation strength, the more prominent the display of the associated edge. The mechanical state parameter nodes and micro-damage type nodes are distributed on both sides of the topology according to the node type, and the associated edges are connected to the nodes on both sides. The resulting visualization graphic containing nodes and associated edges is the preliminary topology of the fabric sample.

[0155] The preliminary topology is hierarchically clustered, and the edge weights of the clustered preliminary topology are optimized to obtain the optimized topology network of the fabric sample. The operator performs hierarchical clustering on the nodes in the preliminary topology according to the stretching stage corresponding to the node. The mechanical state parameter nodes and the corresponding micro-damage type nodes in the same stretching stage are divided into the same clustering level. After the clustering is completed, the weights of each associated edge are re-evaluated. The weight evaluation is based on the duration of the corresponding mechanical state parameter and micro-damage type in the fused time-series data stream. The longer the duration, the higher the weight value. The display labels of the associated edges are adjusted according to the new weight values. The adjusted topology graph containing multi-level clustered nodes and optimized weighted associated edges is the optimized topology network of the fabric sample.

[0156] Key nodes are identified in the temporal paths of the optimized topology network to obtain the key evolution path of the fabric sample. The operator sorts out the node connection paths in the optimized topology network in chronological order and selects the mechanical state parameter nodes that play a decisive role in the occurrence of subsequent damage types. These nodes are the key nodes. The key nodes are specially identified in the optimized topology network, and the specially identified key nodes are connected in chronological order. The temporal path containing the key nodes is the key evolution path of the fabric sample.

[0157] The key evolution path is rendered by multi-dimensional information overlay to obtain the damage evolution map of the fabric sample. The operator overlays the tensile stage information, damage severity information, and mechanical state parameter range information corresponding to each node in the key evolution path. Different rendering colors are used for nodes with different tensile stages, and different rendering brightness is used for nodes with different damage severity. The key evolution path with overlaid multi-dimensional information and completed rendering is visualized, and the resulting visualized graphic is the damage evolution map of the fabric sample.

[0158] The beneficial effects include integrating mechanical and damage time-series data, establishing the linkage between the two, analyzing the symbiotic relationship between mechanical state and micro-damage at different stretching stages, constructing a correlation matrix and transforming it into a topological structure, clarifying the core correlation through cluster optimization, identifying key evolution nodes, and superimposing multi-dimensional information to form a damage evolution map, providing an intuitive and comprehensive reference for optimizing the damage resistance performance of fabrics.

[0159] S6. The tensile performance index and the damage evolution map are structurally integrated to obtain the tensile test report of the fabric sample.

[0160] In this embodiment of the invention, the step of structurally integrating the tensile performance index with the damage evolution map to obtain the tensile test report of the fabric sample includes:

[0161] Based on a preset report template framework, an information association index is established between the tensile performance index and the damage evolution map;

[0162] Based on the information association index, key damage evolution stages and corresponding mechanical states are extracted from the damage evolution map;

[0163] The key damage evolution stages and corresponding mechanical states are associated with the tensile performance indicators to obtain the damage association labeling information of the fabric sample.

[0164] According to the damage development sequence and performance degradation logic of the fabric sample, the damage association annotation information is filled into the report template frame to obtain the initial structured report of the fabric sample.

[0165] A key conclusion summary is generated from the initial structured report to obtain the tensile test report of the fabric sample.

[0166] Based on a preset report template framework, an information association index is established between the tensile performance index and the damage evolution map. The operator retrieves the preset report template framework, identifies the information modules in the framework used to carry the tensile performance index and the damage evolution map, and binds the performance level information in the tensile performance index to the key damage stage information in the damage evolution map. A unique association identifier is assigned to each set of corresponding information, and this association identifier is embedded in the data field of the tensile performance index and the attribute field of the damage evolution map, respectively. Through this association identifier, rapid information retrieval between the tensile performance index and the damage evolution map is realized. The resulting index system containing the association identifier and corresponding information is the information association index between the tensile performance index and the damage evolution map.

[0167] Based on the information association index, key damage evolution stages and corresponding mechanical states are extracted from the damage evolution map. The operator locates the damage evolution map content associated with tensile performance indicators according to the association identifier in the information association index. Damage stages that directly affect the attenuation of tensile performance are screened in the damage evolution map. These stages are the key damage evolution stages. At the same time, the mechanical state information corresponding to each key damage evolution stage is retrieved. This information comes from the mechanical parameter range marked by the nodes in the damage evolution map. The extracted key damage evolution stages and corresponding mechanical states are integrated one by one to form a complete set of associated information.

[0168] The key damage evolution stages and their corresponding mechanical states are associated with the tensile performance indicators to obtain the damage association labeling information of the fabric sample. The operator arranges the extracted key damage evolution stages and their corresponding mechanical states alongside the tensile performance indicators, and adds association labeling symbols next to each set of corresponding information to clearly indicate the specific impact of the key damage evolution stage on the tensile performance indicators. For example, a certain key damage evolution stage corresponds to a decrease in elasticity in the tensile performance indicators. The association information of the mechanical states and tensile performance indicators of all the marked key damage evolution stages is summarized, and the resulting set of labeling information is the damage association labeling information of the fabric sample.

[0169] According to the damage development sequence and performance degradation logic of the fabric sample, the damage association annotation information is filled into the report template framework to obtain the initial structured report of the fabric sample. The operator sorts the damage association annotation information according to the time sequence of fabric damage from generation to development to aggravation, and the logical sequence of performance from stabilization to gradual degradation. According to the information layout requirements of the preset report template framework, the sorted damage association annotation information is filled into the corresponding content modules. At the same time, the judgment criteria of tensile performance index and the generation instructions of damage evolution map are added to ensure that the report content is complete and logically coherent. The report text formed after the information is filled in is the initial structured report of the fabric sample.

[0170] A key conclusion summary is generated from the initial structured report to obtain the tensile test report for the fabric sample. The operator reads through the initial structured report, extracts the core content, including the final tensile performance index level of the fabric sample, the specific characteristics of the mechanical state and the correlation between the key damage evolution stages and the damage development, as well as the main reasons for the decline in the tensile performance of the fabric. These core contents are then streamlined and integrated in a logical order to form a concise and clear key conclusion summary. This summary is added to the beginning of the initial structured report. At the same time, redundant statements in the report are deleted and optimized to ensure that the report content is concise and highlights the key points. The optimized report is the tensile test report for the fabric sample.

[0171] The beneficial effects include establishing an index linking performance indicators and damage maps, accurately extracting core damage stages and corresponding mechanical states, linking and annotating the relationship between damage and performance, generating structured reports logically and extracting summaries, forming a test report that highlights key points, and providing intuitive evidence for fabric performance evaluation.

[0172] like Figure 2 The diagram shown is a functional block diagram of a garment fabric stretch testing system provided in an embodiment of the present invention.

[0173] The garment fabric tensile testing system 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the garment fabric tensile testing system 100 may include a detection sequence setting module 101, a stress detection module 102, a performance index evaluation module 103, a microscopic damage identification module 104, a damage map construction module 105, and a test report generation module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0174] In this embodiment, the functions of each module / unit are as follows:

[0175] The detection sequence setting module 101 is used to set a multi-mode stretch detection sequence for the fabric sample according to the properties of the clothing fabric under dynamic stress conditions during the simulation of actual wearing process.

[0176] The stress detection module 102 is used to perform stress detection on the fabric sample based on the multi-mode tensile detection sequence to obtain a data set of the tensile process of the fabric sample.

[0177] The performance index evaluation module 103 is used to evaluate the tensile characteristics of the fabric sample based on the tensile process dataset to obtain the tensile performance index of the fabric sample.

[0178] The micro-damage identification module 104 is used to respond to acoustic emission events of the fabric sample and identify the micro-damage information of the fabric sample based on the acoustic emission event response results.

[0179] The damage map construction module 105 is used to perform time-series correlation analysis between the stretching process dataset and the micro-damage information to construct a damage evolution map of the fabric sample.

[0180] The test report generation module 106 is used to structurally integrate the tensile performance index and the damage evolution map to obtain a tensile test report for the fabric sample.

[0181] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0182] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0184] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0185] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for testing the tensile strength of clothing fabrics, characterized in that, The method includes: S1. Under the dynamic stress state of simulating actual wearing process, set the multi-mode stretching detection sequence of the fabric sample according to the properties of the clothing fabric. S2. Based on the multi-mode stretching detection sequence, stress detection is performed on the fabric sample to obtain the stretching process dataset of the fabric sample. S3. Based on the stretching process dataset, evaluate the stretching characteristics of the fabric sample to obtain the stretching performance index of the fabric sample. S4. Perform acoustic emission event response on the fabric sample, and identify the microscopic damage information of the fabric sample based on the acoustic emission event response results. S5. Perform time-series correlation analysis on the stretching process dataset and the micro-damage information to construct a damage evolution map of the fabric sample; S6. The tensile performance index and the damage evolution map are structurally integrated to obtain the tensile test report of the fabric sample.

2. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The process of simulating the dynamic stress state during actual wear, based on the fabric properties, involves setting a multi-mode stretching detection sequence for the fabric sample, including: Based on the fabric properties of the fabric sample, the initial set of mechanical parameters of the fabric sample is extracted. Under the dynamic stress state during the simulation of actual wearing process, the initial set of mechanical parameters is subjected to stress mode identification to obtain the typical stress mode of the fabric sample. Based on the typical stress mode, the initial set of mechanical parameters is optimized through multi-dimensional coupling iterative optimization to obtain the primary detection sequence of the fabric sample; The primary detection sequence is embedded in a buffer detection stage to obtain the transition detection sequence of the fabric sample; The transition detection sequence is subjected to adaptive loading rate modulation to obtain the multi-mode stretch detection sequence of the fabric sample.

3. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The process of stress detection on the fabric sample based on the multi-mode tensile detection sequence to obtain a tensile process dataset of the fabric sample includes: Based on the multi-mode tensile testing sequence, the fabric sample is subjected to multiaxial tensile load to obtain the real-time stress response signal of the fabric sample. The real-time stress response signal is acquired synchronously through multiple channels to obtain a set of synchronous stress signals for the fabric sample. Baseline correction is performed on the synchronous stress signal set to obtain the clean stress signal sequence of the fabric sample; The time-domain feature analysis of the clean stress signal sequence is performed to obtain the stretching process dataset of the fabric sample.

4. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The process of evaluating the tensile characteristics of the fabric sample based on the tensile process dataset to obtain the tensile performance index of the fabric sample includes: The stress-strain relationship curves in the tensile process dataset are analyzed for characteristic inflection points to obtain the elastic response parameters, plastic initiation parameters, and fracture limit parameters of the fabric sample. The elastic response parameter, the plastic initiation parameter, and the fracture limit parameter are normalized to obtain the normalized feature vector set of the fabric sample. Based on the normalized feature vector set, the tensile performance index of the fabric sample is calculated, wherein the formula for calculating the tensile performance index is as follows: ； In the formula, This indicates the tensile property index. This indicates the contribution weight of the elasticity stage of the fabric sample. This represents the elastic modulus in the normalized eigenvector set. This represents the reference elastic modulus of the fabric sample. This indicates the contribution weight of the yield stage of the fabric sample. This represents the yield stress in the normalized eigenvector set. This represents the reference yield stress of the fabric sample. This indicates the contribution weight of the fracture stage of the fabric sample. This represents the elongation at break in the normalized feature vector set. This represents the baseline elongation at break of the fabric sample. The tensile performance index is mapped and matched with a preset performance level boundary to obtain the tensile performance index of the fabric sample.

5. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The step of performing acoustic emission event response on the fabric sample and identifying the microscopic damage information of the fabric sample based on the acoustic emission event response results includes: Based on the multi-mode tensile stress state of the fabric sample, the original acoustic emission signal of the fabric sample is collected by an acoustic emission sensor array. Perform time-frequency domain joint noise reduction on the original acoustic emission signal to obtain the noise-reduced acoustic emission signal of the fabric sample; Event trigger detection is performed on the noise-reduced acoustic emission signal to obtain the event trigger time sequence of the fabric sample; Based on the event triggering time series, independent acoustic emission event features are extracted from the denoised acoustic emission signal to obtain the acoustic emission event feature parameters of the denoised acoustic emission signal. The acoustic emission event feature parameters are mapped to a preset typical damage mode feature library to obtain the microscopic damage information of the fabric sample.

6. The method for testing the tensile strength of clothing fabric as described in claim 5, characterized in that, The step of mapping the acoustic emission event feature parameters to a preset typical damage pattern feature library to obtain the microscopic damage information of the fabric sample includes: Based on the acoustic emission event feature parameters, the feature library of typical damage modes is projected into a multi-dimensional feature space to obtain the feature projection vector of the fabric sample. Nearest neighbor pattern search is performed on the feature projection vector to obtain the damage pattern category of the fabric sample; The damage pattern categories are correlated and integrated in a spatiotemporal manner to obtain the damage event sequence of the fabric sample; The severity of the damage event sequence is assessed to obtain the microscopic damage information of the fabric sample.

7. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The step of performing a time-series correlation analysis between the stretching process dataset and the microscopic damage information to construct a damage evolution map of the fabric sample includes: The mechanical state sequence in the stretching process dataset and the damage event sequence in the micro-damage information are fused with temporal information to obtain the fused temporal data stream of the fabric sample; By performing association rule mining on the fused time-series data stream, the symbiotic relationship between specific mechanical state parameters and specific micro-damage types of the fabric sample under different stretching stages is analyzed. Based on the symbiotic relationship, a damage dynamic correlation matrix for the fabric sample is constructed; The damage dynamic correlation matrix is ​​visualized and topologically reconstructed to obtain the damage evolution map of the fabric sample.

8. The method for testing the tensile strength of clothing fabric as described in claim 7, characterized in that, The step of visualizing and topologically reconstructing the damage dynamic correlation matrix to obtain the damage evolution map of the fabric sample includes: The nodes and associated edges in the damage dynamic correlation matrix are visualized and mapped to obtain the preliminary topological structure of the fabric sample. Hierarchical clustering is performed on the preliminary topology, and edge weight optimization is performed on the clustered preliminary topology to obtain the optimized topology network of the fabric sample. Key nodes are identified in the temporal paths of the optimized topology network to obtain the key evolution path of the fabric sample; The key evolution path is overlaid with multidimensional information to obtain the damage evolution map of the fabric sample.

9. The method for testing the tensile strength of clothing fabrics as described in claim 1, characterized in that, The structured integration of the tensile performance indicators and the damage evolution map to obtain the tensile test report of the fabric sample includes: Based on a preset report template framework, an information association index is established between the tensile performance index and the damage evolution map; Based on the information association index, key damage evolution stages and corresponding mechanical states are extracted from the damage evolution map; The key damage evolution stages and corresponding mechanical states are associated with the tensile performance indicators to obtain the damage association labeling information of the fabric sample. According to the damage development sequence and performance degradation logic of the fabric sample, the damage association annotation information is filled into the report template frame to obtain the initial structured report of the fabric sample. A key conclusion summary is generated from the initial structured report to obtain the tensile test report of the fabric sample.

10. A garment fabric tensile testing system, characterized in that, The system for implementing the method for testing the tensile strength of clothing fabrics according to claims 1-9 includes: The detection sequence setting module is used to set a multi-mode stretch detection sequence for fabric samples based on the properties of the clothing fabric under dynamic stress conditions during the simulation of actual wearing process. The stress detection module is used to perform stress detection on the fabric sample based on the multi-mode tensile detection sequence to obtain a dataset of the tensile process of the fabric sample. The performance index evaluation module is used to evaluate the tensile characteristics of the fabric sample based on the tensile process dataset to obtain the tensile performance index of the fabric sample. The micro-damage identification module is used to perform acoustic emission event response on the fabric sample and identify the micro-damage information of the fabric sample based on the acoustic emission event response results. The damage map construction module is used to perform time-series correlation analysis between the stretching process dataset and the micro-damage information to construct a damage evolution map of the fabric sample. The test report generation module is used to structurally integrate the tensile performance indicators and the damage evolution map to obtain a tensile test report for the fabric sample.

Images