Automatic identification system for fabric weave structure

Abstract

The invention relates to the technical field of artificial intelligence and computer vision crossing, and discloses a fabric weave structure automatic identification system, which comprises a data acquisition module, a production monitoring module, a production data analysis module, an evaluation module, an adjustment module, an execution module, a feedback module and an upgrading module, precise integration of raw material data and historical process data is realized by establishing a data acquisition module, multi-dimensional data acquisition is realized by a production monitoring module, quantitative calculation of key parameters is realized by a production data analysis module, multi-dimensional performance evaluation is realized by an evaluation module, targeted process optimization is realized by an adjustment module, and real-time parameter adjustment is realized by an execution module. The feedback module realizes closed-loop data circulation, and the upgrading module realizes continuous evolution of the system, so that the system has full-process intelligent management and control capability, the limitation of traditional two-dimensional analysis is effectively broken through, and high precision, high adaptability and high dynamic response of fabric weave structure identification are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence and computer vision, in particular to a fabric structure automatic identification system. BACKGROUND

[0002] The current mainstream fabric structure automatic identification system mainly relies on two-dimensional projection images for analysis. This method has some limitations. Due to the lack of three-dimensional structure analysis capability, the system cannot accurately capture key three-dimensional information such as the thickness of the fabric and the interlayer interweaving relationship, resulting in a high error of up to 30% in the estimation of the actual gram weight of double-layer plush cloth based on single-layer vision. In addition, the microscopic undulations caused by the warp tension in the real weaving process (with a wave amplitude of 0.5mm) are not taken into account, and the existing algorithm can only be approximated in the plane, which seriously restricts its application accuracy in the field of precision simulation. The dynamic adaptability of the system is also weak: on the one hand, the preset parameters are difficult to cope with process changes caused by fluctuations in raw material batches (such as different fiber lengths of the same cotton due to differences in origin, which in turn affect the shrinkage rate), experimental data show that for every 1 unit deviation of the raw material's micronaire value from the standard value, the recognition error rate increases by 7%; on the other hand, when faced with new blended materials (such as graphene modified fibers), the model update cycle is as long as several months, and the response speed lags far behind the change rhythm of market demand. These technical bottlenecks show that the traditional analysis framework based on two-dimensional images has been unable to meet the needs of high-precision, multi-scene fabric structure identification, and it is urgent to introduce innovative methods such as three-dimensional reconstruction, dynamic modeling and adaptive learning to break through the existing limitations. SUMMARY

[0003] (I) Technical problems solved

[0004] In view of the deficiencies of the prior art, the present application provides a fabric structure automatic identification system, which has the advantages of multi-dimensional structure perception, dynamic process adaptation and intelligent self-evolution, and solves the core problems of traditional two-dimensional image analysis that cannot capture three-dimensional features, fixed thresholds that cannot cope with fluctuations in raw materials, and slow response to new materials.

[0005] (II) Technical solutions

[0006] To achieve the above purpose, the present application provides the following technical solutions: a fabric structure automatic identification system, characterized in that it comprises a data acquisition module, a production monitoring module, a production data analysis module, an evaluation module, an adjustment module, an execution module, a feedback module and an upgrade module;

[0007] The data acquisition module detects key indicators for each batch of raw materials and obtains historical process data corresponding to different varieties of raw materials;

[0008] The production monitoring module captures three-dimensional data and two-dimensional image data of the fabric by installing online monitoring devices at different positions;

[0009] The production data analysis module outputs weft and warp density compensation values based on the monitoring and collection data , three-dimensional structure characteristic parameters , abnormal deviation degree , and cumulative error ;

[0010] The evaluation module evaluates the calculation results of the production data analysis module, online monitoring data, and preset evaluation criteria;

[0011] The adjustment module constructs a process adjustment experience atlas based on the evaluation results of the evaluation module and historical deviation correction records, and generates adjustment schemes for raw material selection, process parameter setting, and production process according to the atlas;

[0012] The execution module receives real-time adjustments of loom parameters, drying temperature, cloth winding tension, and other process parameters of the production line from the adjustment module;

[0013] The feedback module generates feedback information after analyzing the execution result data;

[0014] The upgrade module upgrades and optimizes the algorithm model, database, and hardware devices of the system according to the long-term feedback data provided by the feedback module.

[0015] Preferably, the data collection module includes a raw material index detection unit, a historical data retrieval unit, and a database construction unit.

[0016] Preferably, the raw material index detection unit detects the micronaire value, short fiber rate, fiber length, fiber fineness, impurity content, and moisture regain index of each batch of raw material through a cotton quality detector, a fiber length detector, a fiber fineness detector, and other detection devices; the historical data retrieval unit obtains historical process data of corresponding varieties of raw materials through an online variety raw material table, a process parameter table, and a production result table; and the database construction unit integrates variety raw material data and historical process data to establish a variety raw material material property database.

[0017] Preferably, the production monitoring module installs laser scanning sensors and high-resolution industrial cameras at the entrance of the loom, the exit of the loom, the exit of the drying machine, and the cloth winding machine of the production line, captures three-dimensional data of the fabric through the laser scanning sensors, monitors two-dimensional image data of the fabric through the high-resolution industrial cameras, automatically samples and detects the first and last sections of each roll of cloth through automatic sampling equipment, and finally constructs three-dimensional models of the fabric semi-finished product and finished product sampling samples using three-dimensional modeling software.

[0018] Preferably, the production data analysis module includes a latitude and longitude density compensation calculation unit, a three-dimensional structural parameter analysis unit, an anomaly deviation assessment unit, and a cumulative error calculation unit, and calculates the latitude and longitude density compensation value sequentially based on online monitoring data, raw material data, and historical data. 3D structural feature parameters Abnormal deviation With cumulative error .

[0019] Preferably, the latitude and longitude density compensation calculation unit calculates the latitude and longitude density compensation value through the mapping relationship between historical process data and current raw material characteristics. The calculation formula is as follows:

[0020] ;

[0021] In the formula, Indicates the latitude and longitude density compensation value. This indicates the measured micronaire value of the current batch of raw materials. This represents the baseline value for the standard Micron value. This represents the standard deviation of Macron values ​​in the historical database. This represents the measured average fiber length. This indicates the target fiber length setting. This indicates the permissible range of fiber length variation. This represents the workshop relative humidity correction factor. This indicates the weighting factor for the impact of Macron value deviation on latitude and longitude density. This indicates the weighting factor for the impact of fiber length differences on warp and weft density. This represents the weighting factor for the influence of relative humidity in the workshop on latitude and longitude density.

[0022] Preferably, the three-dimensional structural parameter analysis unit calculates the volumetric characteristics of the fabric based on laser-scanned three-dimensional point cloud data. The calculation formula is as follows:

[0023] ;

[0024] In the formula, Indicates the volumetric characteristics of the fabric. , These represent the first three-dimensional point cloud data. The X and Y coordinates of each point , These represent the first three-dimensional point cloud data. +1 point's X and Y coordinates, Indicates the first The fabric thickness value corresponding to each point.

[0025] Preferably, the abnormal deviation degree evaluation unit calculates the abnormal deviation degree according to the first and last section sampling self-checking data of each roll of cloth and the standard process parameter value , and the calculation formula is as follows:

[0026] ;

[0027] In the formula, represents the abnormal deviation degree, represents the process parameter value in the sampling self-checking data, represents the total number of process parameters participating in the calculation, represents the standard value of each process parameter, represents the weight of each process parameter, represents the mean value of the total standard process parameters.

[0028] Preferably, the cumulative error accounting unit calculates the cumulative error by continuously monitoring the data , and when the set threshold is exceeded, a global recalibration program is started, and the calculation formula is as follows:

[0029] ;

[0030] In the formula, represents the cumulative error, represents the error value of the th monitoring, represents the time interval between the th monitoring and the previous monitoring, and ∑ represents the summation operation.

[0031] Preferably, the evaluation module performs warp and weft density recognition accuracy evaluation according to the warp and weft density compensation value , online monitoring data, and preset evaluation standards, and judges whether the compensated warp and weft density is within the qualified range, and the specific steps are as follows:

[0032] S1.1, when the warp and weft density compensation value ∈[-0.5,0.5], only the software algorithm fine-tunes the recognition parameters, without changing the hardware settings;

[0033] S1.2, when the warp and weft density compensation value ∈(0.5,2]∪[-2,-0.5), adjust the warp let-off amount parameter of the loom and update the compensation formula weight factor synchronously;

[0034] S1.3, when the warp and weft density compensation value exceeds the interval (−∞,-2)∪(2,+∞), start the raw material re-inspection program → recalibrate the detection equipment → correct the raw material index detection value and then calculate the compensation value again;

[0035] According to the three-dimensional structure characteristic parameters , online monitoring data and preset evaluation criteria, the integrity and consistency of the fabric three-dimensional structure are evaluated, and whether the three-dimensional structure parameters meet the design requirements is analyzed. The specific steps are as follows:

[0036] S2.1, when the three-dimensional structure characteristic parameters are within the design value ±3σ interval, it is determined that the structure uniformity is excellent, and when it exceeds the range, the potential wrinkle risk area is marked and the heat setting temperature adjustment scheme is associated;

[0037] S2.2, when the volume mutation rate is greater than 15%, the system automatically triggers a weft density abnormality alarm;

[0038] According to the abnormal deviation degree , online monitoring data and preset evaluation criteria, process stability evaluation is carried out to determine whether the abnormal deviation is within the acceptable threshold, and the judgment process is as follows:

[0039] S3.1, when the abnormal deviation degree ∈[0,0.1], it is determined to be normal fluctuation;

[0040] S3.2, when the abnormal deviation degree ∈(0.1,0.3], the online re-inspection program is started and the sampling quantity is increased to confirm the sporadic factors;

[0041] S3.3, when the abnormal deviation degree >0.3, the process parameter traceability is triggered, the production of this batch is suspended, the influencing factors of raw materials / equipment / environment are traced back, and the process parameters are adjusted;

[0042] According to the cumulative error , online monitoring data and preset evaluation criteria, long-term running accuracy evaluation of the system is carried out to determine whether global recalibration needs to be started, and the specific steps are as follows:

[0043] S4.1, when the cumulative error is less than 0.5%, the present situation is observed;

[0044] S4.2, when the cumulative error reaches 0.8%, the sampling frequency is doubled;

[0045] S4.3, when the cumulative error is greater than or equal to 1% threshold, the system forcibly triggers the whole production line reference calibration process and updates the standard reference sample library;

[0046] The adjustment module constructs a process adjustment experience map according to the above evaluation results and historical correction records to adjust the scheme.

[0047] Compared with the prior art, the present invention provides an automatic identification system for fabric structure, which has the following advantages:

[0048] 1. This invention overcomes the limitations of two-dimensional analysis by capturing three-dimensional data with a laser scanning sensor, supplements planar detail information with a high-resolution industrial camera, and realizes full-process data visualization through automated sampling and three-dimensional modeling. This system solves the problems of traditional methods being unable to capture three-dimensional structural features, having a single data dimension, and insufficient sample representativeness.

[0049] 2. This invention calculates latitude and longitude density compensation values. This is used to quantify the impact of raw material fluctuations and environmental factors on latitude and longitude density, and to perform real-time dynamic corrections. The calculated latitude and longitude density compensation value... Within the range of [-0.5, 0.5], only the identification parameters are fine-tuned through software algorithms, without changing the hardware settings; when the latitude and longitude density compensation value... When the distance is in the range (0.5,2]⋃[-2,-0.5), adjust the warp feed parameters of the loom and update the weighting factor of the compensation formula simultaneously; when the warp and weft density compensation value... When the value exceeds the range of (−∞,-2)⋃(2,+∞), the raw material re-inspection procedure is initiated, the testing equipment is recalibrated, the raw material index test value is corrected, and the compensation value is recalculated. Finally, the system solves the problem that the fixed threshold cannot cope with the fluctuation of raw material batches.

[0050] 3. This invention uses laser-scanned three-dimensional point cloud data to analyze three-dimensional structural parameters and calculate the volumetric characteristics of the fabric. To accurately reconstruct the spatial topological relationship of the yarn, and to predict the deformation behavior under different tensions, the volume characteristics of the fabric are considered. When the design value is within ±3σ, the structure is judged to have excellent uniformity; if it exceeds this range, potential wrinkle risk areas are marked and associated with heat setting temperature adjustment schemes; when the volume change rate is >15%, the system automatically triggers a weft density abnormality alarm, which finally solves the problem of high error rate in double-layer structure identification and enables reliable identification of complex jacquard fabrics.

[0051] 4. This invention utilizes abnormal deviation. The calculation is used to assess the degree of deviation of a single roll of fabric from the standard process, making process abnormalities quantifiable, traceable, and graded for handling. When the degree of deviation is... When the deviation is within the range of [0, 0.1], it is considered a normal fluctuation; only data is recorded without interfering with production. When the deviation is abnormal... When the value is in the range (0.1, 0.3), initiate the online re-inspection procedure, increase the sampling size, and confirm whether the anomaly is due to an isolated incident; when the anomaly deviation is... When the interval exceeds (0.3, +∞), the process parameter traceability is triggered, the production of the batch is suspended, the influencing factors of raw materials, equipment and environment are traced back, and the process parameters are adjusted, finally the system solves the problem of late discovery of production process abnormalities, and realizes early discovery and early treatment of quality defects of the production line. BRIEF DESCRIPTION OF DRAWINGS

[0052] Fig. 1 The system flowchart of the present application is shown in the figure.

[0053] Fig. 2 The system implementation step diagram of the first embodiment of the present application is shown in the figure.

[0054] Fig. 3 The system implementation step diagram of the second embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0056] Please refer to Figs. 1-3 , an automatic fabric structure identification system, comprising a data acquisition module, a production monitoring module, a production data analysis module, an evaluation module, an adjustment module, an execution module, a feedback module and an upgrade module;

[0057] The data acquisition module detects the key indicators of each batch of raw materials, and obtains the historical process data corresponding to different varieties of raw materials. Finally, the variety of raw material data and historical process data are integrated to establish a variety of raw material material property database.

[0058] The production monitoring module captures three-dimensional data and two-dimensional image data of the fabric by installing online monitoring equipment at different positions, and uses automatic sampling equipment to sample and self-check the head and tail sections of each roll of fabric. Finally, three-dimensional modeling software is used to construct a three-dimensional model of the fabric sampling sample.

[0059] The production data analysis module outputs the weft and warp density compensation value , three-dimensional structure characteristic parameters , abnormal deviation and cumulative error based on the monitoring and acquisition data.

[0060] The evaluation module evaluates the accuracy, consistency and stability of the fabric weave structure recognition in multiple dimensions according to the calculation results of the production data analysis module, online monitoring data and preset evaluation criteria, and judges whether the current recognition result meets the production requirements and quality standards.

[0061] The adjustment module constructs a process adjustment experience atlas according to the evaluation results of the evaluation module and in combination with historical correction records, generates adjustment schemes for raw material selection, process parameter setting and production flow according to the atlas, and guides subsequent production scheduling and process optimization.

[0062] The execution module receives the adjustment schemes generated by the adjustment module and the execution instructions for abnormal processing and recalibration issued by the production data analysis module, adjusts the loom parameters, drying temperature, cloth tension and other process parameters of the production line in real time, and simultaneously performs sampling reinspection and equipment calibration operations.

[0063] The feedback module collects the execution result data of the execution module, including the adjusted process parameters, fabric weave structure recognition results and production quality data, generates feedback information after analyzing the execution result data, and feeds back to the production data analysis module, the evaluation module and the adjustment module, providing a basis for subsequent calculation, evaluation and adjustment.

[0064] The upgrade module analyzes the performance of the system under different raw materials, processes and production environments according to the long-term feedback data provided by the feedback module, identifies the performance short board and potential improvement points of the system, and optimizes the algorithm model, database and hardware equipment of the system according to the development trend of new technologies and new materials in the industry, to improve the adaptability and recognition accuracy of the system.

[0065] The advantages are: through the establishment of the data acquisition module to realize the accurate integration of raw material data and historical process data, the production monitoring module to realize multi-dimensional data acquisition, the production data analysis module to realize key parameter quantitative calculation, the evaluation module to realize multi-dimensional performance evaluation, the adjustment module to realize targeted process optimization, the execution module to realize real-time parameter adjustment, the feedback module to realize closed-loop data flow, and the upgrade module to realize system continuous evolution, the system has full-process intelligent control capability, effectively breaks through the traditional two-dimensional analysis limitation, realizes high-precision, high adaptability and high dynamic response of fabric weave structure recognition.

[0066] The data acquisition module includes a raw material index detection unit, a historical data retrieval unit and a database construction unit.

[0067] The raw material index detection unit detects the index of each batch of raw material, such as micronaire, short fiber rate, fiber length, fiber fineness, impurity content and moisture regain, through a cotton quality detector, a fiber length detector, a fiber fineness detector and other detection equipment; the historical data retrieval unit obtains the historical process data of the corresponding variety of raw material through an online variety of raw material table, a process parameter table and a production result table; and the database construction unit integrates the variety of raw material data and the historical process data to establish a variety of raw material material property database.

[0068] The advantages are that the raw material key index is comprehensively quantified by the raw material index detection unit, the process data is accurately traced by the historical data retrieval unit, and the data is systematically integrated by the database construction unit, so that the system has the basis for correlation analysis of raw material-process-result, and provides data support for dynamic process adaptation.

[0069] The production monitoring module installs laser scanning sensors and high-resolution industrial cameras at the entrance of the loom on the production line, the exit of the loom, the exit of the drying machine and the cloth rolling machine. The three-dimensional data of the fabric is captured by the laser scanning sensor, including thickness, interlaminar interweaving relationship, microscopic undulation caused by warp tension, fiber arrangement direction and yarn twist distribution. The two-dimensional image data of the fabric is monitored by the high-resolution industrial camera as a supplement to the three-dimensional data in terms of planar texture details, color distribution and local defect identification. The first and last sections of each roll of fabric are sampled and self-checked by automatic sampling equipment. Finally, three-dimensional modeling software is used to construct three-dimensional models of the fabric semi-finished product and finished product sampling samples, realizing multi-dimensional data acquisition and modeling of fabric structure from macro to micro.

[0070] The advantages are that the three-dimensional data captured by the laser scanning sensor breaks through the limitations of two-dimensional analysis, the high-resolution industrial camera supplements the planar detail information, and the automation sampling and three-dimensional modeling realize the visualization of the whole process data, so that the system solves the problems of traditional methods that cannot capture three-dimensional structure characteristics, single data dimension and insufficient sample representativeness.

[0071] The production data analysis module includes warp and weft density compensation calculation unit, three-dimensional structure parameter analysis unit, abnormal deviation degree evaluation unit and cumulative error calculation unit, and according to the online monitoring data, raw material data and historical record data, the warp and weft density compensation value , three-dimensional structure characteristic parameters , abnormal deviation degree and cumulative error are calculated in turn.

[0072] The warp and weft density compensation calculation unit calculates the warp and weft density compensation value by the mapping relationship between the historical process data and the current raw material characteristics, which is used to correct the warp and weft density in real time, and the calculation formula is:

[0073] ;

[0074] In the formula, represents the warp and weft density compensation value, represents the measured value of the current batch of raw materials, represents the standard micronaire value reference value, represents the standard deviation of the micronaire value in the historical database, represents the measured average fiber length (mm), represents the target fiber length set value, represents the allowable fiber length fluctuation range, represents the workshop relative humidity correction coefficient (%), represents the influence weight factor of micronaire value deviation on warp and weft density, represents the influence weight factor of fiber length difference on warp and weft density, represents the influence weight factor of workshop relative humidity on warp and weft density, and the above three weight factors are obtained by least squares fitting of historical process optimization records.

[0075] The advantage is that the influence of raw material fluctuation and environmental factors on warp and weft density is quantified by calculating the warp and weft density compensation value , and real-time dynamic correction is performed; when the calculated warp and weft density compensation value is in the interval [-0.5, 0.5], only the software algorithm fine-tuning identification parameter is adjusted, without changing the hardware setting; when the warp and weft density compensation value is in the interval (0.5, 2]⋃[-2,-0.5), the warp and weft density compensation value is adjusted, and the weight factor of the compensation formula is updated synchronously; when the warp and weft density compensation value exceeds the interval (−∞,-2)⋃(2,+∞), the raw material re-inspection program is started, the detection equipment is recalibrated, and the compensation value is calculated again after correcting the raw material index detection value, finally the system solves the problem that the fixed threshold cannot cope with the batch fluctuation of raw materials.

[0076] The three-dimensional structure parameter analysis unit analyzes the three-dimensional structure parameters based on the three-dimensional point cloud data of laser scanning, and calculates the volume characteristics of the fabric, including the volume characteristics, interlayer interweaving parameters and thickness value, and the calculation formula is:

[0077] ;

[0078] In the formula, represents the volume characteristics of the fabric, , represents the X and Y coordinates of the i-th point in the three-dimensional point cloud data, , , respectively represent the X, Y coordinates of the i-th point in the three-dimensional point cloud data +1 respectively represent the X, Y coordinates of the i-th point in the three-dimensional point cloud data respectively represent the X, Y coordinates of the i-th point in the three-dimensional point cloud data

[0079] The advantage is that the three-dimensional structure parameters are analyzed by the three-dimensional point cloud data scanned by the laser, and the volume characteristics of the fabric are calculated to accurately restore the spatial topological relationship of the yarn, predict the deformation behavior under different tensions, and when the volume characteristics of the fabric are within the design value ±3σ interval, it is determined that the structure uniformity is excellent; when it exceeds the range, the potential wrinkle risk area is marked and the heat setting temperature adjustment scheme is associated; when the volume mutation rate is >15%, the system automatically triggers the weft density abnormal alarm, and finally the system solves the problem of high error rate in double-layer structure identification, and realizes reliable identification of complex jacquard fabric.

[0080] The abnormal deviation degree evaluation unit calculates the abnormal deviation degree according to the sampling self-checking data of the first and last sections of each roll of fabric and the standard process parameter value, which is used to determine whether to trigger the process parameter traceability, and the calculation formula is:

[0081] ;

[0082] In the formula, represents the abnormal deviation degree, represents each process parameter value in the sampling self-checking data, represents the total number of process parameters participating in the calculation, represents the standard value of each process parameter, represents the weight of each process parameter, represents the mean value of the total standard process parameters.

[0083] The advantage is that through the calculation of the abnormal deviation degree , the deviation degree of the single roll of fabric from the standard process is evaluated, so that the process abnormality is quantifiable and traceable, and is processed in stages, when the abnormal deviation degree is in the interval [0, 0.1], it is determined to be normal fluctuation, only the data is recorded without intervention in production; when the abnormal deviation degree is in the interval (0.1, 0.3], the online rechecking program is started, the sampling number is increased, and it is confirmed whether the abnormality is an occasional factor; when the abnormal deviation degree exceeds the interval (0.3, +∞), the process parameter traceability is triggered, the production of this batch is suspended, the influencing factors of raw materials, equipment and environment are traced and the process parameters are adjusted, and finally the system solves the problem of lag in discovering production process abnormalities, and realizes early discovery and early treatment of quality defects on the production line.

[0084] The cumulative error accounting unit calculates the cumulative error by continuously monitoring the data When the set threshold is exceeded, a global recalibration procedure is initiated, whose formula is:

[0085] ;

[0086] In the formula, represents the cumulative error, represents the error value of the th monitoring, represents the time interval between the th monitoring and the previous monitoring, and ∑ represents the summation operation.

[0087] The advantage is that by calculating the cumulative error , long-term implicit trends are made explicit, and preventive systematic corrections are made. When the cumulative error is less than 0.5%, the current observation is maintained; when the cumulative error reaches 0.8%, the sampling frequency is doubled; when the cumulative error is greater than or equal to 1% threshold, the system is forced to trigger the full production line reference calibration process and update the standard reference film library, finally solving the problem of chronic drift caused by equipment aging, ensuring that the recognition accuracy does not decay more than 3% of the initial value within 72 hours of continuous operation.

[0088] The evaluation module evaluates the longitudinal and latitudinal density recognition accuracy according to the longitudinal and latitudinal density compensation values , online monitoring data, and preset evaluation standards, determines whether the compensated longitudinal and latitudinal density is within the qualified range; evaluates the fabric three-dimensional structure integrity and consistency according to the three-dimensional structure feature parameters , online monitoring data, and preset evaluation standards, analyzes whether the three-dimensional structure parameters meet the design requirements; evaluates the process stability according to the abnormal deviation , online monitoring data, and preset evaluation standards, determines whether the abnormal deviation is within the acceptable threshold; evaluates the long-term running accuracy of the system according to the cumulative error , online monitoring data, and preset evaluation standards, determines whether global recalibration needs to be initiated;

[0089] The adjustment module constructs a process adjustment experience map based on the evaluation results of the above-mentioned evaluation module and historical correction records, adjusts the scheme, specifically:

[0090] (1) When the warp and weft density recognition accuracy is not up to standard, the production data analysis module combines the historical adjustment records of the same kind of raw materials in the experience atlas to recalculate the weight factor of the raw material indexes of the micronaire value and the fiber length, correct the warp and weft density compensation formula, and at the same time, transmit the recalculated values to the adjustment module through the network to adjust the warp feed amount parameters of the loom;

[0091] (2) When the fabric three-dimensional structure integrity and consistency is insufficient, the adjustment module optimizes the installation angle and scanning range of the laser scanning sensor of the production monitoring module according to the experience atlas, and at the same time, adjusts the layer fusion algorithm of the three-dimensional modeling software of the production monitoring module, and adjusts the weaving process corresponding to the abnormal area of interlayer interweaving parameters;

[0092] (3) When the process stability exceeds the threshold value, the adjustment module traces the raw material batch, equipment state and other influencing factors that cause the abnormality according to the calculated abnormal deviation degree of the corresponding process parameter traceability path, adjusts the drying machine temperature, cloth winding tension and other related process parameters, and finally records the cause and effect of this adjustment;

[0093] (4) When the system long-term running precision evaluation shows that global recalibration needs to be started, the adjustment module refers to the historical recalibration scheme in the experience atlas to calibrate the precision of the laser scanning sensor, high-resolution industrial camera and detection equipment, update the reference value in the standard process parameter library, and retrain the warp and weft density compensation calculation model;

[0094] The advantages are: through precise matching of evaluation results and adjustment schemes to realize targeted optimization, with the help of experience atlas to inherit historical adjustment wisdom and improve decision-making efficiency, with multi-dimensional data linkage analysis to ensure the scientificity of adjustment, and through the closed-loop adjustment mechanism to continuously improve the adaptability of the system, to guide the subsequent production scheduling and process optimization.

[0095] Example 1

[0096] High-end fashion fabric customized production (small batch, multi-variety): customers require complex jacquard design, raw materials are imported long pile cotton and silk blended, and the requirements for color fastness, hand feeling and pattern fidelity are extremely high.

[0097] System implementation steps:

[0098] S1, the data acquisition module quickly detects the micronaire value (actual value = 3.8) and fiber length distribution (average = 42mm) of the new batch of raw materials, and matches the process parameters of the same kind of high-end fabric in the historical database (such as warp and weft density = 60x40). Because the raw material quality is excellent and stable, the warp and weft density compensation value is calculated as +0.3 (falling in the interval [-0.5, 0.5]), and only the software algorithm is adjusted to recognize the parameters, without hardware intervention;

[0099] S2, the production monitoring module captures fabric three-dimensional point cloud data using laser scanning, finds that the interlayer interweaving angle deviation is less than or equal to 2°, verifies the pattern integrity in combination with the texture image collected by the industrial camera, automatically samples equipment takes 5 samples at the beginning and end of each roll of cloth to model, confirms that the volume characteristic fluctuation is within the design value ± 3σ, and determines that the structure uniformity is excellent;

[0100] S3, the evaluation module displays that all indicators meet the preset standard (warp and weft density qualified rate is 99%, abnormal deviation is less than 0.1), and directly enters the mass production stage;

[0101] S4, the adjustment module calls the "silk blended" process library in the experience atlas, optimizes the drying temperature curve to 120°C gradual heating mode to avoid silk overheating damage. The execution module synchronizes the parameters to the loom control system in real time to ensure that the tension fluctuation is less than ± 1N;

[0102] S5, the feedback module records that the qualified rate of this batch of finished products reaches 99.7%, and stores the data into the knowledge base of the upgrading module for rapid adaptation of subsequent similar orders.

[0103] Implementation effect: realize zero trial and error delivery of small batch customized orders, and improve customer satisfaction to 98%.

[0104] Example 2

[0105] Large-scale manufacturing of industrial canvas (high load, low cost): daily output exceeds 10,000 meters, raw material is ordinary polyester staple fiber, needs to withstand outdoor exposure and mechanical wear and tear, focuses on tensile strength and grammage consistency. System implementation steps:

[0106] S1, the data acquisition module detects that the raw material micronaire value suddenly drops to 2.9 (deviates from the reference value 3.5 by Δ = -0.6), triggers warp and weft density compensation calculation, because the fiber length fluctuation is large (σ_L = 4mm), the compensation value rises to -1.8 (falls into the interval (−2,−0.5)), the system automatically adjusts the warp delivery amount of the loom by +5%, and updates the weight factor α1 = 0.7 to strengthen the micronaire value influence weight;

[0107] S2, the production monitoring module finds that the local thickness exceeds the standard (the measured value is 0.15mm thicker than the standard thickness) at the cloth winding machine, three-dimensional modeling shows that the yarn twist in this area is insufficient, immediately starts the layered marking function to guide the subsequent process to strengthen the compaction treatment in this area;

[0108] S3, the evaluation module alarms that the cumulative error reaches 0.9% (close to the 1% threshold), determines that the equipment has chronic wear and tear, the adjustment module refers to the experience atlas to execute the preventive maintenance scheme: polish and repair the steel reed of the 3 / 7 loom, and synchronize the calibration of the laser sensor reference surface;

[0109] S4, the execution module completes global recalibration in the night off-peak period, the next day shift production data shows that the standard deviation of the weight is narrowed from ±4% to ±1.5%;

[0110] S5, the upgrade module analyzes the data trend for three months, and suggests that the grouping strategy of the polyester raw material is refined into "new material / return material" double-channel management to reduce the difference between batches.

[0111] Implementation effect: the monthly average defective rate is reduced by 40%, and the unplanned downtime of the equipment is reduced by 60%.

[0112] Advantages: as can be seen from the above embodiment 1 and embodiment 2, the system can flexibly adjust the operation mode according to the needs of different production scenes, realize high-quality delivery in high-end customization scenes by virtue of precise data acquisition and fine-tuning ability, and guarantee production stability in large-scale manufacturing scenes by relying on dynamic compensation and preventive maintenance, to verify the universality and high efficiency of the fabric organizational structure automatic identification system in different production modes such as multi-variety, small batch and large-scale, low cost, fully display the beneficial effects of the system in improving product quality, reducing production cost and enhancing customer satisfaction.

[0113] Although embodiments of the present application have been shown and described, it will be understood by those having ordinary skill in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A fabric weave structure automatic recognition system, characterized by, The system comprises a data collection module, a production monitoring module, a production data analysis module, an evaluation module, an adjustment module, an execution module, a feedback module and an upgrade module. The data collection module detects key indicators of each batch of raw materials and obtains historical process data corresponding to different varieties of raw materials. The production monitoring module captures three-dimensional data and two-dimensional image data of the fabric by installing online monitoring devices at different positions. The production data analysis module outputs the latitude and longitude density compensation value based on monitoring and collecting data , three-dimensional structure characteristic parameters , abnormal deviation degree and cumulative error ; The evaluation module evaluates the results of the production data analysis module, online monitoring data and preset evaluation criteria. The adjustment module constructs a process adjustment experience atlas based on the evaluation results of the evaluation module and historical correction records, and generates adjustment schemes for raw material selection, process parameter setting and production process according to the atlas. The execution module receives real-time adjustments of loom parameters, drying temperature, cloth tension and other process parameters of the production line from the adjustment module. The feedback module generates feedback information after analyzing the execution result data. The upgrade module upgrades and optimizes the algorithm model, database and hardware devices of the system according to the long-term feedback data provided by the feedback module.

2. The fabric weave structure automatic recognition system according to claim 1, characterized in that: The data collection module comprises a raw material index detection unit, a historical data retrieval unit and a database construction unit.

3. The fabric weave structure automatic recognition system according to claim 2, characterized in that: The raw material index detection unit detects the micronaire value, short fiber rate, fiber length, fiber fineness, impurity content and moisture regain of each batch of raw materials through a cotton quality detector, a fiber length detector, a fiber fineness detector and other detection devices; the historical data retrieval unit obtains historical process data of corresponding varieties of raw materials through an online variety of raw materials table, a process parameter table and a production result table; and the database construction unit integrates variety of raw materials data and historical process data to establish a variety of raw materials material property database.

4. The fabric weave structure automatic recognition system of claim 1, wherein: The production monitoring module installs laser scanning sensors and high-resolution industrial cameras at the entrance of the loom, the exit of the loom, the exit of the drying machine and the cloth rolling machine, captures three-dimensional data of the fabric through the laser scanning sensors, monitors two-dimensional image data of the fabric through the high-resolution industrial cameras, automatically samples and detects the first and last sections of each roll of cloth through automatic sampling equipment, and finally constructs a three-dimensional model of the fabric semi-finished product and finished product sampling samples using three-dimensional modeling software.

5. The fabric weave structure automatic recognition system according to claim 1, characterized in that: The production data analysis module comprises a longitude and latitude density compensation calculation unit, a three-dimensional structure parameter analysis unit, an abnormal deviation degree evaluation unit and a cumulative error accounting unit, and according to online monitoring data, raw material data and historical record data, longitude and latitude density compensation values are sequentially calculated , three-dimensional structure characteristic parameters , abnormal deviation degrees and cumulative errors .

6. The fabric weave structure automatic recognition system according to claim 5, characterized in that: The warp and weft density compensation calculation unit calculates the warp and weft density compensation values through a mapping relationship between historical process data and current raw material characteristics The calculation formula is: ； In the formula, represents the warp and weft density compensation value, represents the measured value of the current batch of raw materials, represents the standard micronaire value reference value, represents the standard deviation of the micronaire value in the historical database, represents the measured average fiber length, represents the target fiber length set value, represents the allowable fiber length fluctuation range, represents the workshop relative humidity correction coefficient, represents the influence weight factor of micronaire value deviation on warp and weft density, represents the influence weight factor of fiber length difference on warp and weft density, represents the influence weight factor of workshop relative humidity on warp and weft density.

7. The fabric weave structure automatic recognition system according to claim 5, characterized in that: The three-dimensional structure parameter analysis unit calculates the volume feature of the fabric based on the three-dimensional point cloud data of the laser scanning The calculation formula is: ； In the formula, Indicates the volumetric characteristics of the fabric. , Let X and Y coordinates be the values ​​of the i-th point in the 3D point cloud data, respectively. , These represent the first three-dimensional point cloud data. +1 point's X and Y coordinates, Indicates the first The fabric thickness value corresponding to each point.

8. The fabric weave structure automatic recognition system of claim 5, wherein: The abnormal deviation degree evaluation unit calculates the abnormal deviation degree according to the first and last section sampling self-check data of each roll of cloth and the standard process parameter value The calculation formula is: ； In the formula, represents the abnormal deviation degree, represents the value of each process parameter in the sampling self-check data, represents the total number of process parameters participating in the calculation, represents the standard value of each process parameter, represents the weight of each process parameter, represents the mean value of the total standard process parameters.

9. The fabric weave structure automatic recognition system of claim 5, wherein: The cumulative error accounting unit calculates cumulative error by continuously monitoring data A global recalibration procedure is initiated when a set threshold is exceeded, calculated as: ； In the formula, denotes the cumulative error, denotes the error value of the monitoring, denotes the time interval between the monitoring and the previous monitoring, and ∑ denotes the summation operation.

10. The fabric weave structure automatic recognition system of claim 1, wherein: The evaluation module evaluates the longitudinal and latitudinal density recognition accuracy according to the longitudinal and latitudinal density compensation values , online monitoring data and preset evaluation criteria, and judges whether the compensated longitudinal and latitudinal density is within a qualified range, and the specific steps are as follows: S1.1, when the latitude and longitude density compensation value ∈[-0.5,0.5], only through the software algorithm fine-tuning identification parameters, without changing the hardware settings; S1.2, when the latitude and longitude density compensation value when ∈ (0.5, 2]∪[-2, -0.5), adjust the warp let-off amount parameter of the loom and update the compensation formula weight factor synchronously; S1.3, when the latitude and longitude density compensation value When the interval (−∞,−2)∪(2, +∞) is exceeded, start the raw material re-inspection procedure → recalibrate the detection equipment → correct the raw material index detection value and then calculate the compensation value again; According to the three-dimensional structure characteristic parameters , online monitoring data and preset evaluation criteria, the fabric three-dimensional structure integrity and consistency is evaluated, and whether the three-dimensional structure parameters meet the design requirements is analyzed. The specific steps are as follows: S2.1, when the three-dimensional structure characteristic parameter is within the design value ± 3σ interval, it is determined that the structure uniformity is good, and when it exceeds the range, a potential wrinkle risk area is marked and a heat setting temperature adjustment scheme is associated. S2.2, when the volume mutation rate is greater than 15%, the system automatically triggers a weft density abnormality alarm; According to the abnormal deviation degree , online monitoring data and preset evaluation criteria, process stability evaluation is performed to determine whether the abnormal deviation is within an acceptable threshold, and the judgment process is: S3.1, when the abnormal deviation degree ∈[0, 0.1] is determined as normal fluctuation; S3.2, initiate online review procedure and increase sampling size to confirm sporadic factors when the abnormal deviation degree ∈(0.1,0.3] S3.3, when abnormal deviation degree > 0.3, trigger process parameter tracing → suspend the batch production → trace the influencing factors of raw materials / equipment / environment and adjust the process parameters; According to the accumulated error , online monitoring data and preset evaluation criteria, the long-term running accuracy of the system is evaluated to determine whether global recalibration needs to be started, and the specific steps are as follows: S4.1, when the accumulated error <0.5%, maintain the status quo observation; S4.2, when the cumulative error is 0.8%, the sampling frequency is doubled. S4.3, When the accumulated error ≥1% threshold, the system forces to trigger the full line reference calibration process and update the standard reference film library; The adjustment module constructs a process adjustment experience atlas based on the above evaluation results and historical correction records to adjust the scheme.

Images