A clothing sewing management system and method based on RFID technology

Abstract

The present invention discloses a clothing sewing management system and method based on RFID technology, which relates to the technical field of clothing sewing; the clothing sewing management system includes several function modules that operate in sequence, namely a sewing operation monitoring module, a sewing type determination module, a complexity measurement module, a sampling frequency setting module, and a feedback correction module; the technical key points are as follows: the management system designs a method for setting the initial sampling inspection frequency value by combining the process type serial number and complexity, realizing the precise matching of the inspection frequency with the process complexity and type; a dynamic sampling inspection frequency adjustment mechanism based on real-time image recognition effectively improves the abnormal detection and processing ability during the production process, dynamically adjusts the sampling inspection frequency on the basis of the initial sampling inspection frequency, not only improving the accuracy and efficiency of abnormal detection to a certain extent, but also realizing the optimal allocation of inspection resources.

Description

Technical Field

[0001] The present invention relates to the technical field of garment sewing, and in particular to a garment sewing management system and method based on RFID technology. Background Art

[0002] Garment sewing is the process of combining fabrics or other materials into complete garments through manual or machine sewing techniques according to specific design patterns and size requirements. This process covers every link from design concept to finished product production and is the core part of garment production. Workers will draw the design drawings of the garments and select appropriate fabrics and accessories. Then, according to the design drawings, cutters or equipment will cut the fabrics into various shaped pieces. These pieces are finely stitched, including details such as hemming, splicing, installing zippers, buttons, etc., gradually presenting the outline of the garment. During the sewing process, the proficiency of sewing techniques and attention to details directly affect the quality and appearance of the garment. In addition, garment sewing also needs to consider the comfort and practicality of wearing to ensure that the garment is not only beautiful but also durable.

[0003] In the existing document with the publication number CN109359895A and the title of "An RFID Garment Process Guidance System and Its Guidance Method, Production Management System and Method", it is pointed out that it includes RFID electronic tags, station computers, and network servers, and information can be transmitted between components. The RFID electronic tags are attached to the cut pieces, and the information of the cut pieces is written therein. The station computer includes an RFID reader and a display screen. The RFID reader reads the information on the RFID electronic tag and transmits the read cut piece information to the network server. Features: The network server includes a database and a process library. The process library determines the process flow chart according to the style type, divides the processes of the garment style, makes process guidance materials, and stores the process guidance materials in the database. When the process library receives the cut piece information, it transmits the corresponding process guidance materials to the employee's station computer for guiding the employee's operation; it can guide the employees to produce in real time, avoid sewing errors, better guide the employees to sew, and improve production efficiency; in the traditional management process, it is also necessary to conduct regular sampling inspections on the semi-finished or finished garments after sewing to ensure the quality and pass rate of the products. Currently, there is no management system for the inspection frequency of garment products on the market.

[0004] In combination with the above documents and the prior art, there may be multiple processes in the traditional sewing production process. The setting procedures of the equipment required for different types of processes or the technical requirements of manual labor are different. The more complex the process, the higher the requirements. Similarly, the probability of abnormalities or problems is also higher. When sampling and inspecting the semi-finished or finished clothing produced in the corresponding process subsequently, the number of samples drawn each time is also different. In traditional production, the setting of the inspection frequency is blind and lacks a scientific basis. At the same time, the allocation of quality inspection resources is not reasonable enough to effectively meet the high requirements of complex processes for quality control, and there may be problems of over-inspection or under-inspection. Summary of the Invention

[0005] (I) Technical problems to be solved

[0006] In view of the deficiencies of the prior art, the present invention provides a clothing sewing management system and method based on RFID technology. A method for setting the initial sampling inspection frequency value is designed in combination with the process type serial number and complexity, realizing the precise matching of the inspection frequency with the process complexity and type; a dynamic sampling inspection frequency adjustment mechanism based on real-time image recognition effectively improves the abnormal detection and processing ability in the production process, dynamically adjusts the sampling inspection frequency on the basis of the initial sampling inspection frequency, not only improves the accuracy and efficiency of abnormal detection to a certain extent, but also realizes the optimal allocation of inspection resources, and solves the problems proposed in the background art.

[0007] (II) Technical solutions

[0008] To achieve the above objectives, the present invention is realized through the following technical solutions:

[0009] A clothing sewing management system based on RFID technology, the system includes:

[0010] A sewing operation monitoring module, which pre-records the material information of the target cut piece using an RFID tag and records the sewing information using the RFID tag during the sewing process of the target cut piece; wherein, the material information at least includes the origin, batch, and quality of the target cut piece; the sewing information at least includes the sewing strength and sewing speed;

[0011] A sewing type determination module, based on RFID technology, combined with machine vision monitoring and data analysis and processing, to determine the type of the current sewing process; wherein, the types of sewing processes include:

[0012] Process 1: A single sewing operation process;

[0013] Process 2: Multiple serial sewing operation processes;

[0014] Process 3: Parallel sewing operation processes;

[0015] The complexity measurement module runs a simplification processing mechanism according to the determined sewing process type, inputs the obtained result and the pre-collected operation qualification rate into the corresponding complexity calculation model established, and outputs the process complexity under the corresponding sewing process type.

[0016] The sampling frequency setting module combines the type and process complexity of the corresponding sewing process to set the preliminary sampling inspection frequency value, which is used to provide inspection frequency guidance for the semi-finished garments obtained from the corresponding type of sewing process.

[0017] The feedback correction module performs real-time sampling actions according to the preliminary sampling inspection frequency value. Within the set number of samplings M, real-time image recognition actions are performed. When the recognition result is normal, the established strategy is executed; when the recognition result is abnormal, the feedback correction strategy is executed to correct the preliminary sampling inspection frequency value.

[0018] Furthermore, a management warning unit can be added to the sewing operation monitoring module. Through RFID technology, sewing information is monitored in real time. When it is detected that the fluctuation value of the sewing force within the set time window S exceeds the set fluctuation standard value, a first-level warning signal is triggered; when the real-time sewing speed is reduced to 90% of the set speed, a second-level warning signal is triggered.

[0019] Under the condition of receiving any warning signal, the power-off action of the equipment is performed, and dispatch and maintenance processing are carried out.

[0020] Among them, the value range of S is: at least greater than 0; the fluctuation value of the sewing force within the time window S represents: the absolute value of the difference between the maximum value and the minimum value of the sewing force within the time window S.

[0021] Furthermore, the process of combining machine vision monitoring and data analysis and processing is as follows:

[0022] Machine vision system deployment: Deploy machine vision cameras on the production line during the sewing process to monitor the sewing process in real time; through the machine vision system, image recognition and analysis are carried out on the sewing process to identify the type of sewing operation currently being carried out, including any one or several of straight sewing and curved sewing.

[0023] Data collection and integration: Integrate the data collected by RFID technology and the machine vision system to form a process data chain for judging the type of sewing process:

[0024] When the RFID tag shows that the current station is any type of sewing operation, and the machine vision system reconfirms that the station is performing the sewing operation of this type, it is determined that the current process is a single sewing operation process, that is, process one.

[0025] When the RFID tag indicates that multiple types of sewing operations are sequentially performed at the current work station and the machine vision system identifies the sequence of multiple types of sewing operations, it is determined that the current process is a multiple serial sewing operation process, that is, Process Two;

[0026] When the RFID tag indicates that multiple work stations are performing sewing operations simultaneously and the machine vision system monitors that the sewing operations are simultaneous, it is determined that the current process is a parallel sewing operation process, that is, Process Three.

[0027] Furthermore, the running process of the simplified processing mechanism is as follows:

[0028] Under the conditions that the sewing types are straight stitching and curved stitching, when calculating the operation difficulty coefficient of straight stitching, the formula used is: , where D1 in the formula represents the operation difficulty coefficient of straight stitching, represents the basic difficulty coefficient, represents the complexity adjustment factor corresponding to straight stitching;

[0029] When calculating the operation difficulty coefficient of curved stitching, the formula used is: , where D2 in the formula represents the operation difficulty coefficient of curved stitching, represents the complexity adjustment factor corresponding to curved stitching;

[0030] When calculating the parallel cooperation coefficient, the formula used is as follows:

[0031] ;

[0032] ;

[0033] In the formula, C represents the parallel cooperation coefficient, bs represents the number of parallel operations, and pr represents the cooperation difficulty factor.

[0034] Furthermore, when the determined sewing process type is a single sewing operation process;

[0035] then, the running process of the corresponding complexity calculation model is as follows:

[0036] ;

[0037] In the formula, Cp represents the process complexity, P represents the operation qualification rate of the corresponding type of sewing process, and D represents the operation difficulty coefficient corresponding to the corresponding sewing type;

[0038] When the determined sewing process type is a multiple serial sewing operation process;

[0039] then, the running process of the corresponding complexity calculation model is as follows:

[0040] ;

[0041] Wherein, represents the operation qualification rate of the i-th operation, represents the operation difficulty coefficient of the i-th operation, and n represents the total number of operations;

[0042] When the determined sewing process type is a parallel sewing operation process;

[0043] Then, the operation process of the corresponding complexity calculation model is as follows:

[0044] .

[0045] Furthermore, in combination with the type of the corresponding sewing process and the process complexity, after dimensionless processing, the preliminary sampling inspection frequency value is set in the following manner:

[0046] ;

[0047] ;

[0048] Wherein, F represents the preliminary sampling inspection frequency value, represents rounding up, Q_nb represents the value to be rounded up, represents the growth coefficient, and the value range is: 0 < < 1, and Tx represents the serial number corresponding to the sewing process type.

[0049] Furthermore, the process of real-time image recognition is as follows:

[0050] Data preparation: Collect a number of normal and abnormal images as the training data set, and preprocess the training data set; among them, the abnormal images include thread head breakage, non-straightness, and fracture; the preprocessing includes image enhancement and standardization;

[0051] Model selection and training: Select CNN as the computer vision model architecture, use the preprocessed training data set to train the CNN model, and during the training process, adjust the model parameters through the loss function;

[0052] Real-time sampling and image recognition: Within the set number of samplings M, perform real-time sampling actions according to the preliminary sampling inspection frequency value, input the sampled images into the trained CNN model for recognition, and the CNN model outputs a probability value indicating whether the image is abnormal;

[0053] Abnormality judgment and processing: Preset an abnormality judgment threshold;

[0054] When the probability value is higher than the abnormality judgment threshold, it is judged that the image is abnormal;

[0055] When the probability value is not higher than the anomaly judgment threshold, it is determined that the image is normal.

[0056] Furthermore, the established strategy to be executed is: maintaining the original preliminary sampling inspection frequency value for real-time sampling operations.

[0057] Furthermore, the feedback correction strategy to be executed is as follows:

[0058] Construct a dynamic adjustment formula based on the anomaly rate:

[0059] ;

[0060] In the formula, \(F_{xz}\) represents the dynamic sampling inspection frequency value, represents the adjustment coefficient, with a value range of \(0 \lt \lt 1\), \(N_c\) represents the number of anomalies detected in \(M\) samplings, and \(N_c / M\) represents the anomaly rate.

[0061] A clothing sewing management method based on RFID technology includes the following steps:

[0062] S1. Use RFID tags to pre-record the material information of the target cut pieces, and use RFID tags to record the sewing information during the sewing process of the target cut pieces; among them, the material information at least includes the origin, batch, and quality of the target cut pieces; the sewing information at least includes the sewing strength and sewing speed;

[0063] S2. Based on RFID technology, combined with machine vision monitoring and data analysis and processing, to determine the type of the current sewing process; among them, the types of sewing processes include:

[0064] Process 1: Single sewing operation process;

[0065] Process 2: Multiple serial sewing operation processes;

[0066] Process 3: Parallel sewing operation process;

[0067] S3. According to the determined type of sewing process, run a simplified processing mechanism, input the obtained result and the pre-collected operation qualification rate into the corresponding complexity calculation model built, and output the process complexity under the corresponding type of sewing process;

[0068] S4. Combine the type of the corresponding sewing process and the process complexity to set the preliminary sampling inspection frequency value, which is used to provide inspection frequency guidance for the semi-finished clothing obtained under the corresponding type of sewing process;

[0069] S5. Perform real-time sampling actions according to the preliminary sampling inspection frequency value. During the set number of sampling times M, perform real-time image recognition actions. If the recognition result is normal, execute the established strategy; if the recognition result is abnormal, execute the feedback correction strategy to correct the preliminary sampling inspection frequency value.

[0070] (III) Beneficial effects

[0071] The present invention provides a clothing sewing management system and method based on RFID technology, having the following beneficial effects:

[0072] This solution integrates RFID technology, machine vision monitoring, and data analysis and processing. It not only ensures the rapid warehousing, outbound, and inventory management of raw materials but also realizes the real-time monitoring and early warning of key parameters during the sewing process, effectively reducing equipment failure rates and production anomalies; the automatic judgment of sewing processes reduces manual intervention and improves production efficiency and accuracy;

[0073] This solution realizes the precise quantification and dynamic adjustment of the sampling inspection frequency for the complexity of sewing processes, significantly improving the effectiveness and efficiency of production quality control; according to the types of sewing processes (single, multiple serial, parallel) and their corresponding complexities, a special calculation model comprehensively considers the operation qualification rate, difficulty coefficient, and parallel cooperation efficiency to reasonably and effectively evaluate the complexity of the processes; furthermore, a method for setting the preliminary sampling inspection frequency value is designed in combination with the process type serial number and complexity, realizing the precise matching of the inspection frequency with the process complexity and type;

[0074] This solution realizes a dynamic sampling inspection frequency adjustment mechanism based on real-time image recognition, effectively improving the anomaly detection and processing capabilities during the production process. On the basis of the preliminary sampling inspection frequency, a convolutional neural network model is used to accurately recognize real-time sampling images, and the sampling inspection frequency is dynamically adjusted according to the anomaly rate in the recognition result; when an anomaly is detected, it can quickly feedback and correct the sampling frequency to ensure timely response to production anomalies, not only improving the accuracy and efficiency of anomaly detection but also realizing the optimal allocation of inspection resources and avoiding problems of over-inspection or under-inspection. Brief description of the drawings

[0075] Figure 1 It is a modular schematic diagram of the management system in the present invention;

[0076] Figure 2 It is the overall step flow chart of the management method in the present invention. Detailed implementation manners

[0077] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0078] Embodiment 1

[0079] Please refer to Figure 1 , this embodiment provides a garment sewing management system based on RFID technology;

[0080] The purpose of this solution is to construct an efficient and accurate garment sewing management system by introducing RFID (Radio Frequency Identification) technology. This system specifically covers the entire process from the sewing process of garment materials to the inspection of finished or semi-finished products. Through real-time monitoring and data analysis, the sampling detection frequency of batch semi-finished products obtained under different sewing process types is adjusted specifically, ensuring production efficiency to a certain extent, and being able to promptly detect abnormal situations, facilitating subsequent timely adjustment of relevant equipment to ensure the effective management of the entire sewing operation process;

[0081] System Function Module Design

[0082] This garment sewing management system includes several function modules that run sequentially, namely a sewing operation monitoring module, a sewing type determination module, a complexity measurement module, a sampling frequency setting module, and a feedback correction module;

[0083] The following is an explanation of each function module in this system:

[0084] Sewing Operation Monitoring Module:

[0085] Use RFID tags to pre-record the material information of the target cut piece, and use RFID tags to record the sewing information during the sewing process of the target cut piece; among them, the material information at least includes the origin, batch, and quality of the target cut piece; the sewing information at least includes the sewing strength and sewing speed;

[0086] Among them, for the use of RFID tags on each target cut piece, the recorded information can be operated as needed;

[0087] Use RFID tags to record information such as the origin, batch, and quality of the target cut piece (i.e., the corresponding raw material), realizing the rapid warehousing, outwarehousing, and inventory management of raw materials; through RFID technology, realize the whole-process traceability of raw materials to ensure the controllability of raw material quality; at the same time, improve the accuracy and efficiency of raw material management;

[0088] During the sewing process, RFID tags are used to record key parameters such as sewing force and sewing speed. Usually, automated equipment is used to perform the sewing process. It should be noted that in this application, all sewing operations are carried out by automated equipment, not manually;

[0089] Therefore, a management warning unit can also be added to the sewing operation monitoring module. Through RFID technology, sewing information is monitored in real time. When the fluctuation value of the sewing force within the set time window S exceeds the set fluctuation standard value, a first-level warning signal is triggered; when the real-time sewing speed drops to 90% of the set speed, a second-level warning signal is triggered;

[0090] When the system receives any warning signal, the equipment is powered off and maintenance dispatch processing is carried out;

[0091] Among them, the value range of S is: at least greater than 0;

[0092] The fluctuation value of the sewing force within the time window S means: the absolute value of the difference between the maximum value and the minimum value of the sewing force within the time window S is the sewing force fluctuation value;

[0093] The first-level warning signal and the second-level warning signal are only used to distinguish the types of equipment anomalies, which is convenient for the subsequent maintenance work. At the same time, for the two types of warning signals, different warning methods are adopted. For example, the first-level warning signal is warned by a yellow strobe light, and the second-level warning signal is warned by a red strobe light.

[0094] Sewing type determination module:

[0095] Based on RFID technology, combined with machine vision monitoring and data analysis and processing, to judge the type of the current sewing process;

[0096] This solution installs RFID readers at the production line station nodes, equips each target cut piece with an RFID tag, combines with a machine vision system to monitor the sewing process in real time, and finally processes the collected information through a data analysis system to automatically judge the type of the current sewing process;

[0097] The specific steps for the operation of the sewing type determination module are as follows:

[0098] 1. Data collection and label binding

[0099] Application of RFID technology: Install RFID readers at the workstation nodes on the production line (corresponding to different types of sewing processes), and equip each target cut piece with an RFID tag. When the target cut piece passes through a workstation node on the production line or is being processed at the workstation node, the RFID tag communicates wirelessly with the RFID reader to read and transmit information of the RFID tag, such as key information like the current workstation, process status, production batch, etc.;

[0100] Example: Suppose a target cut piece is undergoing a straight stitching operation. Its RFID tag will record that the current workstation of this target cut piece is the "straight stitching workstation" and the process status is "in progress";

[0101] 2. Machine vision monitoring

[0102] Deployment of machine vision system: Deploy machine vision cameras around the production line during the sewing process to monitor the sewing process in real time; Image recognition and analysis: Through the machine vision system, perform image recognition and analysis on the sewing process to identify the type of sewing operation currently being carried out, such as straight stitching, curve stitching, etc.;

[0103] Example: The machine vision system captures that a certain target cut piece is undergoing a curve stitching operation and transmits this information for analysis;

[0104] 3. Data analysis and judgment

[0105] Data collection and integration: Integrate the data collected by the RFID technology and the machine vision system to form a complete process data chain;

[0106] Judgment of process type

[0107] Single sewing operation process: If the RFID tag shows that the current workstation is a certain specific sewing operation (such as the straight stitching workstation), and the machine vision system confirms that this operation is being carried out at this workstation, then judge that the current process is a single sewing operation process; Example: The RFID tag shows that the current workstation is the "straight stitching workstation", and the machine vision system confirms that the straight stitching operation is being carried out at this workstation, then judge that the current process is a single sewing operation process;

[0108] Multiple serial sewing operation processes: If the RFID tag shows that multiple sewing operations need to be carried out sequentially at the current workstation (such as straight stitching first and then curve stitching), and the machine vision system can identify the sequence of these operations, then judge that the current process is a multiple serial sewing operation process; Example: The RFID tag shows that straight stitching needs to be carried out first and then curve stitching at the current workstation, and the machine vision system monitors that these two operations are carried out sequentially, then judge that the current process is a multiple serial sewing operation process;

[0109] Parallel Sewing Operation Process: If the RFID tag indicates that multiple workstations are currently performing sewing operations simultaneously (e.g., straight stitching and curved stitching are being carried out on different machines at the same time), and the machine vision system can monitor that these operations are occurring simultaneously, then the current process is determined to be a parallel sewing operation process; Example: The RFID tag shows that there are two workstations currently, one performing straight stitching and the other performing curved stitching, and the machine vision system monitors that these two operations are occurring simultaneously, then the current process is determined to be a parallel sewing operation process;

[0110] Therefore, the types of current sewing processes include:

[0111] Process 1: Single Sewing Operation Process;

[0112] Process 2: Multiple Serial Sewing Operation Processes;

[0113] Process 3: Parallel Sewing Operation Process;

[0114] Each of the above types of sewing processes corresponds to a workstation, and is operated by the automated sewing equipment debugged on the corresponding workstation. Moreover, after each type of sewing process sews and processes the target cut piece, a batch of semi-finished garments is obtained;

[0115] The technical advantages of the solution are as follows:

[0116] Real-time and accuracy: Through the real-time monitoring of RFID technology and machine vision, real-time and accurate judgment of the type of sewing process can be achieved; Efficiency: Automated judgment reduces manual intervention and waiting time, improving production efficiency; Scalability: As the production line continues to expand and change, RFID readers and tags, machine vision cameras, etc. can be easily added and adjusted to meet new production requirements;

[0117] In summary, through the comprehensive application of combining RFID technology, machine vision, and data analysis, automatic judgment of the type of sewing process can be achieved, thereby improving the automation, informatization, and intelligence levels of the production line.

[0118] By adopting the above technical solution, real-time and accurate judgment and automated management of the type of sewing process are achieved, significantly improving the efficiency and intelligence level of the production line;

[0119] This solution integrates RFID technology, machine vision monitoring, and data analysis and processing. It not only ensures the rapid warehousing, outbound, and inventory management of raw materials, but also realizes the real-time monitoring and early warning of key parameters during the sewing process, effectively reducing equipment failure rates and production anomalies; At the same time, through the automated judgment of the sewing process, manual intervention is reduced, and production efficiency and accuracy are improved; In addition, this solution also has good scalability and can easily handle the changes and expansion requirements of the production line;

[0120] In summary, this technical solution successfully solves the problems existing in the traditional sewing production process, such as inaccurate process judgment, low production efficiency, and high management difficulty, and realizes the intelligent identification and management of sewing processes.

[0121] Complexity measurement module:

[0122] According to the determined sewing process type, run a simplification processing mechanism, input the obtained result and the pre-collected operation qualification rate into the corresponding complexity calculation model built, and output the process complexity under the corresponding sewing process type, which reflects the attention degree of the system to the current type of sewing process;

[0123] Among them, the process of running the simplification processing mechanism is as follows:

[0124] Under the conditions that the sewing types are straight stitching and curve stitching, when calculating the operation difficulty coefficient of straight stitching, the formula is: , where D1 in the formula represents the operation difficulty coefficient of straight stitching, represents the basic difficulty coefficient, and its value is usually 1, representing the most basic sewing operation difficulty, represents the complexity adjustment factor corresponding to straight stitching, and its value is 0.2. Although straight stitching is relatively simple, certain skills are still required, so a complexity adjustment factor of 0.2 is added;

[0125] When calculating the operation difficulty coefficient of curve stitching, the formula is: , where D2 in the formula represents the operation difficulty coefficient of curve stitching, represents the complexity adjustment factor corresponding to curve stitching, and its value is 0.5. Curve stitching has higher technical requirements and greater operation difficulty than straight stitching, so the complexity adjustment factor is set to 0.5;

[0126] When calculating the parallel cooperation coefficient, the formula is as follows:

[0127] ;

[0128] ;

[0129] In the formula, C represents the parallel cooperation coefficient, bs represents the number of parallel operations, and pr represents the cooperation difficulty factor; when pr = 0.1, it means that for each additional parallel operation, the cooperation difficulty increases by 10%;

[0130] It should be noted that the parallel cooperation coefficient is used to reflect the coordination and synchronization difficulty among operations in parallel sewing operations; this setting takes into account the influence of the number of parallel operations on the cooperation difficulty and quantifies it through the cooperation difficulty factor; although the specific values may vary depending on the actual situation, this setting provides a reasonable starting point.

[0131] The determined type of sewing process is: single sewing operation process, that is, when it is process one;

[0132] Then, the running process of the corresponding complexity calculation model is as follows:

[0133] ;

[0134] In the formula, Cp represents the process complexity, P represents the operation qualification rate of the corresponding type of sewing process, that is, the probability of successful completion of this operation, and D represents the operation difficulty coefficient corresponding to the corresponding sewing type;

[0135] Explanation: For a single sewing operation process, its complexity is directly determined by the operation qualification rate and the difficulty coefficient. The higher the qualification rate and the greater the difficulty, the higher the process complexity; Example: Suppose the qualification rate of a straight stitch operation is 95% and the operation difficulty coefficient is 1.2 (determined by the simplified processing mechanism result); then the process complexity = 95% × 1.2 = 1.14;

[0136] The determined type of sewing process is: multiple serial sewing operation processes, that is, when it is process two;

[0137] Then, the running process of the corresponding complexity calculation model is as follows:

[0138] ;

[0139] In the formula, represents the operation qualification rate of the i-th operation, represents the operation difficulty coefficient of the i-th operation, and n represents the total number of operations;

[0140] Explanation: For multiple serial sewing operation processes, its complexity is determined by the weighted average of the qualification rate and the difficulty coefficient of each operation. The weighted average is used here to consider the importance of different operations in the process; Example: Suppose a process includes two sewing operations. The first operation (straight stitch) has a qualification rate of 95% and a difficulty coefficient of 1.2; the second operation (curved stitch) has a qualification rate of 90% and a difficulty coefficient of 1.5; then the process complexity = (95% × 1.2 + 90% × 1.5) / 2 = 1.185;

[0141] The determined type of sewing process is: parallel sewing operation process, that is, when it is process three;

[0142] Then, the running process of the corresponding complexity calculation model is as follows:

[0143] ;

[0144] In the formula, C represents the parallel cooperation coefficient;

[0145] Explanation: For parallel sewing operation processes, in addition to considering the qualification rate and difficulty coefficient of each operation, the coordination efficiency between parallel operations also needs to be considered; the parallel coordination coefficient is used to adjust the increased complexity brought by parallel operations; Example: Suppose a parallel process includes two identical straight stitching operations, the qualification rate of each operation is 95%, the difficulty coefficient is 1.2, and the parallel coordination coefficient is 1.1; then the process complexity = (95%×1.2 + 95%×1.2) / 2×1.1 = 1.254.

[0146] Sampling frequency setting module:

[0147] Combined with the type and process complexity of the corresponding sewing process, to set the preliminary sampling inspection frequency value, which provides theoretical guidance for the inspection frequency of semi-finished clothing obtained from the corresponding type of sewing process;

[0148] Among them, after dimensionless processing by combining the type and process complexity of the corresponding sewing process, the preliminary sampling inspection frequency value is set in the following way:

[0149] ;

[0150] ;

[0151] In the formula, F represents the preliminary sampling inspection frequency value, represents rounding up, Q_nb represents the value to be rounded up, represents the growth coefficient, which is a fixed value used to adjust the growth rate difference between different process types, and the value range is: 0 < < 1, Tx represents the serial number corresponding to the sewing process type;

[0152] It should be noted that considering the differences in process types, we can adjust the growth rate through a regulation parameter bT based on the process type serial number (where bT > 1 to ensure exponential growth); for simplicity, we can assume that bT is a certain function of the process type serial number Tx, such as bT = 1 + ×Tx, where is a fixed growth coefficient; the above formula adjusts the base of the exponential function through ×Tx, thus realizing the exponential growth requirement of the inspection frequency for different process types; as the process complexity Cp increases, the inspection frequency F will increase at an exponential rate related to the process type serial number Tx;

[0153] The following is an example of parameter setting and calculation results, where we assume = 0.2:

[0154]

[0155] In this example, as the process complexity Cp and the process type serial number Tx increase, the inspection frequency F shows an exponential growth, and the above example is only illustrative data for auxiliary understanding.

[0156] When the initial sampling inspection frequency value F = 2, it means that for each sampling inspection, the number of semi-finished garments selected is 2.

[0157] By adopting the above technical solution, the accurate quantification of the sewing process complexity and the dynamic adjustment of the sampling inspection frequency are realized, significantly improving the effectiveness and efficiency of production quality control; according to the sewing process type (single, multiple serial, parallel) and its corresponding complexity, the dedicated calculation model comprehensively considers the operation qualification rate, difficulty coefficient and parallel cooperation efficiency to scientifically evaluate the complexity of the process; furthermore, through the dimensionless processing of the process type serial number and complexity, a method for setting the initial sampling inspection frequency value is innovatively designed to achieve the precise matching of the inspection frequency with the process complexity and type;

[0158] This technical solution not only solves the problem of blind setting and lack of scientific basis for the inspection frequency in traditional production, but also ensures the reasonable allocation of quality inspection resources, improving the inspection efficiency and accuracy; through the exponential growth of the inspection frequency setting, it effectively meets the high requirements of complex processes for quality control, provides an intelligent and refined quality management solution for the garment manufacturing industry, and strongly promotes the double improvement of production efficiency and product quality.

[0159] Feedback correction module:

[0160] Based on the initial sampling inspection frequency value, real-time sampling actions are performed. Within the set number of sampling times M, real-time image recognition actions are carried out. When the recognition result is normal, the established strategy is executed; when the recognition result is abnormal, the feedback correction strategy is executed to correct the initial sampling inspection frequency value, so as to obtain and perform subsequent sampling actions according to the dynamic sampling inspection frequency value;

[0161] Among them, the process of real-time image recognition is as follows:

[0162] 1. Data preparation

[0163] Training data set: Collect a large number of normal and abnormal (such as thread breaks, non-straightness, fractures) images as the training data set, which can be from historical production records, simulated abnormal scenario shootings, etc.;

[0164] Preprocessing: Preprocess the training data, including steps such as image enhancement, size adjustment and standardization;

[0165] Image enhancement can improve the contrast and clarity of images, helping to better distinguish normal and abnormal images; size adjustment can resize the input image to a size suitable for model input; normalization can make the pixel values of the image fall within a specific range to accelerate model training speed and improve the generalization ability of the model;

[0166] 2. Model Selection and Training

[0167] Model Architecture: Select a suitable computer vision model architecture, such as a convolutional neural network (CNN). CNN performs well in the field of image processing, can automatically extract image features, and is suitable for anomaly detection tasks;

[0168] Training Process: Use the preprocessed training dataset to train the CNN model. During the training process, adjust the model parameters through the loss function and optimization algorithm so that the model can accurately identify normal and abnormal images;

[0169] 3. Real-time Sampling and Image Recognition

[0170] Real-time Sampling: Within the set number of sampling times M, perform real-time sampling actions according to the preliminary sampling inspection frequency value;

[0171] Image Recognition: Input the sampled image into the trained CNN model for recognition. The model will output a probability value indicating whether the image has anomalies (such as broken, non-straight, or fractured thread ends, etc.);

[0172] 4. Anomaly Judgment and Handling

[0173] Set Threshold: Set an anomaly judgment threshold according to business requirements. If the anomaly probability value output by the model is higher than the threshold, it is judged that the image has an anomaly; otherwise, there is no anomaly;

[0174] Anomaly Handling: For the identified abnormal images, corresponding handling measures can be taken, such as marking the abnormal location, issuing an alarm, stopping for inspection, etc.;

[0175] The established strategy to be executed is as follows:

[0176] Maintain the original preliminary sampling inspection frequency value for real-time sampling actions;

[0177] The feedback correction strategy to be executed is as follows:

[0178] Construct a dynamic adjustment formula based on the anomaly rate:

[0179] ;

[0180] In the formula, F_xz represents the dynamic sampling inspection frequency value, denotes the adjustment coefficient, which is used to control the influence degree of the number of anomalies on the sampling inspection frequency value, and its value range is 0 < < 1, where Nc represents the number of anomalies detected in M samplings, and Nc / M represents the anomaly rate;

[0181] Logical description:

[0182] When Nc = 0, that is, no anomaly is detected, the corrected sampling inspection frequency value remains F;

[0183] When N > 0, that is, an anomaly is detected, the corrected sampling inspection frequency value will increase, and the degree of increase depends on the anomaly rate and the adjustment coefficient; the higher the anomaly rate, the higher the corrected sampling inspection frequency value, and the larger the adjustment coefficient k, the greater the influence of the number of anomalies on the sampling inspection frequency value, that is, the faster the corrected sampling inspection frequency value increases.

[0184] By adopting the above technical solution, a dynamic sampling inspection frequency adjustment mechanism based on real-time image recognition is realized, effectively improving the anomaly detection and processing capabilities in the production process; based on the initial sampling inspection frequency, this solution accurately recognizes the real-time sampling images through a convolutional neural network model, and dynamically adjusts the sampling inspection frequency according to the anomaly rate in the recognition results; when an anomaly is detected, it can quickly feedback and correct the sampling frequency to ensure timely response to production anomalies;

[0185] This technical solution not only improves the accuracy and efficiency of anomaly detection, but also realizes the optimal allocation of inspection resources, avoiding the problems of over-inspection or under-inspection; generally speaking, this solution successfully solves the technical problem that the frequency setting in traditional sampling inspection is fixed and cannot adapt to the dynamic changes of production.

[0186] Embodiment 2

[0187] Please refer to Figure 2 , based on Embodiment 1, this embodiment also provides a clothing sewing management method based on RFID technology, including the following specific steps:

[0188] S1. Use RFID tags to pre-record the material information of the target cut piece, and use RFID tags to record the sewing information during the sewing process of the target cut piece; among them, the material information includes at least the origin, batch, and quality of the target cut piece; the sewing information includes at least the sewing strength and sewing speed;

[0189] S2. Based on RFID technology, combined with machine vision monitoring and data analysis and processing, to judge the type of the current sewing process; among them, the types of sewing processes include:

[0190] Process 1: Single sewing operation process;

[0191] Process Step 2: Multiple serial sewing operation steps;

[0192] Process Step 3: Parallel sewing operation steps;

[0193] S3. According to the determined sewing process type, run the simplification processing mechanism, input the obtained result and the pre-collected operation qualification rate into the corresponding complexity calculation model built, and output the process complexity under the corresponding sewing process type;

[0194] S4. Combine the type and process complexity of the corresponding sewing process to set the preliminary sampling inspection frequency value, which is used to provide inspection frequency guidance for the semi-finished garments obtained under the corresponding type of sewing process;

[0195] S5. Perform real-time sampling actions according to the preliminary sampling inspection frequency value. Within the set number of sampling times M, perform real-time image recognition actions. When the recognition result is normal, execute the established strategy; when the recognition result is abnormal, execute the feedback correction strategy to correct the preliminary sampling inspection frequency value.

[0196] The above sampling inspection frequencies are all for a batch of semi-finished garments obtained under different types of processes. For semi-finished products made by automated equipment, there are rarely abnormalities or mistakes. Therefore, fixed-frequency sampling is required. For the sampling inspection frequency, it represents the number of semi-finished products inspected at each fixed time point. For example: 3 pieces each time, 6 pieces each time are both sampling inspection frequencies. If the error rate of the automated equipment is low, the sampling inspection frequency will decrease. For example: from the original 6 pieces each time to 3 pieces each time.

[0197] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution.

[0198] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, and may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A clothing sewing management system based on RFID technology, characterized in that: The system includes: The sewing operation monitoring module uses an RFID tag to record the material information of the target piece in advance, and uses the RFID tag to record the sewing information during the sewing process of the target piece; wherein the material information at least includes the origin, batch, and quality of the target piece; and the sewing information at least includes the sewing force and sewing speed; The sewing type determination module is based on RFID technology, combined with machine vision monitoring and data analysis and processing to determine the type of the current sewing process; among which, the types of sewing processes include: Process 1: Single sewing operation process; Process 2: Multiple serial sewing operations; Process three: parallel sewing operation process; The complexity measurement module runs the simplified processing mechanism according to the sewing process type determined, inputs the obtained results and the pre-collected operation qualification rate into the corresponding complexity calculation model, and outputs the process complexity under the corresponding sewing process type; the simplified processing mechanism process is as follows: When the sewing type is straight stitching and curved stitching, the formula used to calculate the difficulty coefficient of straight stitching operation is: , where D1 represents the difficulty coefficient of linear suture operation, Indicates the basic difficulty coefficient, Indicates the complexity adjustment factor corresponding to linear suture; The formula used to calculate the difficulty coefficient of the curve stitching operation is: , where D2 represents the difficulty coefficient of curve stitching operation, Indicates the complexity adjustment factor corresponding to curve stitching; The formula used to calculate the parallel coordination coefficient is as follows: ； ； In the formula, C represents the parallel coordination coefficient, bs represents the number of parallel operations, and pr represents the coordination difficulty factor; The sampling frequency setting module combines the type and complexity of the corresponding sewing process to set the preliminary sampling inspection frequency value, which is used to provide inspection frequency guidance for the semi-finished garments obtained from the corresponding type of sewing process; The feedback correction module performs real-time sampling actions according to the preliminary sampling inspection frequency value, and performs real-time image recognition actions within the set sampling times M. When there is no abnormality in the recognition result, the established strategy is executed to maintain the original preliminary sampling inspection frequency value for real-time sampling actions; when there is an abnormality in the recognition result, the feedback correction strategy is executed to correct the preliminary sampling inspection frequency value.

2. The garment sewing management system based on RFID technology according to claim 1, characterized in that: A management warning unit can also be added to the sewing operation monitoring module to monitor sewing information in real time through RFID technology. When the sewing force fluctuation value within the set time window S exceeds the set fluctuation standard value, a first-level warning signal is triggered; When the real-time sewing speed is reduced to 90% of the set speed, the secondary warning signal is triggered; If any warning signal is received, the equipment will be powered off and maintenance will be dispatched; The value range of S is: at least greater than 0; the suture force fluctuation value within the time window S represents: the absolute value of the difference between the maximum value and the minimum value of the suture force within the time window S.

3. The garment sewing management system based on RFID technology according to claim 1, characterized in that: The process of combining machine vision monitoring and data analysis and processing is as follows: Machine vision system deployment: Machine vision cameras are deployed on the production line of the sewing process to monitor the sewing process in real time; the machine vision system is used to perform image recognition and analysis on the sewing process to identify the type of sewing operation currently being performed, including any one or more of straight sewing and curved sewing; Data collection and integration: Integrate the data collected by RFID technology and machine vision system to form a process data chain to determine the type of sewing process: When the RFID tag shows that the current workstation is any sewing operation type, and the machine vision system determines for the second time that the workstation is performing this type of sewing operation, the current process is determined to be a single sewing operation process, i.e., process one; When the RFID tag shows that the current workstation performs multiple types of sewing operations in sequence, and the machine vision system recognizes the sequence of the multiple types of sewing operations, it is determined that the current process is a multiple serial sewing operation process, that is, process two; When the RFID tag shows that there are multiple workstations performing sewing operations simultaneously, and the machine vision system monitors that the sewing operations are performed simultaneously, it is determined that the current process is a parallel sewing operation process, that is, process three.

4. The garment sewing management system based on RFID technology according to claim 1, characterized in that: When the sewing process type determined to be a single sewing operation process; Then, the operation process of the corresponding complexity calculation model is as follows: ； In the formula, Cp represents the complexity of the process, P represents the qualified rate of the corresponding type of sewing process, and D represents the corresponding operation difficulty coefficient under the corresponding sewing type; When the sewing process type determined to be multiple serial sewing operation processes; Then, the operation process of the corresponding complexity calculation model is as follows: ； In the formula, represents the operation qualification rate of the i-th operation, represents the difficulty coefficient of the i-th operation, and n represents the total number of operations; When the sewing process type is determined to be a parallel sewing operation process; Then, the operation process of the corresponding complexity calculation model is as follows: 。 5. The garment sewing management system based on RFID technology according to claim 4 is characterized in that: Combined with the type and complexity of the corresponding sewing process, after dimensionless processing, the preliminary sampling inspection frequency value is set as follows: ； ； Where F represents the frequency of preliminary sampling inspection. Indicates rounding up, Q_nb indicates the value to be rounded, Indicates the growth coefficient, value range: 0< <1, Tx represents the serial number corresponding to the sewing process type.

6. The garment sewing management system based on RFID technology according to claim 1, characterized in that: The process of performing image recognition actions in real time is as follows: Data preparation: Collect several normal and abnormal images as training data sets, and preprocess the training data sets; abnormal images include broken, uneven, and fractured threads; preprocessing includes image enhancement and standardization; Model selection and training: CNN is selected as the computer vision model architecture, and the CNN model is trained using the preprocessed training data set. During the training process, the model parameters are adjusted through the loss function. Real-time sampling and image recognition: within the set sampling times M, real-time sampling is performed according to the preliminary sampling inspection frequency value, and the sampled image is input into the trained CNN model for recognition. The CNN model outputs a probability value indicating whether the image is abnormal; Abnormal judgment and processing: preset an abnormal judgment threshold; When the probability value is higher than the abnormality judgment threshold, the image is judged to be abnormal; When the probability value is not higher than the abnormality judgment threshold, the image is judged to be normal.

7. The garment sewing management system based on RFID technology according to claim 1, characterized in that: The feedback correction strategy implemented is as follows: Construct a dynamic adjustment formula based on the abnormal rate: ； Where F_xz represents the dynamic sampling inspection frequency value, Indicates the adjustment coefficient, the value range is 0< <1, Nc represents the number of abnormalities detected in M ​​samplings, and Nc / M represents the abnormality rate.

8. A garment sewing management method based on RFID technology, using any system described in claims 1 to 7, characterized in that: The steps include: S1. Using RFID tags to record material information of target pieces in advance, and using RFID tags to record sewing information during sewing of the target pieces; wherein the material information at least includes the origin, batch, and quality of the target pieces; and the sewing information at least includes sewing force and sewing speed; S2. Based on RFID technology, combined with machine vision monitoring and data analysis and processing, the type of the current sewing process is determined; wherein the types of sewing processes include: Process 1: Single sewing operation process; Process 2: Multiple serial sewing operations; Process three: parallel sewing operation process; S3. According to the sewing process type determined, the simplified processing mechanism is run, the obtained result and the pre-collected operation qualification rate are input into the corresponding complexity calculation model, and the process complexity under the corresponding sewing process type is output; the simplified processing mechanism process is as follows: When the sewing type is straight stitching and curved stitching, the formula used to calculate the difficulty coefficient of straight stitching operation is: , where D1 represents the difficulty coefficient of linear suture operation, Indicates the basic difficulty coefficient, Indicates the complexity adjustment factor corresponding to linear suture; The formula used to calculate the difficulty coefficient of the curve stitching operation is: , where D2 represents the difficulty coefficient of curve stitching operation, Indicates the complexity adjustment factor corresponding to curve stitching; The formula used to calculate the parallel coordination coefficient is as follows: ； ； In the formula, C represents the parallel coordination coefficient, bs represents the number of parallel operations, and pr represents the coordination difficulty factor; S4. In combination with the type and complexity of the corresponding sewing process, a preliminary sampling inspection frequency value is set to provide inspection frequency guidance for semi-finished garments obtained from the corresponding type of sewing process; S5. Perform real-time sampling based on the preliminary sampling inspection frequency value, and perform image recognition in real time within the set sampling times M. When there is no abnormality in the recognition result, execute the established strategy and maintain the original preliminary sampling inspection frequency value to perform real-time sampling; when there is an abnormality in the recognition result, execute the feedback correction strategy to correct the preliminary sampling inspection frequency value.

Images