Textile and clothing design and production process management method and system based on artificial intelligence

Abstract

The present invention discloses a textile and garment design and production process management method and system based on artificial intelligence, belonging to the technical field of garment production management. The method comprises the following steps: analyzing a first complexity index of garment sewing, thereby determining a sewing process risk label; analyzing a garment sewing complexity index based on the sewing process risk label determination result, performing initial sewing work parameter configuration; determining the need for sewing work parameter adjustment; analyzing a sewing process stability index; and adaptively adjusting sewing work parameters in combination with the garment sewing complexity index. The present invention can estimate sewing difficulty and risk in advance, providing an accurate numerical basis for subsequent work, rationally configuring initial sewing work parameters, improving the accuracy of production preparation, and, during the production process, determining the need for parameter adjustment using the production beat variation coefficient, and adaptively adjusting the work parameters, effectively ensuring the stability and continuity of sewing production, improving product quality, and increasing production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of clothing production management, and in particular to a textile clothing design and production process management method and system based on artificial intelligence. Background Art

[0002] With the development of intelligent manufacturing technology, the textile and apparel industry is gradually transforming towards digitalization, informatization, and automation. Currently, a variety of information collection and processing methods have been introduced into the clothing design and production process, including automated cutting, intelligent sewing, and production scheduling optimization, aiming to improve production efficiency, product quality, and flexible response capabilities.

[0003] In recent years, artificial intelligence (AI) technology has been widely used in information processing and decision support within the apparel industry, including image recognition, data modeling, and process prediction. Combining AI with garment sewing process management facilitates intelligent extraction of sewing data, quantitative analysis of complexity indicators, and intelligent adjustment of sewing process parameters, laying the foundation for the refinement and intelligence of garment manufacturing.

[0004] For example, the invention patent announcement with announcement number: CN116485277B discloses an intelligent management system for clothing factories based on big data feature analysis, which includes: an incoming fabric classification module, a fabric surface detection and analysis module, a fabric depth detection and screening module, a cut fabric quality depth analysis module, an incoming fabric comprehensive quality assessment module, a display terminal, and a system background.

[0005] For example, the invention patent announcement with announcement number: CN111368413B discloses a clothing production plan tracking management method and system. By establishing a clothing tracking management model corresponding to a target clothing production plan and simulating the clothing production process when the target clothing production plan is executed, a production distribution map of the target clothing production plan at different production process nodes is obtained, feature extraction is performed on the record information of each production node in the production distribution map, and the record information of each production node is clustered according to the obtained production node record information features of each production node record information and the position information of each production node record information on the production distribution map, a corresponding tracking management map including the clothing tracking distribution information between each clothing type and each clothing style in the target clothing production plan is obtained.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] The current textile and clothing design and production process management methods ignore the close connection between clothing design and production, and often only focus on a single aspect. This may make it difficult to effectively implement the design in the production process, reduce the quality of textile and clothing products, and increase the textile and clothing production cycle. At the same time, it is impossible to detect changes in sewing quality and efficiency in a timely manner, which may lead to a large number of defective products, increased equipment failures, and production stagnation. Summary of the Invention

[0008] The first aspect of the present invention provides a textile and garment design and production process management method based on artificial intelligence, comprising the following steps:

[0009] The control center receives textile and garment sewing information, obtains garment sewing data through artificial intelligence, analyzes the first complexity index of garment sewing, and thereby determines the sewing process risk label.

[0010] Based on the sewing process risk label judgment results, the garment sewing complexity index is analyzed and the initial sewing work parameters are configured accordingly.

[0011] The textile and garment sewing production process is started based on the initial sewing working parameters, the coefficient of variation of the textile and garment sewing production rhythm is obtained, and the need for adjusting the sewing working parameters is determined.

[0012] When the result of the sewing work parameter adjustment demand determination is that sewing work parameter adjustment is required, the sewing production process parameters are collected, the sewing process stability index is analyzed, and the sewing work parameters are adaptively adjusted in combination with the garment sewing complexity index.

[0013] The second aspect of the present invention provides a textile and garment design and production process management system based on artificial intelligence, comprising:

[0014] The sewing process risk label determination module is used to control the center to receive textile and garment sewing information, obtain garment sewing data through artificial intelligence, analyze the first complexity index of garment sewing, and thereby determine the sewing process risk label.

[0015] The initial sewing work parameter configuration module is used to analyze the garment sewing complexity index based on the sewing process risk label judgment results, and thus perform initial sewing work parameter configuration.

[0016] The sewing work parameter adjustment demand determination module is used to start the textile and garment sewing production process based on the initial sewing work parameters, obtain the textile and garment sewing production beat variation coefficient, and determine the sewing work parameter adjustment demand.

[0017] The sewing work parameter adjustment module is used to collect sewing production process parameters, analyze sewing process stability indicators, and perform adaptive adjustment of sewing work parameters in combination with clothing sewing complexity indicators when the sewing work parameter adjustment demand determination result is that sewing work parameter adjustment is required.

[0018] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0019] 1. The AI-based textile and garment design and production process management method provided by this invention can predict sewing difficulty and risk in advance by identifying sewing process risk tags, providing an accurate numerical basis for subsequent work. The method also determines the garment sewing complexity index based on the risk tags, allowing for the rational allocation of initial sewing parameters and improving the accuracy of production preparation. During the production process, the production cycle coefficient of variation is used to determine parameter adjustment requirements, and when necessary, the sewing process stability index is combined to adaptively adjust the working parameters. This effectively ensures the stability and continuity of sewing production, reduces problems such as thread breakage and skipped stitches, and improves product quality and production efficiency.

[0020] 2. The present invention analyzes the sewing complexity index of clothing based on the judgment result of sewing process risk label, which can more accurately evaluate the actual difficulty of sewing work. When it is judged to be a low sewing process risk, the first complexity index is directly used as the sewing complexity index to quickly determine the initial sewing work parameters adapted thereto, thereby improving the production preparation efficiency; if it is judged to be a high sewing process risk, the analysis is combined with the historical sewing data of the clothing, so as to be more in line with the actual production situation, so that the subsequent configured initial sewing work parameters, such as sewing tension and needle speed, are more reasonable and scientific, which helps to improve the sewing quality and ensure the smooth progress of production.

[0021] 3. By adaptively adjusting sewing parameters, the present invention can respond to situations that arise during the sewing process in real time, improving sewing production stability and product quality. When fluctuations in textile and garment sewing production are detected during production, parameters can be adjusted promptly to avoid quality defects caused by unreasonable parameters, ensuring stable and efficient sewing operations and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of the textile and apparel design and production process management method based on artificial intelligence provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the structure of the textile and clothing design and production process management system based on artificial intelligence provided in an embodiment of the present application;

[0024] Figure 3 This is a flow chart of sewing working parameter adjustment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] Reference Figure 1 As shown, the first aspect of the present invention provides a textile and garment design and production process management method based on artificial intelligence, comprising the following steps:

[0027] The control center receives textile and garment sewing information, obtains garment sewing data through artificial intelligence, analyzes the first complexity index of garment sewing, and thereby determines the sewing process risk label.

[0028] In this embodiment, the first complexity index of garment sewing is analyzed, and the specific analysis method is as follows:

[0029] Garment sewing data includes fabric elasticity coefficient, number of stitching, curve sewing ratio and maximum overlapping thickness of layers.

[0030] Textile and garment sewing information includes but is not limited to textile and garment design drawings, technical specifications, process sheets and other sewing information sources.

[0031] The specific steps for obtaining clothing sewing data through artificial intelligence are: constructing a multimodal encoder including an image encoder, a text encoder, a CAD parsing module and a feature fusion layer, inputting textile and clothing sewing information, and outputting clothing sewing data. The image encoder and CAD parsing module use graph neural networks, the text encoder uses a natural language processing model, and the feature fusion layer uses a multi-layer perceptron.

[0032] Analyze the first complexity index of clothing sewing based on clothing sewing data.

[0033] The first complexity index of clothing sewing is a quantitative indicator of the influence of fabric elasticity coefficient, number of splicing, proportion of curve sewing and maximum overlapping thickness of layers on the complexity of clothing sewing. The specific analysis process is: the fabric elasticity coefficient, number of splicing, proportion of curve sewing and maximum overlapping thickness of layers are differentiated with the corresponding reference values, and the differentiation results are coupled with the corresponding allocation factors to obtain the first complexity index of clothing sewing.

[0034] It should be noted that there is an interaction between the elastic coefficient of the fabric, the number of splicing, the proportion of curve sewing and the maximum overlapping thickness of the layers. For example, the elastic coefficient of the fabric affects the splicing and sewing process. Fabrics with high elasticity are more easily deformed during splicing and curve sewing, requiring more sophisticated processes, and the thickness changes are more complicated when multiple layers are overlapped. An increase in the number of splicing will increase the unevenness of the fabric surface and affect the elastic performance. At the same time, an increase in the proportion of curve sewing means higher process difficulty, a greater challenge to the stability of elastic fabrics, and uneven thickness at the overlapping parts. The increase in the maximum overlapping thickness of the layers not only changes the overall physical properties of the fabric, but also affects the operational difficulty and final effect of splicing and sewing. The four factors work together to affect the molding quality and wearing performance of clothing or products.

[0035] The reference fabric elastic coefficient, reference splicing quantity, reference curve sewing ratio and reference layer maximum overlapping thickness stored in the database are extracted.

[0036] Extract the fabric elastic coefficient distribution factor, splicing quantity distribution factor, curve sewing ratio distribution factor and maximum overlapping thickness distribution factor preset in the database.

[0037] It should be noted that the fabric elastic coefficient distribution factor, the splicing number distribution factor, the curve sewing ratio distribution factor and the maximum overlapping thickness distribution factor of the layers are pre-set values ​​in the database, and their value range is between 0 and 1. They can be directly extracted from the database when used. The specific extraction method is, for example: the fabric elastic coefficient, the splicing number, the curve sewing ratio and the maximum overlapping thickness of the layers are respectively mapped to the fabric elastic coefficient distribution factor, the splicing number distribution factor, the curve sewing ratio distribution factor and the maximum overlapping thickness distribution factor to construct a one-to-one mapping set. When used, the fabric elastic coefficient, the splicing number, the curve sewing ratio and the maximum overlapping thickness of the layers obtained in real time are input into the corresponding mapping set, so as to extract the fabric elastic coefficient distribution factor, the splicing number distribution factor, the curve sewing ratio distribution factor and the maximum overlapping thickness distribution factor of the layers.

[0038] In a specific embodiment, the first complexity index of garment sewing is specifically expressed as follows:

[0039] ,

[0040] in, It is the first complexity index of garment sewing. is the elastic coefficient of the fabric, is the number of splicing, is the proportion of curve sewing, is the maximum overlapping thickness of the layers, is the elastic coefficient of the reference fabric, For reference splicing quantity, For reference curve sewing ratio, is the maximum overlapping thickness of the reference layers, Assign a factor to the elastic coefficient of the fabric, Assign a factor for the number of splices, Assign a factor to the curve sewing ratio, Assigns a factor for the maximum overlap thickness of the layers.

[0041] In this embodiment, the sewing process risk label is determined, and the specific analysis process is as follows:

[0042] Extract the preset clothing sewing complexity threshold in the database.

[0043] If the first garment sewing complexity index is less than the garment sewing complexity threshold, the sewing process risk label is recorded as low sewing process risk.

[0044] If the first garment sewing complexity index is less than the garment sewing complexity threshold, this indicates that the combined impact of the fabric elasticity coefficient, number of splices, proportion of curved sewing, and maximum overlap thickness of the layers involved in the current garment sewing process on the complexity of the sewing process is relatively low. In this case, the fabric is easier to splice and sew, the number of splices is small, the fabric surface is relatively flat, and it is easy to process. The low proportion of curved sewing means that most sewing work is more conventional straight-line sewing, which is easy to operate. The maximum overlap thickness of the layers is also within a manageable range and will not significantly increase the sewing difficulty or affect the final result. Therefore, the overall sewing process is less likely to have risks, and the sewing process risk label is recorded as low sewing process risk.

[0045] If the first garment sewing complexity index is greater than or equal to the garment sewing complexity threshold, the sewing process risk label is recorded as high sewing process risk.

[0046] If the first complexity index of garment sewing is greater than or equal to the garment sewing complexity threshold, it means that the fabric has a large elastic coefficient and is extremely easy to deform during splicing and curve sewing, requiring more advanced and sophisticated technology to ensure sewing quality; the increase in the number of splicing makes the surface flatness of the fabric worse, which not only affects the elastic performance, but also increases the difficulty of sewing and the chance of error; the increase in the proportion of curve sewing greatly increases the difficulty of the process, which is a huge test for the stability of the elastic fabric, and will also make the thickness of the overlapping parts more uneven; the increase in the maximum overlapping thickness of the layers changes the overall physical properties of the fabric, making the splicing and sewing operations much more difficult, and may also have an adverse effect on the final molding quality and wearing performance. Therefore, the risk of various problems occurring during the sewing process is relatively high, so the sewing process risk label is recorded as high sewing process risk.

[0047] Based on the sewing process risk label judgment results, the garment sewing complexity index is analyzed and the initial sewing work parameters are configured accordingly.

[0048] In this embodiment, the garment sewing complexity index is analyzed based on the sewing process risk label determination result. The specific process is as follows:

[0049] When the sewing process risk label is low sewing process risk, the first clothing sewing complexity index is marked as the clothing sewing complexity index.

[0050] When the sewing process risk label is high sewing process risk, artificial intelligence is used to obtain the historical sewing data of the clothing corresponding to the textile and clothing sewing information, and the historical sewing risk score of the clothing is analyzed.

[0051] The garment sewing complexity correction value corresponding to each garment sewing first complexity index interval stored in the database is extracted, and the garment sewing complexity correction value corresponding to the interval where the garment sewing first complexity index is located is mapped and extracted.

[0052] The second complexity index of clothing sewing is analyzed according to the clothing historical sewing risk score and the clothing sewing complexity correction value, which is specifically expressed as the numerical result of multiplying the clothing historical sewing risk score by the clothing sewing complexity correction value as the second complexity index of clothing sewing.

[0053] The second garment sewing complexity index is marked as the garment sewing complexity index.

[0054] In this embodiment, the garment sewing history risk score is analyzed in the following specific process:

[0055] The historical sewing data of clothing includes the historical processing failure rate, historical rework rate and historical downtime frequency of clothing.

[0056] It's important to note that the historical processing failure rate, historical rework rate, and historical downtime frequency influence and correlate with each other. A high historical processing failure rate indicates a high number of defective or substandard products in past production, which often requires rework, leading to an increase in the historical rework rate. Frequent processing failures and reworks of products constantly subject equipment to high loads or abnormal operating conditions, increasing the probability of equipment failure and leading to an increase in the historical downtime frequency. Furthermore, a high historical downtime frequency interrupts the production process, impacting the continuity of product processing. This can lead to increased errors during processing, further increasing the historical processing failure rate. It can also cause normal processing tasks to need to be readjusted due to interruptions, increasing the likelihood of rework and further increasing the historical rework rate. These three factors collectively reflect stability and efficiency issues in the garment sewing production process.

[0057] Analyze clothing historical sewing risk scores based on clothing historical sewing data.

[0058] The historical sewing risk score of clothing is a quantitative indicator of the degree of impact of the historical processing failure rate, historical rework rate and historical downtime frequency of clothing on the historical sewing risk of clothing. The specific analysis process is: the historical processing failure rate, historical rework rate and historical downtime frequency of clothing are differentiated from the corresponding reference values, and the differentiation results are coupled with the corresponding allocation factors to analyze and obtain the historical sewing risk score of clothing.

[0059] The reference historical machining failure rate, the reference historical rework rate, and the reference historical downtime frequency stored in the database are extracted.

[0060] Extract the historical processing failure rate allocation factor, historical rework rate allocation factor and historical downtime frequency allocation factor preset in the database.

[0061] It should be added that the historical processing failure rate allocation factor, the historical rework rate allocation factor and the historical downtime frequency allocation factor are all pre-set values ​​in the database, and their specific value ranges are all from 0 to 1. They can be directly extracted from the database when used. The extraction method is, for example: the historical processing failure rate, the historical rework rate and the historical downtime frequency are respectively mapped to the historical processing failure rate allocation factor, the historical rework rate allocation factor and the historical downtime frequency allocation factor to construct a one-to-one mapping set. When used, the real-time historical processing failure rate, the historical rework rate and the historical downtime frequency are input into the corresponding mapping set, thereby extracting the historical processing failure rate allocation factor, the historical rework rate allocation factor and the historical downtime frequency allocation factor.

[0062] In a specific embodiment, the garment sewing history risk score is specifically expressed as follows:

[0063] ,

[0064] in, Score the historical sewing risk of the garment, is the historical processing failure rate of the garment, is the historical rework rate of garments, is the historical downtime frequency of the garment, For reference to historical processing failure rates, For reference to historical rework rates, For reference to historical outage frequencies, Assign a factor to the historical machining failure rate, is the historical rework rate allocation factor, Assign a factor to the historical outage frequency.

[0065] In this embodiment, the initial sewing working parameter configuration is performed, and the specific analysis process is as follows:

[0066] The sewing working parameters corresponding to each garment sewing complexity index interval stored in the database are extracted, and the sewing working parameters corresponding to the interval where the garment sewing complexity index is located are mapped and recorded as initial sewing working parameters.

[0067] It should be noted that the greater the garment sewing complexity index, the more difficult it is to sew the garment. For example, the fabric may be more elastic and more easily deformed, the large number of splicing may lead to uneven fabric, the high proportion of curved sewing may increase the difficulty of the process, and the large maximum overlapping thickness of the layers may affect the operation and effect. In order to ensure sewing quality, avoid problems such as thread breakage, stitch skipping, and uneven sewing, and ensure the smooth progress of the sewing process, the corresponding extracted garment sewing tension and garment sewing needle speed are higher. Higher sewing tension can better control the position of the fabric during the sewing process and prevent it from being displaced due to problems such as elasticity or splicing. Higher sewing needle speed can improve production efficiency and complete sewing operations in a timely manner when faced with complex sewing tasks to meet the requirements of complex sewing processes.

[0068] The initial sewing working parameters include garment sewing tension and garment sewing needle speed.

[0069] Perform initial sewing working parameter configuration according to the initial sewing working parameters.

[0070] It should be added that, in a specific embodiment, after obtaining the initial sewing working parameters, the initial sewing working parameters are written into the device through an automatic writing device, and a low-speed operation test is started according to the test rules pre-set in the database. After confirming that there is no thread breakage or shifting fault, a configuration completion information is generated to confirm that the configuration is successful.

[0071] It should also be added that if a wire breakage and displacement fault occurs after starting the low-speed operation test, the parameter configuration will be stopped and a prompt message will be generated.

[0072] The automatic writing device may be an MES system (Manufacturing Execution System).

[0073] The textile and garment sewing production process is started based on the initial sewing working parameters, the coefficient of variation of the textile and garment sewing production rhythm is obtained, and the need for adjusting the sewing working parameters is determined.

[0074] In this embodiment, the specific analysis process for determining the need for adjusting sewing parameters is as follows:

[0075] During a preset monitoring period, the sewing production rhythm of textiles and garments is monitored at a monitoring frequency preset in a database to obtain the sewing production rhythm of each textile and garment.

[0076] Based on the sewing production rhythm of each textile and garment, the standard deviation and mean of the sewing production rhythm of textile and garment are obtained.

[0077] The numerical result of dividing the standard deviation of textile and garment sewing production rhythm by the mean of textile and garment sewing production rhythm is taken as the coefficient of variation of textile and garment sewing production rhythm.

[0078] Extract the sewing production beat variation coefficient threshold preset in the database.

[0079] If the coefficient of variation of the textile and garment sewing production beat is less than the threshold value of the coefficient of variation of the sewing production beat, the sewing work parameter adjustment demand determination result is recorded as no need for sewing work parameter adjustment.

[0080] If the coefficient of variation of the sewing production rhythm of textile and garments is less than the threshold value of the coefficient of variation of the sewing production rhythm, it means that the sewing production process is running stably, the existing sewing working parameters can better adapt to the production needs, and the production rhythm will not fluctuate greatly due to unreasonable parameters. Therefore, in this case, it is determined that there is no need to adjust the sewing working parameters to maintain the current stable production state and ensure the stability of production efficiency and product quality.

[0081] See Figure 3 The figure shows a flow chart of the adjustment of sewing parameters involved in an embodiment of the present invention. When it is determined that there is a "demand for adjustment of sewing parameters", the process begins to enter the adaptive adjustment stage. First, the process stability correction factor corresponding to the interval of the current garment sewing complexity index is extracted. Subsequently, the system obtains the sewing process stability index in the current production, combines the index with the correction factor, calculates the stability correction index, and determines whether the correction index is greater than the threshold set by the system. If it is greater than the threshold, it means that the sewing process stability is good and no parameter adjustment is required. The original sewing parameters are maintained and production continues. If it is less than or equal to the threshold, it indicates that the current sewing stability is insufficient and parameter adjustment is required. The sewing process stability correction deviation index is further analyzed to extract the sewing work adjustment parameters, including the tension adjustment value and the needle speed adjustment value. Adaptive adjustment is then performed to complete the adjustment of the sewing work parameters for this time.

[0082] If the textile garment sewing production beat variation coefficient is greater than or equal to the sewing production beat variation coefficient threshold, the sewing work parameter adjustment demand determination result is recorded as the required sewing work parameter adjustment.

[0083] If the coefficient of variation of the sewing production rhythm of textile and garments is greater than or equal to the threshold value of the coefficient of variation of the sewing production rhythm, it means that the sewing production rhythm has fluctuated greatly. In order to restore the stability of the production process and ensure product quality and production efficiency, it is necessary to adjust the sewing working parameters. By adjusting the parameters to adapt to the changes in the production process and solve the problem of unstable production rhythm, it is determined that the sewing working parameters need to be adjusted.

[0084] When the result of the sewing work parameter adjustment demand determination is that sewing work parameter adjustment is required, the sewing production process parameters are collected, the sewing process stability index is analyzed, and the sewing work parameters are adaptively adjusted in combination with the garment sewing complexity index.

[0085] In this embodiment, the sewing process stability index is analyzed, and the specific analysis steps are as follows:

[0086] Sewing production process parameters include thread breakage rate, stitch skipping rate, rework rate and needle speed stability.

[0087] It should be noted that sewing production process parameters can be extracted from the MES system (Manufacturing Execution System).

[0088] It's important to note that the thread breakage rate, stitch skipping rate, and rework rate are closely related and mutually influential to needle speed stability. Poor needle speed stability leads to unstable operation of sewing equipment, which can easily cause thread breakage and stitch skipping, increasing these rates. Thread breakage and stitch skipping directly result in sewing quality defects, requiring rework of these defective products, which in turn increases the rework rate. Conversely, a high rework rate means the sewing process is frequently interrupted and restarted, requiring the equipment to repeatedly adjust its operating state. This further affects needle speed stability, causing greater needle speed fluctuations and further increasing the likelihood of thread breakage and stitch skipping.

[0089] Analyze sewing process stability indicators based on sewing production process parameters.

[0090] The sewing process stability index is a quantitative indicator of the degree of influence of the thread breakage rate, skipped stitch rate, rework rate and needle speed stability on the sewing process stability. The specific analysis process is as follows: the reference values ​​of the thread breakage rate, skipped stitch rate and rework rate are differentiated from the thread breakage rate, skipped stitch rate and rework rate respectively, the needle speed stability is differentiated from the reference value, and the differentiation result is coupled with the corresponding distribution coefficient to obtain the sewing process stability index.

[0091] The reference thread breakage rate, reference stitch skipping rate, reference rework rate and reference needle speed stability stored in the database are extracted.

[0092] Extract the thread breakage rate distribution coefficient, stitch skipping rate distribution coefficient, rework rate distribution coefficient and needle speed stability distribution coefficient preset in the database.

[0093] It should be noted that the thread breakage rate distribution coefficient, stitch skipping rate distribution coefficient, rework rate distribution coefficient and needle speed stability distribution coefficient are all pre-set values ​​in the database, and their specific value ranges are all from 0 to 1. They can be directly extracted from the database when used. The extraction method is, for example: constructing a one-to-one mapping set of the thread breakage rate, stitch skipping rate, rework rate and needle speed stability with the thread breakage rate distribution coefficient, stitch skipping rate distribution coefficient, rework rate distribution coefficient and needle speed stability distribution coefficient respectively. When used, the thread breakage rate, stitch skipping rate, rework rate and needle speed stability obtained in real time are input into the corresponding mapping set, thereby extracting the thread breakage rate distribution coefficient, stitch skipping rate distribution coefficient, rework rate distribution coefficient and needle speed stability distribution coefficient.

[0094] In a specific embodiment, the sewing process stability index is specifically expressed as:

[0095] ,

[0096] in, It is an indicator of sewing process stability. is the disconnection rate, is the stitch skipping rate, is the rework rate, is the needle speed stability, is the reference disconnection rate, For reference stitch skipping rate, For reference rework rate, is the reference needle speed stability, is the disconnection rate distribution coefficient, is the stitch skipping rate distribution coefficient, is the heavy work rate allocation coefficient, is the needle speed stability distribution coefficient.

[0097] In this embodiment, the sewing parameters are adaptively adjusted, and the specific analysis steps are as follows:

[0098] The process stability correction factor corresponding to each garment sewing complexity index interval stored in the database is extracted, and the process stability correction factor corresponding to the interval where the garment sewing complexity index is located is mapped and recorded as the sewing process stability correction factor.

[0099] It should be noted that the greater the garment sewing complexity index, the higher the difficulty faced in sewing the garment, and the corresponding extracted sewing process stability correction factor is larger. A larger correction factor can more effectively adjust the sewing process stability index, and compensate and correct the unstable factors in the sewing process to a greater extent, thereby maintaining the stability of the sewing process and ensuring the sewing quality of the product.

[0100] The sewing process stability correction index is analyzed based on the sewing process stability index and the sewing process stability correction factor. Specifically, the sewing process stability index is multiplied by the sewing process stability correction factor to obtain the numerical result as the sewing process stability correction index.

[0101] Extract the sewing process stability correction threshold preset in the database.

[0102] If the sewing process stability correction index is greater than the sewing process stability correction threshold, the self-adaptive adjustment of the sewing working parameters is not performed.

[0103] If the sewing process stability correction index is less than or equal to the sewing process stability correction threshold, the sewing process stability correction index is subtracted from the sewing process stability correction threshold to obtain the sewing process stability correction deviation index.

[0104] The adjustment parameters corresponding to each sewing process stability correction deviation index interval stored in the database are extracted, and the adjustment parameters corresponding to the interval where the sewing process stability correction deviation index is located are mapped and extracted, and recorded as sewing work adjustment parameters.

[0105] It should be noted that a larger sewing process stability correction deviation index indicates a greater gap between the current sewing process stability correction index and the preset sewing process stability correction threshold. This indicates a significant deviation from the ideal sewing process stability, likely leading to frequent thread breakage, skipped stitches, rework, or poor needle speed stability. To restore the sewing process to a stable state and ensure sewing quality and production efficiency, significant adjustments to the sewing parameters are necessary. The corresponding extracted garment sewing tension adjustment value and garment sewing needle speed adjustment value are both negative, and the larger the absolute value, the greater the negative value. This is because negative adjustments mean reducing the current sewing tension and needle speed. When these instabilities occur, reducing sewing tension can prevent excessive tension from causing excessive fabric stretching and thread breakage. Reducing sewing needle speed can also stabilize equipment operation, reducing skipped stitches and unstable needle speed caused by high-speed operation, thereby improving the sewing process and stabilizing it.

[0106] Sewing work adjustment parameters include clothing sewing tension adjustment value and clothing sewing needle speed adjustment value.

[0107] The sewing working parameters are adaptively adjusted based on the initial sewing working parameters and the sewing working adjustment parameters, specifically: the numerical result of the garment sewing tension plus the garment sewing tension adjustment value is used as the current garment sewing tension, and the numerical result of the garment sewing needle speed plus the garment sewing needle speed adjustment value is used as the current garment sewing needle speed.

[0108] See Figure 2As shown, the second aspect of the present invention provides a textile and garment design and production process management system based on artificial intelligence, comprising:

[0109] The sewing process risk label determination module is used to control the center to receive textile and garment sewing information, obtain garment sewing data through artificial intelligence, analyze the first complexity index of garment sewing, and thereby determine the sewing process risk label.

[0110] The initial sewing work parameter configuration module is used to analyze the garment sewing complexity index based on the sewing process risk label judgment results, and thus perform initial sewing work parameter configuration.

[0111] The sewing work parameter adjustment demand determination module is used to start the textile and garment sewing production process based on the initial sewing work parameters, obtain the textile and garment sewing production beat variation coefficient, and determine the sewing work parameter adjustment demand.

[0112] The sewing work parameter adjustment module is used to collect sewing production process parameters, analyze sewing process stability indicators, and perform adaptive adjustment of sewing work parameters in combination with clothing sewing complexity indicators when the sewing work parameter adjustment demand determination result is that sewing work parameter adjustment is required.

[0113] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0117] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0118] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The textile and clothing design and production process management method based on artificial intelligence is characterized by: The following steps are involved: The control center receives textile and garment sewing information, obtains garment sewing data through artificial intelligence, analyzes the first complexity index of garment sewing, and thereby determines the sewing process risk label; Analyze the garment sewing complexity index based on the sewing process risk label judgment results, and configure the initial sewing work parameters accordingly; Starting the textile and garment sewing production process based on the initial sewing working parameters, obtaining the coefficient of variation of the textile and garment sewing production rhythm, and determining the need for adjusting the sewing working parameters; When the result of the sewing work parameter adjustment demand determination is that the sewing work parameter adjustment is required, the sewing production process parameters are collected, the sewing process stability index is analyzed, and the sewing work parameters are adaptively adjusted in combination with the garment sewing complexity index; The specific process of analyzing the garment sewing complexity index based on the sewing process risk label determination result is as follows: When the sewing process risk label is low sewing process risk, the first garment sewing complexity index is marked as the garment sewing complexity index; When the sewing process risk label is high, artificial intelligence is used to obtain the historical sewing data of the textile and garment sewing information, and the historical sewing risk score of the garment is analyzed; Extracting the garment sewing complexity correction value corresponding to each garment sewing first complexity index interval stored in the database, and mapping and extracting the garment sewing complexity correction value corresponding to the interval where the garment sewing first complexity index is located; Analyze the second complexity index of clothing sewing according to the clothing historical sewing risk score and clothing sewing complexity correction value; The second complexity index of garment sewing is marked as the garment sewing complexity index; The self-adaptive adjustment of sewing parameters is carried out, and the specific analysis steps are as follows: Extracting the process stability correction factor corresponding to each garment sewing complexity index interval stored in the database, and mapping the extracted process stability correction factor corresponding to the interval where the garment sewing complexity index is located, and recording it as the sewing process stability correction factor; Analyze the sewing process stability correction index based on the sewing process stability index and the sewing process stability correction factor; Extracting the sewing process stability correction threshold preset in the database; If the sewing process stability correction index is greater than the sewing process stability correction threshold, the self-adaptive adjustment of the sewing working parameters is not performed; If the sewing process stability correction index is less than or equal to the sewing process stability correction threshold, subtracting the sewing process stability correction index from the sewing process stability correction threshold to obtain a sewing process stability correction deviation index; Extracting the adjustment parameters corresponding to each sewing process stability correction deviation index interval stored in the database, and mapping the extracted adjustment parameters corresponding to the interval in which the sewing process stability correction deviation index is located, and recording them as sewing work adjustment parameters; The sewing work adjustment parameters include clothing sewing tension adjustment value and clothing sewing needle speed adjustment value; The sewing working parameters are adaptively adjusted based on the initial sewing working parameters and the sewing working adjustment parameters.

2. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, characterized in that: The specific analysis method for analyzing the first complexity index of garment sewing is as follows: The garment sewing data includes fabric elastic coefficient, number of stitching, curve sewing ratio and maximum overlapping thickness of layers; Analyze the first complexity index of garment sewing based on garment sewing data; The first complexity index of clothing sewing is a quantitative indicator of the influence of the elastic coefficient of the fabric, the number of splicing, the proportion of curved sewing and the maximum overlapping thickness of the layers on the complexity of clothing sewing. The specific analysis process is: the elastic coefficient of the fabric, the number of splicing, the proportion of curved sewing and the maximum overlapping thickness of the layers are differentiated with the corresponding reference values, and the differentiation processing results are coupled with the corresponding allocation factors to obtain the first complexity index of clothing sewing.

3. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, characterized in that: The specific analysis process for determining the sewing process risk label is as follows: Extracting the garment sewing complexity threshold preset in the database; If the first garment sewing complexity index is less than the garment sewing complexity threshold, the sewing process risk label is recorded as low sewing process risk; If the first garment sewing complexity index is greater than or equal to the garment sewing complexity threshold, the sewing process risk label is recorded as high sewing process risk.

4. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, characterized in that: The specific analysis process of the clothing history sewing risk score is as follows: The historical sewing data of the garments include the historical processing failure rate, historical rework rate and historical downtime frequency of the garments; Analyze clothing historical sewing risk scores based on clothing historical sewing data; The clothing historical sewing risk score is a quantitative indicator of the degree of impact of the clothing's historical processing failure rate, historical rework rate, and historical downtime frequency on the clothing's historical sewing risk. The specific analysis process is: the clothing's historical processing failure rate, historical rework rate, and historical downtime frequency are differentiated from the corresponding reference values, and the differentiation results are coupled with the corresponding allocation factors to analyze and obtain the clothing's historical sewing risk score.

5. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, wherein: The initial sewing working parameter configuration is performed, and the specific analysis process is as follows: Extracting sewing working parameters corresponding to each garment sewing complexity index interval stored in the database, and mapping and extracting the sewing working parameters corresponding to the interval where the garment sewing complexity index is located, and recording them as initial sewing working parameters; The initial sewing working parameters include garment sewing tension and garment sewing needle speed; Perform initial sewing working parameter configuration according to the initial sewing working parameters.

6. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, characterized in that: The specific analysis process for determining the adjustment requirements of sewing parameters is as follows: During the preset monitoring period, the sewing production rhythm of textiles and garments is monitored at the monitoring frequency preset in the database to obtain the sewing production rhythm of each textile and garment; Based on the sewing production rhythm of each textile and garment, the standard deviation and mean of the sewing production rhythm of the textile and garment are obtained; The coefficient of variation of textile and garment sewing production rhythm is obtained by dividing the standard deviation of textile and garment sewing production rhythm by the mean value of textile and garment sewing production rhythm. Extracting the sewing production beat variation coefficient threshold value preset in the database; If the coefficient of variation of the textile and garment sewing production beat is less than the threshold value of the coefficient of variation of the sewing production beat, the result of the determination of the need for adjustment of the sewing work parameters is recorded as no need for adjustment of the sewing work parameters; If the textile garment sewing production beat variation coefficient is greater than or equal to the sewing production beat variation coefficient threshold, the sewing work parameter adjustment demand determination result is recorded as the required sewing work parameter adjustment.

7. The method for managing textile and garment design and production processes based on artificial intelligence according to claim 1, characterized in that: The specific analysis steps for analyzing the sewing process stability index are as follows: The sewing production process parameters include thread breakage rate, stitch skipping rate, rework rate and needle speed stability; Analyze sewing process stability index based on sewing production process parameters; The sewing process stability index is a quantitative indicator of the degree of influence of the thread breakage rate, skipped stitch rate, rework rate and needle speed stability on the sewing process stability. The specific analysis process is: the reference values ​​of the thread breakage rate, skipped stitch rate and rework rate are differentiated from the thread breakage rate, skipped stitch rate and rework rate respectively, the needle speed stability is differentiated from the reference value, and the differentiation processing result is coupled with the corresponding distribution coefficient to obtain the sewing process stability index.

8. A system for applying the method for textile and garment design and production process management based on artificial intelligence as described in any one of claims 1 to 7, characterized in that: include: The sewing process risk label determination module is used to control the center to receive textile and garment sewing information, obtain garment sewing data through artificial intelligence, analyze the first complexity index of garment sewing, and determine the sewing process risk label; An initial sewing work parameter configuration module is used to analyze the garment sewing complexity index based on the sewing process risk label determination results, and thereby configure the initial sewing work parameters; A sewing work parameter adjustment demand determination module is used to start the textile and garment sewing production process based on the initial sewing work parameters, obtain the textile and garment sewing production beat variation coefficient, and determine the need for sewing work parameter adjustment; The sewing work parameter adjustment module is used to collect sewing production process parameters, analyze sewing process stability indicators, and perform adaptive adjustment of sewing work parameters in combination with clothing sewing complexity indicators when the sewing work parameter adjustment demand determination result is that sewing work parameter adjustment is required.

Images