Intelligent embroidery customization production system and method

Abstract

The invention relates to the technical field of closed-loop control, and discloses an intelligent embroidery customization production system and method, and the system comprises a personalized demand processing module, an intelligent scheme construction module, a production scheduling optimization module, a quality regulation and control module, a closed-loop optimization module, and a digital billboard module. Acquiring personalized demand data of patterns, colors and sizes through a user demand interaction module; dynamically planning a production task sequence through an intelligent scheduling algorithm in combination with order priority and resource state; the stitch density, the stitch consistency and the color deviation index are monitored in real time through the multi-area step-by-step detection technology; when the quality index deviates from a preset threshold value, a parameter adjustment mechanism is automatically triggered to optimize equipment parameters; and finally, a user capability portrait is constructed through a self-adaptive optimization module, and the design efficiency and the production quality are iteratively improved. According to the method, the precision of a customized scheme and the user satisfaction are improved, the order delivery timeliness is guaranteed, the resource utilization rate is optimized, and the rework rate and raw material loss are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of closed-loop control, in particular to an intelligent custom production system and method for embroidered products. BACKGROUND

[0002] Closed-loop control is a basic concept of control theory, which refers to a control relationship in which the output as the controlled quantity returns to the input as the controlled quantity in a certain way and exerts a control influence on the input. It is a system control method with feedback information. When the operator starts the system, the control information is transmitted to the controlled object through system operation, and the state information of the controlled object is fed back to the input to correct the operation process, so that the output of the system meets the expected requirements. Closed-loop control is a relatively flexible and high-performance control method. Most control methods in industrial production adopt the design of closed-loop control. An intelligent custom production system for embroidered products is a complex system based on closed-loop control, aiming to improve the efficiency and quality of custom production of embroidered products.

[0003] At present, due to the involvement of multiple complex processes in the production of embroidered products, it is not possible to generate a design scheme that meets the changing requirements of users in real time when processing personalized needs. If the user modifies the pattern or color preference during the process, it may cause frequent design iteration and cannot guarantee production efficiency.

[0004] Therefore, the present application provides an intelligent custom production system and method for embroidered products to solve the above problems. SUMMARY

[0005] (I) Technical problems to be solved In view of the deficiencies of the prior art, the present application provides an intelligent custom production system and method for embroidered products to solve the problems raised in the background art.

[0006] (II) Technical solutions To achieve the above purpose, the present application provides the following technical solutions: an intelligent custom production system and method for embroidered products, comprising: A personalized demand processing module acquires user requirements through a pattern element acquisition unit, a color element acquisition unit, and a size element acquisition unit, and generates a personalized demand data package through a demand fusion processing unit; An intelligent scheme construction module receives the demand data package, analyzes key features through a demand feature extraction unit, outputs an initial design scheme using a scheme generation algorithm unit, and shows the user interaction through a scheme preview unit; A production scheduling optimization module receives the final scheme confirmed by the user, decomposes production parameters through an order element analysis unit, analyzes the state of equipment and materials through a resource monitoring unit, generates a production task sequence through a scheduling algorithm optimization unit, and assigns embroidery machine operation instructions through a task arrangement unit. A quality regulation module, which monitors production indexes in real time through a stitch quality acquisition unit and a color matching precision acquisition unit, compares preset threshold values by using a deviation analysis unit, and outputs device adjustment instructions via a parameter self-adaptive unit; A closed-loop optimization module, which receives adjustment instructions from the quality regulation module, constructs a data matrix by using a production history analysis unit, identifies efficiency bottlenecks by using a trend prediction unit, and outputs parameter optimization instructions to an intelligent scheme construction module and a production scheduling optimization module via a strategy generation unit; A digital dashboard module, which integrates production full-link data, calculates quality scores and efficiency coefficients by using a multi-dimensional index fusion unit, and generates dynamic evaluation reports via a visualization unit.

[0007] Preferably, the method comprises the following steps: S1, collecting personalized demand information of the user for the embroidered product through a user demand interaction module, the personalized demand information including pattern demand, color demand and size demand; S2, generating multiple design schemes meeting the user's demand based on the personalized demand information by using an intelligent design module; S3, intelligently planning the production process of the embroidered product and arranging the working tasks of the embroidery machine equipment according to the design scheme and order information by using a production scheduling module; S4, monitoring production quality indexes in real time by using a quality monitoring module during the production process of the embroidered product, and generating quality monitoring data; S5, outputting the finished embroidered product when the quality monitoring data meets the preset standard, and performing production parameter adjustment processing when the quality monitoring data does not meet the preset standard, and generating adjusted production data; S6, executing the production task of the embroidered product based on the adjusted production data or the original production data, and outputting the customized embroidered product; S7, storing the production data of the customized embroidered product and the user demand information into a database to generate production history record data.

[0008] Preferably, the S1 comprises the following steps: S11, receiving pattern demand information input by the user through an online design platform, the pattern demand information including embroidery theme, style and complexity; S12, receiving color demand information selected by the user through the online design platform, the color demand information including main color tone, auxiliary color tone and gradient parameter; S13, receiving size demand information set by the user through the online design platform, the size demand information including length, width and shape ratio; S14, combining and processing the pattern demand information, color demand information and size demand information to generate a personalized demand information data package.

[0009] Preferably, S2 comprises the following steps: S21, obtaining the personalized demand information data packet; S22, using a deep learning algorithm to analyze and process the personalized demand information data packet, and extracting key design features; S23, generating a plurality of design schemes based on the key design features and combining big data analysis, the design schemes including pattern sketches, color schemes, and size layouts; dimensionless normalization processing is performed on the design features to ensure that all feature values are within the range of [0, 1], and a design scheme formula is generated: ; wherein, is a generated design scheme vector, a multidimensional real number vector without dimension, is a weight coefficient of the i-th design feature, 0≤ ≤1, the threshold value is at least 0 and at most 1, is a normalized i-th feature value, 0≤ ≤1, the threshold value is at least 0 and at most 1, is a bias adjustment constant, a real number without dimension, the threshold value is -0.5≤ ≤0.5, is the total number of features, an integer, the threshold value ≥1, by default =3; S24, displaying the plurality of design schemes to the user through an online design platform for the user to select or modify.

[0010] Preferably, S3 comprises the following steps: S31, obtaining the final design scheme selected by the user and order information, the order information including production quantity, delivery time, and priority; S32, based on the final design scheme and the order information, analyzing production resource status, the production resource status including embroidery machine availability, material inventory, and personnel configuration; S33, using an intelligent scheduling algorithm to plan a production process and generate a production task sequence, the production task sequence including equipment allocation, time nodes, and task priority; S34, arranging the work tasks of the embroidery machine equipment according to the production task sequence, and generating production scheduling instructions.

[0011] Preferably, S4 comprises the following steps: S41, during the execution of the work tasks by the embroidery machine equipment, real-time collection of production quality indicators, the production quality indicators including stitch density, stitch consistency, and color deviation; S42, compare the production quality index with a preset standard value to generate quality deviation data; S43, when the quality deviation data is within a preset threshold, output the quality monitoring data as qualified; S44, when the quality deviation data exceeds the preset threshold, output the quality monitoring data as unqualified.

[0012] Preferably, S5 comprises the following steps: S51, when the quality monitoring data is unqualified, analyze the quality deviation reason to generate a deviation analysis report; S52, based on the deviation analysis report, adjust the parameters of the embroidery machine equipment, including needle speed, tension or wire type; S53, generate adjusted production data using an optimization algorithm, the adjusted production data including updated production task sequence and equipment parameters; The deviation coefficient is dimensionally normalized to ensure that the coefficient is within the range [0, 1], and the parameter adjustment formula is: ; Wherein, is the adjusted parameter value, a real number, is the original parameter value, a real number, a dimensionless base value, is the base scaling factor, 0.5 ≤2, threshold minimum 0.5, maximum 2, is the normalized deviation influence coefficient, 0 ≤1, threshold minimum 0, maximum 1, is the deviation correction factor, 0 ≤1, threshold minimum 0.01, maximum 1; S54, when the quality monitoring data is qualified, directly use the original production data to continue the production process.

[0013] Preferably, S6 comprises the following steps: S61, based on the adjusted production data or the original production data, control the embroidery machine equipment to execute the production task; S62, during task execution, real-time monitor the equipment state to generate an equipment operation log; S63, when the equipment state is abnormal, automatically switch to a backup equipment or adjust the production task; S64, after completing the production task, output the customized embroidered product finished product and perform quality re-inspection.

[0014] Preferably, S7 comprises the following steps: S71, collect the production data of the customized embroidered product, including production time, resource consumption and quality index; S72, collecting user demand information and final design scheme; S73, combining and storing the production data, user demand information and final design scheme to a cloud database; S74, generating production history record data for big data analysis and production optimization.

[0015] Preferably, the method further comprises the steps of: S8, based on the production history record data, using a machine learning algorithm to optimize the intelligent design module and the production scheduling module to generate optimization parameters; S9, applying the optimization parameters to the subsequent production process to improve the efficiency and quality consistency of customized production.

[0016] (Three) beneficial effects Compared with the prior art, the present application provides an intelligent embroidered product customized production system and method, which has the following beneficial effects: 1. In the present application, the deep learning algorithm is used to fuse the pattern, color and size demand characteristics to automatically generate diversified design schemes, ensuring the conversion efficiency of user demand; at the same time, the design weight is dynamically optimized according to the user demand, which can respond to the change of user design preference in real time, avoid production delay caused by repeated iteration of design, and improve the accuracy of customized scheme and user satisfaction.

[0017] 2. In the present application, the resource monitoring unit is used to track the embroidery machine state and material inventory in real time, and the intelligent scheduling algorithm is used to dynamically plan the task sequence; when high-priority orders conflict, the equipment allocation strategy is automatically adjusted to correct the task allocation deviation in real time, solve the problems of equipment idling and production delay, guarantee the order delivery time and optimize the resource utilization rate.

[0018] 3. In the present application, the multi-region hierarchical detection technology is used to synchronously analyze the stitch density, stitch consistency and color deviation parameters, and the multi-dimensional index abnormality is judged in real time according to the preset standard value; when local quality deviation is detected, the parameter adaptive unit is automatically triggered to adjust the needle speed and tension in stages, avoiding the overall production quality fluctuation, improving the product pass rate, and reducing the rework rate and raw material loss. BRIEF DESCRIPTION OF DRAWINGS

[0019] Fig. 1 It is a schematic diagram of the framework of the intelligent embroidered product customized production system and method of the present application; Fig. 2 It is a step flow chart of the intelligent embroidered product customized production system and method of the present application. DETAILED DESCRIPTION

[0020] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0021] Please refer to Figs. 1-2 A specific example of an intelligent embroidery product customization production system and method is as follows: Comprise: The personalized demand processing module acquires user demand through the pattern element acquisition unit, the color element acquisition unit, and the size element acquisition unit, and generates a personalized demand data packet via the demand fusion processing unit; The intelligent scheme construction module receives the demand data packet, analyzes key features through the demand feature extraction unit, outputs an initial design scheme using the scheme generation algorithm unit, and shows the user interaction through the scheme preview unit; The production scheduling optimization module receives the final scheme confirmed by the user, decomposes production parameters through the order element analysis unit, analyzes the state of equipment and materials using the resource monitoring unit, generates a production task sequence through the scheduling algorithm optimization unit, and assigns embroidery machine operation instructions through the task arrangement unit; The quality control module monitors production indicators in real time through the stitch quality acquisition unit and the color matching precision acquisition unit, compares the preset threshold value using the deviation analysis unit, and outputs device adjustment instructions via the parameter self-adaptive unit; The closed-loop optimization module receives the adjustment instructions from the quality control module, constructs a data matrix through the production history analysis unit, identifies efficiency bottlenecks using the trend prediction unit, and outputs parameter optimization instructions to the intelligent scheme construction module and the production scheduling optimization module through the strategy generation unit; The digital dashboard module integrates production full-link data, calculates quality scores and efficiency coefficients through the multi-dimensional index fusion unit, and generates dynamic evaluation reports through the visualization unit; The method comprises the following steps: S1, collecting user's individualized demand information for embroidery products through the user demand interaction module, the individualized demand information including pattern demand, color demand and size demand; S2, based on the individualized demand information, generating multiple design schemes meeting the user's demand using the intelligent design module; S3, intelligently planning the embroidery product production process and arranging the work tasks of the embroidery machine equipment according to the design scheme and the order information through the production scheduling module; S4, in the embroidery product production process, monitoring production quality indicators in real time using the quality monitoring module to generate quality monitoring data; S5, output the embroidery product when the quality monitoring data meets the preset standard; when the quality monitoring data does not meet the preset standard, perform production parameter adjustment processing to generate adjusted production data; S6, execute the embroidery production task based on the adjusted production data or the original production data, and output the customized embroidery product; S7, store the production data of the customized embroidery product and the user demand information to the database to generate production history record data; S11, receive the pattern demand information input by the user through the online design platform, the pattern demand information including embroidery theme, style and complexity; S12, receive the color demand information selected by the user through the online design platform, and process using a dimensionless normalization demand fusion formula: ; wherein, is a normalized fusion color value, 0≤ ≤1, is a kth color weight, =1 (k=1,2,3), is an original color parameter value, is a lower limit of the color parameter, =0, is an upper limit of the color parameter, =255; S13, receive the size demand information set by the user through the online design platform, the size demand information including length, width and shape ratio; S14, combine and process the pattern demand information, the color demand information and the size demand information to generate a personalized demand information data package; S21, obtain the personalized demand information data package; S22, analyze and process the personalized demand information data package using a deep learning algorithm to extract key design features; S23, generate a plurality of design schemes based on the key design features and in combination with big data analysis, the design schemes including a pattern sketch, a color matching scheme and a size layout; dimensionally normalize the design features to ensure that all feature values are within the range of [0, 1], and generate a design scheme formula: ; wherein, is a generated design scheme vector, a multidimensional real number vector without dimension, is a weight coefficient of an ith design feature, 0≤ ≤1, the threshold being minimum 0 and maximum 1, is a normalized ith feature value, 0≤ ≤ 1, threshold minimum 0, maximum 1, is a bias adjustment constant, real dimensionless, threshold: -0.5 ≤ ≤ 0.5, is the total number of features, integer, threshold ≥ 1, default = 3; S24, display multiple design schemes to users through an online design platform for users to select or modify; S31, obtain a final design scheme selected by a user and order information, the order information including a production quantity, a delivery time, and a priority; S32, analyze production resource conditions based on the final design scheme and the order information, the production resource conditions including embroidery machine availability, material inventory, and personnel configuration; S33, plan a production process by using an intelligent scheduling algorithm to generate a dimensionally normalized scheduling optimization value: ; wherein, is a normalized scheduling coefficient, 0 ≤ ≤ 1, is a device utilization rate, 0% ≤ ≤ 100%, is a material turnover rate, 0 ≤ ≤ 5, , is a weight factor, , ≥ 0, ≥ 0; S34, arrange work tasks of the embroidery machine device according to a production task sequence, and generate production scheduling instructions; S41, in the process of the embroidery machine device performing the work tasks, real-time collection of production quality indicators, the production quality indicators including stitch density, stitch consistency, and color deviation; S42, comparison of the production quality indicators with preset standard values to calculate a dimensionally normalized comprehensive deviation rate: ; wherein, is a normalized comprehensive deviation rate, 0 ≤ ≤ 1, is a quality measured value, is a quality standard value, is a lower limit of the standard value, stitch density 0.5 mm, stitch deviation 0°, ΔE color difference 1.0, is an upper limit of the standard value, stitch density 2.0 mm, stitch deviation 10°, ΔE color difference 5.0; S43, when , output quality monitoring data as qualified. S44, when the quality monitoring data is unqualified, output the quality monitoring data as unqualified; S51, when the quality monitoring data is unqualified, analyze the quality deviation reason and generate a deviation analysis report; S52, based on the deviation analysis report, adjust the parameters of the embroidery machine equipment, including needle speed, tension or wire type; S53, generate adjusted production data using an optimization algorithm, the adjusted production data including updated production task sequence and equipment parameters; dimensionless normalization processing is performed on the deviation coefficient to ensure that the coefficient is within the range of [0, 1], and the parameter adjustment formula is: ; wherein, is the adjusted parameter value, a real number, is the original parameter value, a real number, a dimensionless base value, is the base scaling factor, 0.5 ≤ 2, threshold minimum 0.5, maximum 2, is the normalized deviation influence coefficient, 0 ≤ 1, threshold minimum 0, maximum 1, is the deviation correction factor, 0 ≤ 1, threshold minimum 0.01, maximum 1; S54, when the quality monitoring data is qualified, directly use the original production data to continue the production process; S61, based on the adjusted production data or the original production data, control the embroidery machine equipment to execute the production task; S62, real-time monitoring of equipment status, generating dimensionless normalized load warning value: ; wherein, is the normalized load rate, 0 ≤ 1, is the actual working time 0 ≤ 24, unit: hour, is the maximum sustainable working time = 8, unit: hour / day; S63, when switch to standby equipment; S64, after completing the production task, output the customized embroidered product finished product and perform quality reinspection; S71, collect production data of customized embroidered products, including production time, resource consumption and quality indicators; S72, collect user demand information and final design scheme; S73, combine production data, user demand information and final design scheme to store to cloud database; S74, generate production history record data for big data analysis and production optimization; S8, based on production history record data, use machine learning algorithm optimization module to calculate dimensionless optimization gain value: ; Wherein, is the normalized optimization gain rate, -1≤ ≤1, is the production efficiency after optimization, 0≤ ≤100%, is the original production efficiency, 0≤ ≤100%, is the reference efficiency value, =50% is the industry reference; S9, when >0.05, apply optimization parameters.

[0022] The operation steps of an intelligent embroidery product customization production system and method are as follows: Demand intelligent acquisition stage: The system starts the customization process through the user demand interaction module, synchronously acquires the core demand parameters of the user for the embroidery product through the multi-channel input interface, the pattern element recognition unit analyzes the image features uploaded by the user, extracts key information such as contour and texture, the color preference analysis unit identifies the primary and secondary color tones and gradient requirements specified by the user through spectral matching technology, the size parameter calibration unit automatically optimizes the length-width ratio combined with physical constraint conditions, and the three groups of data are integrated into structured demand data packets by the demand fusion engine, ensuring the integrity and executability of personalized demand.

[0023] Intelligent scheme generation stage After receiving the demand data packet, the intelligent design module starts the feature weighting algorithm to analyze the demand priority, the deep learning driving unit calls the pre-trained model library containing a million-level embroidery pattern database, generates multiple candidate schemes through feature space mapping technology, and each scheme contains a three-dimensional visual preview: the vector pattern engine maintains contour accuracy while optimizing needle trace path, the dynamic color matching system simulates color development effect under different lighting conditions, and the proportion adapter automatically adjusts the matching degree of size and carrier object. After the user selects the final scheme through the interactive interface, the system generates a digital process instruction set containing needle method sequence, wire material consumption, etc.

[0024] Production intelligent scheduling stage: After the production scheduling module receives the process instructions and order information, the resource state perception unit monitors in real time: the embroidery machine working load and fault warning state, the wire inventory and replenishment cycle, the artificial process scheduling saturation: the dynamic planning algorithm generates a four-dimensional scheduling matrix based on the constraint conditions of delivery period and cost threshold: device allocation scheme, process time window, material flow path, and abnormal handling plan. Task instructions are issued to the workshop execution layer through the industrial Internet of Things protocol, achieving minute-level response.

[0025] Quality closed-loop control phase: The quality monitoring module deploys a multi-sensor fusion system: the microscopic vision unit detects stitch density with 0.1mm precision, the tension feedback unit monitors stitch uniformity, and the spectrum analyzer compares the color difference ΔE value. Real-time data flows through the quality decision tree to determine: qualified products flow to the packaging station, abnormal products trigger the parameter adaptive mechanism: the needle speed dynamic adjustment module compensates for stitch deviation, the line changing robot automatically corrects color difference, the path optimizer re-plans the complex pattern area, and the adjusted parameters are updated to the process database simultaneously, forming a continuously optimized production knowledge graph.

[0026] Data value sedimentation phase: The system imports all-link data into the cloud-native storage engine, predicts design trends through user preference mining models, optimizes scheduling strategies through device performance evaluation matrices, and reduces rework rates through quality defect correlation analysis: the generated production capacity heat map drives enterprise resource planning, realizing continuous evolution of customized production.

[0027] It should be noted that, in this text, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0028] Although embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and alterations can be made thereto without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A customized intelligent embroidery production system, characterized in that: include: The personalized demand processing module acquires user demands through the pattern element acquisition unit, color element acquisition unit, and size element acquisition unit, and generates a personalized demand data package through the demand fusion processing unit. The intelligent solution construction module receives the requirement data packet, parses key features through the requirement feature extraction unit, outputs an initial design solution through the solution generation algorithm unit, and displays the interactive solution to the user through the solution preview unit. The production scheduling optimization module receives the final plan confirmed by the user, decomposes the production parameters through the order element parsing unit, analyzes the equipment and material status through the resource monitoring unit, generates the production task sequence through the scheduling algorithm optimization unit, and allocates the embroidery machine operation instructions through the task orchestration unit. The quality control module monitors production indicators in real time through the stitch quality acquisition unit and the color matching accuracy acquisition unit, compares the results with preset thresholds using the deviation analysis unit, and outputs device adjustment instructions through the parameter adaptive unit. The closed-loop optimization module receives adjustment instructions from the quality control module, constructs a data matrix through the production history analysis unit, identifies efficiency bottlenecks using the trend prediction unit, and outputs parameter optimization instructions to the intelligent solution construction module and the production scheduling optimization module via the strategy generation unit. The digital dashboard module integrates data from the entire production chain, calculates quality scores and efficiency coefficients through a multi-dimensional indicator fusion unit, and generates dynamic evaluation reports through a visualization unit.

2. A method for customized production of intelligent embroidered products, characterized in that: The method includes the following steps: S1. Collect users' personalized needs for embroidered products through the user needs interaction module. The personalized needs include pattern needs, color needs, and size needs. S2. Based on the personalized needs information, the intelligent design module generates a variety of design schemes that meet the user's needs; S3. Based on the design scheme and order information, the production scheduling module intelligently plans the embroidery production process and arranges the work tasks of the embroidery machine equipment. S4. During the production of embroidered products, the quality monitoring module is used to monitor production quality indicators in real time and generate quality monitoring data. S5. When the quality monitoring data meets the preset standards, output the finished embroidery product; when the quality monitoring data does not meet the preset standards, adjust the production parameters and generate the adjusted production data. S6. Based on the adjusted production data or the original production data, execute the embroidery production task and output customized embroidery products; S7. Store the production data and user demand information of the customized embroidery products in the database to generate historical production data.

3. The intelligent embroidery product customization production method according to claim 2, characterized in that: S1 includes the following steps: S11. Receive pattern requirement information input by the user through an online design platform. The pattern requirement information includes the embroidery theme, style, and complexity. S12. Receive the color requirement information selected by the user through the online design platform. The color requirement information includes the main color, secondary color, and gradient parameters. S13. Receive user-defined size requirements information through an online design platform, wherein the size requirements information includes length, width, and shape proportions; S14. Combine and process the pattern requirement information, color requirement information and size requirement information to generate a personalized requirement information data package.

4. The intelligent embroidery product customization production method according to claim 2, characterized in that: S2 includes the following steps: S21. Obtain the personalized demand information data packet; S22. Use deep learning algorithms to analyze and process the personalized demand information data package and extract key design features; S23. Based on the key design features, multiple design schemes are generated by combining big data analysis. The design schemes include pattern sketches, color schemes, and size layouts. The design features are normalized to ensure that all feature values ​​are within the range of [0,1], and the design scheme formula is generated as follows: ； in, The generated design scheme vector is a multidimensional real vector without dimensions. Let be the weighting coefficient of the i-th design feature, 0 ≤ ≤1, minimum threshold 0, maximum 1. Let be the i-th eigenvalue after normalization, 0 ≤ ≤1, minimum threshold 0, maximum 1. This is a deviation adjustment constant, a dimensionless real number, with a threshold of -0.5 ≤ ≤0.5, For the total number of features, integer, threshold ≥1, default =3; S24. Display the multiple design schemes to the user through an online design platform for the user to select or modify.

5. The intelligent embroidery product customization production method according to claim 2, characterized in that: S3 includes the following steps: S31. Obtain the final design scheme and order information selected by the user, wherein the order information includes production quantity, delivery time and priority; S32. Based on the final design scheme and order information, analyze the production resource status, including embroidery machine availability, material inventory, and personnel allocation; S33. Use an intelligent scheduling algorithm to plan the production process and generate a production task sequence, wherein the production task sequence includes equipment allocation, time nodes and task priorities; S34. Based on the production task sequence, arrange the work tasks of the embroidery machine equipment and generate production scheduling instructions.

6. The intelligent embroidery product customization production method according to claim 2, characterized in that: S4 includes the following steps: S41. During the embroidery machine's work, production quality indicators are collected in real time, including stitch density, stitch consistency, and color deviation. S42. Compare the production quality indicators with preset standard values ​​to generate quality deviation data; S43. When the quality deviation data is within the preset threshold, the output quality monitoring data is qualified; S44. When the quality deviation data exceeds the preset threshold, the output quality monitoring data is unqualified.

7. The intelligent embroidery product customization production method according to claim 2, characterized in that: S5 includes the following steps: S51. When the quality monitoring data is unqualified, analyze the cause of the quality deviation and generate a deviation analysis report; S52. Based on the deviation analysis report, adjust the parameters of the embroidery machine, including needle speed, tension, or thread type; S53. An optimization algorithm is used to generate adjusted production data, which includes updated production task sequences and equipment parameters; The deviation coefficients are normalized to ensure they are within the range of [0,1]. The parameter adjustment formula is as follows: ； in, The adjusted parameter values ​​are real numbers. These are the original parameter values, real numbers, dimensionless fundamental values. Based on the scaling factor, 0.5≤ ≤2, minimum threshold 0.5, maximum 2. The normalized bias influence coefficient, 0 ≤ ≤1, minimum threshold 0, maximum 1. This is the deviation correction factor, 0 < ≤1, the minimum threshold is 0.01, and the maximum is 1; S54. When the quality monitoring data is qualified, the original production data is used directly to continue the production process.

8. The intelligent embroidery product customization production method according to claim 2, characterized in that: S6 includes the following steps: S61. Based on the adjusted production data or the original production data, control the embroidery machine to perform production tasks; S62. During task execution, monitor the equipment status in real time and generate equipment operation logs; S63. When the equipment is in an abnormal state, automatically switch to backup equipment or adjust the production task; S64. After completing the production task, output the customized embroidered finished products and conduct a quality re-inspection.

9. The intelligent embroidery product customization production method according to claim 2, characterized in that: S7 includes the following steps: S71. Collect the production data of the customized embroidery products, including production time, resource consumption and quality indicators; S72. Collect user requirements information and final design solutions; S73. Combine and store the production data, user demand information and final design scheme in the cloud database; S74. Generate historical production data for big data analysis and production optimization.

10. The intelligent embroidery customization production method according to claim 2, characterized in that: The method further includes the following steps: S8. Based on the production history data, machine learning algorithms are used to optimize the intelligent design module and the production scheduling module to generate optimized parameters; S9. Apply the optimized parameters to subsequent production processes to improve customized production efficiency and quality consistency.

Images