Intelligent speed regulation training method and system for high-speed air-jet weaving machine

Abstract

The application discloses an intelligent speed regulation training method and system for a high-speed air-jet color weaving machine, and belongs to the field of textile industry automation; the technical problem of low production efficiency of a traditional high-speed air-jet color weaving machine is solved; the technical scheme is as follows: based on adaptive weaving and printing parameter regulation and control and an intelligent feedback mechanism, combined with a comprehensive strategy of multi-parameter simulation, quality evaluation and defect detection, precise process control and automatic adjustment are realized at different weaving and printing speeds through a multi-parameter real-time monitoring system and an intelligent speed regulation control module of the high-speed air-jet color weaving machine, and the method comprises the following steps: inputting orders and patterns, determining a strategy according to analysis characteristics, calculating the weight of multivariables to adjust the overall speed of the fabric, automatically prompting speed regulation parameters to perform threshold alarm, adaptively adjusting the speed to match the real-time change of multi-parameters, identifying fabric defects based on a color CLE Lab model, dynamically adjusting the weaving and printing speed according to the defect detection result and generating a report; the application is applied to the high-speed air-jet color weaving machine.

Description

Technical Field

[0001] This invention provides an intelligent speed regulation training method and system for high-speed air-jet color looms, belonging to the field of textile industry automation. Background Technology

[0002] With the development of technology, the automation and intelligence of textile machinery are constantly improving. High-speed air-jet looms, as crucial equipment in the textile industry, directly impact the industry's economic benefits through their production efficiency and product quality. However, traditional high-speed air-jet looms, due to the lack of an effective weaving and printing detection mechanism, present operators with difficulties in identifying fabric defects. This often leads to a lack of awareness and understanding, making it difficult to accurately judge weaving and printing quality, thus affecting production efficiency and product quality.

[0003] Traditional high-speed air-jet printing machines typically rely on manual parameter adjustments and quality checks during operation. This method is not only inefficient but also lacks systematic training tools and guidance, failing to help operators effectively address various challenges in production. Therefore, on high-speed and large-scale production lines, this traditional method is clearly inadequate to meet the demands of modern production, necessitating an intelligent speed-adjustment training method and system to improve the accuracy and efficiency of printing inspection.

[0004] To address the aforementioned issues, this invention proposes an intelligent speed regulation training method and system for high-speed air-jet printing machines. This system, through multi-parameter simulation display at real-time, full-range printing speeds, allows operators to clearly understand the machine's operating status, enabling more effective parameter adjustments to optimize fabric speed. Simultaneously, the system features automatic prompts for printing quality assessment under parameterized speed regulation, providing real-time and accurate quality feedback to help operators adjust parameters promptly and ensure printing quality. Furthermore, the system can evaluate color differences perceived by the human eye in matching printing speed adjustments. By simulating human visual perception, it more accurately assesses color differences, ensuring product color uniformity to meet consumer demands. Additionally, the system can mark multi-parameter defects in real-time and generate local case output simulations, helping operators identify and resolve problems promptly, thereby further improving production efficiency and product quality. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the present invention aims to solve the following technical problem: to provide an improved intelligent speed regulation training method and system for a high-speed air-jet color weaving machine.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by this invention is: an intelligent speed regulation training method and system for high-speed air-jet woven machines, characterized by: based on an adaptive weaving and printing parameter control and intelligent feedback mechanism, combined with a comprehensive strategy of multi-parameter simulation, quality assessment, and defect detection, through a multi-parameter real-time monitoring system and intelligent speed regulation control module of the high-speed air-jet woven machine, achieving precise process control and automated adjustment at different weaving and printing speeds. The specific implementation method includes the following steps:

[0007] S1: Input the order and pattern to determine the strategy based on the analysis features.

[0008] S2: Calculate the weights of multiple variables to adjust the overall speed of the fabric.

[0009] S3: Automatically prompts speed adjustment parameters and triggers threshold alarm.

[0010] S4: Adaptive speed adjustment matches real-time changes in multiple parameters.

[0011] S5: Identify fabric defects based on the color CLE Lab model.

[0012] S6: Dynamically adjust the weaving speed and generate reports based on defect detection results.

[0013] Step S1 specifically includes:

[0014] The system inputs order information and patterns, analyzes the input data using advanced feature extraction algorithms, determines the optimal speed stratification strategy, and selects an appropriate speed adjustment mode based on fabric characteristics and pattern complexity to achieve dynamic optimization and performance improvement of the weaving and printing process.

[0015] Step S2 specifically includes:

[0016] Based on the layered analysis results of the pattern, a dynamic control algorithm is used to generate precise speed adjustment signals and color control signals. Through a regional speed adjustment mechanism, fine-grained speed control is implemented for each woven and printed area to ensure the consistency of fabric surface quality and the accuracy of color performance.

[0017] Step S3 specifically includes:

[0018] The system automatically calculates the dynamic speed requirements of each weaving area and uses an adaptive control algorithm to generate corresponding control signals to achieve consistency and coordination of area speeds. If there is a difference between the actual speed and the predicted speed, the system will automatically prompt the user to ensure the overall quality and performance stability of the fabric during the production process.

[0019] Step S4 specifically includes:

[0020] The system employs a custom dynamic speed matching strategy, taking into account user-defined parameters such as fabric texture, color, and pattern complexity. Through advanced data analysis and machine learning algorithms, it determines the speed adjustment strategy in real time. This program dynamically adjusts the air-jet woven fabric's operating speed based on changes in these parameters to match pattern variations. Particularly during the weaving and printing process, if changes in pattern color or complexity are detected, the system automatically adjusts the speed to ensure both quality and efficiency. Furthermore, the system automatically learns and optimizes the speed adjustment strategy based on real-time operational data, further improving the air-jet woven fabric's operating efficiency and product quality.

[0021] Step S5 specifically includes:

[0022] Based on the CIE Lab color model, the system analyzes the color features of the fabric surface in real time and uses a convolutional neural network (CNN) algorithm to identify and judge fabric defects that are difficult for the human eye to perceive. Through correlation analysis between defect feature data and speed control parameters, a linear regression model algorithm is used to dynamically optimize the speed control strategy. Specifically, this involves constructing a mathematical relationship between defect features and speed control parameters, and optimizing the weaving and printing speed through weight calculations to improve production efficiency and ensure the consistency and stability of product quality. Furthermore, the system combines machine learning models for predictive analysis to identify potential defect trends and achieves proactive management of fabric quality through feedforward control, thereby optimizing quality monitoring during the production process.

[0023] Step S6 specifically includes:

[0024] After layering is completed, the weaving speed is dynamically adjusted based on the multifunctional intelligent simulation model of weaving and printing, and the defect information obtained by the real-time defect detection module, to compensate for fabric defects. The system generates corresponding speed adjustment strategies by analyzing the type and severity of defects. Simultaneously, all detected defect data is recorded, and a detailed quality report is generated, including the nature and location of the defects and handling suggestions, to ensure traceability, quality monitoring, and optimization of production efficiency throughout the weaving and printing process.

[0025] A method and system for intelligent speed regulation training of a high-speed air-jet woven machine, characterized in that: it includes a high-speed air-jet woven machine, a multi-parameter real-time monitoring module integrated into the control unit of the high-speed air-jet woven machine, an intelligent speed regulation control module, and a defect detection and marking module, wherein the module functions as described in the running module of the intelligent speed regulation training program for the high-speed air-jet woven machine.

[0026] The intelligent speed regulation training program mainly consists of a multi-parameter surface detection algorithm, a linear feature extraction algorithm, a color detection algorithm based on color gamut analysis, and a defect module; defect data can be recorded and saved, and has the function of exporting and viewing to support subsequent quality analysis and management.

[0027] The dynamic speed control algorithm automatically adjusts the weaving and printing speed based on real-time monitored process parameters through an adaptive optimization algorithm, ensuring stable fabric output under different production conditions. Simultaneously, the model also supports manual speed adjustment, allowing operators to flexibly adjust the weaving and printing speed according to actual needs, and providing self-prompting optimization suggestions during the speed adjustment process to further improve production efficiency and fabric quality. Furthermore, the model can intelligently predict speed changes based on historical data, providing long-term speed adjustment strategy suggestions. The color difference detection algorithm uses the CLE LAB color difference analysis model, combined with the program's built-in visual perception model, to automatically detect color changes during speed adjustment and compare them with the target color, generating a real-time color difference evaluation report to ensure color consistency.

[0028] The aforementioned multi-parameter simulation model for real-time full-domain weaving and printing speed refers to a comprehensive analysis of real-time speed data and various parameters during the weaving process of a high-speed air-jet loom. This model includes objective measurements and subjective evaluations of several key parameters. Objective measurements include four parameters: fabric material, fabric length, color consistency, and pattern accuracy. Subjective evaluations encompass user satisfaction and visual quality scores. The quantitative relationship model between objective measurements and subjective evaluations is achieved by calculating the difference between the objective and subjective parameters for each sample and using a random forest algorithm for nonlinear fitting to determine weight values, thereby enabling effective prediction and optimization of weaving and printing quality. The weight calculation for objective measurements involves analyzing the impact of fabric material, fabric length, color consistency, and pattern accuracy on product quality based on past production data. Relevant past production data, including product quality indicators and production parameters, is collected. Regression analysis is used to find the relationship between each parameter and the final product quality, and a score is given. The score is based on a 1-10 scale (1 being the worst and 10 the best). After scoring the four parameters, normalization is performed using the following formula:

[0029]

[0030] Among them W i It is the weight of the i-th parameter, S i is the score of the i-th parameter, and n is the total number of parameters.

[0031] The fabric speed can be determined based on the calculated weights. Generally, a higher weight allows for a faster fabric speed during production, as this means the parameter has a smaller impact on quality. The specific speed calculation method is as follows:

[0032] SA=k·(1+α·(W m +W l +W c +W p ))

[0033] Where k is a reference speed (unit: meters per minute). W m : Weight of fabric material; W l : Weight of fabric length; W c Weight of color consistency; W p : Weight of pattern accuracy. α: Adjustment coefficient, controlling the magnitude of speed adjustment. By adjusting the value of α, the sensitivity of speed adjustment can be controlled. For example, if α = 0.5, the influence of each parameter will only affect half of the base speed.

[0034] If the sum of all weights is 0, the speed remains unchanged; if the sum of weights is positive, the speed increases; if the sum of weights is negative, the speed decreases.

[0035] The range of α is defined as follows:

[0036] 0.5≤α<1.0: Suitable for smaller adjustment needs, typically used in stable production processes.

[0037] 1.0≤α<2.0: Suitable for production environments that require rapid response to changes, such as high-end customization or complex pattern printing.

[0038] α≥2.0: Can be used in special circumstances, such as production scenarios that require drastic changes, but should be used with caution to avoid affecting fabric quality.

[0039] Case 1: Background: Produces home textiles, focusing on the durability of the fabrics and the precision of the patterns.

[0040] Fabric material score: 8; Fabric length score: 6; Color consistency score: 7; Pattern accuracy score: 9. Weight: Fabric material: Fabric length:

[0041] Color consistency: Pattern precision:

[0042] Speed ​​Adjustment: Assuming a base speed k = 60 (unit: meters per minute), and an adjustment coefficient α = 1.0, the speed adjustment is calculated as follows:

[0043] SA=k·(1+α·(W m +W l +W c +W p )) = 120 meters / minute

[0044] Case 2: Background: High-end silk products, emphasizing the consistency of fabric material and color.

[0045] Fabric material rating: 9; Fabric length rating: 4; Color consistency rating: 10; Pattern accuracy rating: 8

[0046] Weight: Fabric Material: Fabric length:

[0047] Color consistency: Pattern precision:

[0048] Speed ​​Adjustment: Assuming a base speed k = 50 (unit: meters per minute), and an adjustment coefficient α = 1.5, the speed adjustment is calculated as follows:

[0049] SA=k·(1+α·(W m +W l +W c +W p = 125 meters / minute

[0050] Case 3: Background: Durable outdoor sportswear, with particular emphasis on the consistency of fabric material and color.

[0051] Fabric material score: 10; Fabric length score: 5; Color consistency score: 8; Pattern accuracy score: 7

[0052] Weight: Fabric Material: Fabric length:

[0053] Color consistency: Pattern precision:

[0054] Speed ​​Adjustment: Assuming a base speed k = 65 (unit: meters per minute), and an adjustment coefficient α = 1.8, the speed adjustment is calculated as follows:

[0055] SA=k·(1+α·(W m +W l +W c +W p = 182 meters / minute

[0056] The self-prompting parameterized speed control weaving and printing quality assessment device consists of a speed adjustment module, a quality detection module, a feedback optimization module, a data recording device, and a positioning sensor. It possesses the ability to monitor, automatically adjust, and optimize the weaving and printing process in real time, significantly improving weaving and printing quality and production efficiency. Specifically, the speed adjustment module uses a rectangular metal plate with a circumferentially slit array, combined with a microfluidic converging structure, to precisely guide and adjust the weaving and printing speed; the quality detection module monitors the weaving and printing quality in real time through a high-frequency motor and an eccentric wheel; and the feedback optimization module automatically adjusts the speed based on quality data. Furthermore, the positioning sensor monitors the fabric status in real time to ensure precise control. Users can adjust the speed independently based on the monitoring results to meet personalized production needs, while the data recording device supports subsequent analysis and model optimization.

[0057] The speed-matching human-perceived color difference evaluation strategy is based on the color composition and geometric relationships of patterns printed on a high-speed color jet loom. It aims to regulate the color transition and pattern blending at the boundaries of adjacent printing areas. This strategy includes four control methods: overall speed adjustment, local speed adjustment, continuous speed adjustment, and discrete speed adjustment. Combining color component allocation, color characteristics, and human-perceived thresholds, the system will determine adaptive inkjet component ratios and stacking sequences to improve printing quality and efficiency. Specifically, the system will consider factors such as visual thresholds, surface texture, and the slope of the printing area to automatically optimize the speed adjustment strategy, achieving more precise color transitions and pattern blending.

[0058] The multi-parameter defect real-time labeling and local case output simulation model refers to a defect case library based on a high-speed air-jet loom, enabling real-time monitoring and labeling analysis of fabric defects. This model utilizes a convolutional neural network (CNN) to construct a quantitative relationship between objective metrics and subjective evaluations. Objective metrics cover surface defects, line defects, and color defects; subjective evaluations include user satisfaction with fabric quality and visual defect ratings. The model calculates weight values ​​and effectively labels and classifies defects through difference calculation and nonlinear fitting. Key functionalities of this model include real-time monitoring, quantitative relationship modeling, and effective defect classification.

[0059] In summary, the "Intelligent Speed ​​Adjustment Training Method and System for High-Speed ​​Air-Jet Color Looms" of this invention is characterized by high efficiency and precision. It can monitor and adjust the operating status of high-speed air-jet color looms in real time, optimizing speed and quality during fabric production. This program effectively reduces production defects, improves fabric consistency and quality, provides an innovative solution for the weaving industry, and promotes the further development of intelligent weaving equipment. Attached Figure Description

[0060] The invention will be further described below with reference to the accompanying drawings:

[0061] Figure 1 The flowchart of this invention Detailed Implementation

[0062] To realize an intelligent speed regulation training method and system for high-speed air-jet woven machines, the present invention specifically adopts the following technical solution:

[0063] A smart speed regulation training method and system for high-speed air-jet woven machines based on intelligent algorithms optimizes speed and quality during fabric production through real-time data analysis and user-defined parameters. Specific operation steps include:

[0064] 1) Input order information and pattern: First, the user inputs the detailed information of the order and the fabric pattern. The system analyzes its characteristics, determines the appropriate speed stratification strategy, and selects the speed adjustment mode.

[0065] 2) Generation of speed and color control signals: Based on the analysis results, the system generates speed adjustment signals and color control signals to adjust the weaving speed in different areas, ensuring that the color and quality of the fabric in different areas meet the standards.

[0066] 3) Calculate speed adjustment requirements: The system calculates the required speed adjustment for each area and generates corresponding control signals to ensure the consistency of fabric production in each area.

[0067] 4) Real-time speed adjustment strategy determination: Based on user-defined multiple parameters, the system determines the speed adjustment strategy in real time and dynamically adjusts the loom speed to match changes in the fabric pattern, ensuring efficient production.

[0068] 5) Real-time fabric defect identification: Using the color CLE Lab model, the system identifies fabric defects in real time and dynamically adjusts the speed according to the defect type and location to optimize the printing quality and reduce the production of defective products.

[0069] 6) Adjusting weaving speed and generating reports: After layering is completed, the system adjusts the weaving speed based on the defect detection results, records defect information, and generates detailed reports for subsequent analysis and improvement.

[0070] The aforementioned multi-parameter simulation model for real-time full-domain weaving and printing speed refers to a comprehensive analysis of real-time speed data and various parameters during the weaving process of a high-speed air-jet loom. This model includes objective measurements and subjective evaluations of several key parameters. Objective measurements include four parameters: fabric material, fabric length, color consistency, and pattern accuracy. Subjective evaluations encompass user satisfaction and visual quality scores. The quantitative relationship model between objective measurements and subjective evaluations is achieved by calculating the difference between the objective and subjective parameters for each sample and using a random forest algorithm for nonlinear fitting to determine weight values, thereby enabling effective prediction and optimization of weaving and printing quality. The weight calculation for objective measurements involves analyzing the impact of fabric material, fabric length, color consistency, and pattern accuracy on product quality based on past production data. Relevant past production data, including product quality indicators and production parameters, is collected. Regression analysis is used to find the relationship between each parameter and the final product quality, and a score is given. The score is based on a 1-10 scale (1 being the worst and 10 the best). After scoring the four parameters, normalization is performed using the following formula:

[0071]

[0072] Among them W i It is the weight of the i-th parameter, S i is the score of the i-th parameter, and n is the total number of parameters.

[0073] The fabric speed can be determined based on the calculated weights. Generally, a higher weight allows for a faster fabric speed during production, as this means the parameter has a smaller impact on quality. The specific speed calculation method is as follows, where SA is the speed adjustment formula:

[0074] SA=k·(1+α·(W m +W l +W c +W p ))

[0075] Where k is a reference speed (unit: meters per minute). W m : Weight of fabric material; W l : Weight of fabric length; W c Weight of color consistency; W p : Weight of pattern accuracy. α: Adjustment coefficient, controlling the magnitude of speed adjustment. By adjusting the value of α, the sensitivity of speed adjustment can be controlled. For example, if α = 0.5, the influence of each parameter will only affect half of the base speed.

[0076] If the sum of all weights is 0, the speed remains unchanged; if the sum of weights is positive, the speed increases; if the sum of weights is negative, the speed decreases.

[0077] The range of α is defined as follows:

[0078] 0.5≤α<1.0: Suitable for smaller adjustment needs, typically used in stable production processes.

[0079] 1.0≤α<2.0: Suitable for production environments that require rapid response to changes, such as high-end customization or complex pattern printing.

[0080] α≥2.0: Can be used in special circumstances, such as production scenarios that require drastic changes, but should be used with caution to avoid affecting fabric quality.

[0081] Case 1: Background: Produces home textiles, focusing on the durability of the fabrics and the precision of the patterns.

[0082] Fabric material rating: 8; Fabric length rating: 6; Color consistency rating: 7; Pattern accuracy rating: 9

[0083] Weight: Fabric Material: Fabric length:

[0084] Color consistency: Pattern precision:

[0085] Speed ​​Adjustment: Assuming a base speed k = 60 (unit: meters per minute), and an adjustment coefficient α = 1.0, the speed adjustment is calculated as follows:

[0086] SA=k·(1+α·(W m +W l +W c +W p )) = 120 meters / minute

[0087] Case 2: Background: High-end silk products, emphasizing the consistency of fabric material and color.

[0088] Fabric material rating: 9; Fabric length rating: 4; Color consistency rating: 10; Pattern accuracy rating: 8

[0089] Weight: Fabric Material: Fabric length:

[0090] Color consistency: Pattern precision:

[0091] Speed ​​Adjustment: Assuming a base speed k = 50 (unit: meters per minute), and an adjustment coefficient α = 1.5, the speed adjustment is calculated as follows:

[0092] SA=k·(1+α·(W m +W l +W c +W p = 125 meters / minute

[0093] Case 3: Background: Durable outdoor sportswear, with particular emphasis on the consistency of fabric material and color.

[0094] Fabric material score: 10; Fabric length score: 5; Color consistency score: 8; Pattern accuracy score: 7

[0095] Weight: Fabric Material: Fabric length:

[0096] Color consistency: Pattern precision:

[0097] Speed ​​Adjustment: Assuming a base speed k = 65 (unit: meters per minute), and an adjustment coefficient α = 1.8, the speed adjustment is calculated as follows:

[0098] SA=k·(1+α·(W m +W l +W c +W p = 182 meters / minute

[0099] The self-prompting parameterized speed adjustment weaving and printing quality assessment device consists of a speed adjustment module, a quality detection module, a feedback optimization module, a data recording device, and a positioning sensor. It features real-time monitoring, automatic adjustment, and optimization of the weaving and printing process, significantly improving weaving and printing quality and production efficiency. Specifically, the speed adjustment module uses a rectangular metal plate with a circumferential slit array and a microfluidic converging structure to precisely guide the weaving and printing speed and adjust the cutting speed. The quality detection module uses components such as a high-frequency motor, connecting rod, and eccentric wheel to monitor quality changes during the weaving and printing process in real time. The feedback optimization module automatically adjusts the weaving and printing speed based on the quality detection data. Furthermore, the positioning sensor uses a high-precision photoelectric sensor to monitor the fabric's running status and position changes in real time, ensuring precise control of the weaving and printing process. Users can also adjust the speed parameters independently based on real-time monitoring results to meet personalized production needs. The data recording device and positioning sensor are installed in parallel at the four endpoints of the lower surface of the speed adjustment module to collect and record various parameter data during the weaving and printing process, providing support for subsequent data analysis and model optimization.

[0100] The speed-matching human-perceived color difference evaluation strategy refers to an understanding of the color components and geometric relationships of patterns printed on a high-speed color jet loom. It aims to regulate the color transition and pattern joining between adjacent printing areas, forming four control methods: overall speed adjustment and local speed adjustment along the perimeter of the printing area, and continuous and discrete speed adjustment along the printing direction. Combined with the color component distribution data and color characteristics of the printing area, an adaptive control approach is developed, considering visual thresholds, surface texture, and the slope of the printing area to comprehensively plan the inkjet component ratio and stacking sequence of the color printing area. Specifically, the system formulates a speed-matching strategy for the printing area based on the color components and geometric relationships of the printed pattern, as well as the human eye's perception threshold for color differences. This strategy aims to achieve color transition and pattern joining between printing areas, thereby improving printing quality and efficiency. In achieving this goal, the system considers various factors, such as color component distribution data, color characteristics, visual thresholds, surface texture, and the slope of the printing area. Based on these factors, the system will adaptively adjust the composition ratio and stacking order of the inkjet to optimize the printing effect.

[0101] The multi-parameter real-time defect labeling and local case output simulation model refers to the real-time monitoring and labeling analysis of fabric defects based on a defect case library collected during the production process of a high-speed air-jet loom. This model constructs a quantitative relationship model between objective metrics and subjective evaluations for defect identification and classification through training with a Supported Convolutional Neural Network (CNN). The objective metrics include three parameters: surface defects, line defects, and color defects; the subjective evaluations encompass user satisfaction with fabric quality and visual defect ratings. The quantitative relationship model between objective metrics and subjective evaluations calculates the difference between the objective metrics and subjective evaluation parameters for each sample, and then uses a Supported Convolutional Neural Network for nonlinear fitting to determine the weight values, thereby achieving effective defect labeling and classification.

[0102] Regarding the specific structure of this invention, it should be noted that the connection relationships between the various components and modules used in this invention are definite and achievable. Except as specifically described in the embodiments, their specific connection relationships can bring about corresponding technical effects and solve the technical problems proposed by this invention without relying on the execution of corresponding software programs. Unless otherwise specifically described, the models and connection methods of the components, modules, and specific parts appearing in this invention are all prior art such as published patents, published journal articles, or common knowledge that can be obtained by those skilled in the art before the application date, and need not be elaborated. This makes the technical solution provided in this case clear, complete, and achievable, and can reproduce or obtain the corresponding physical product based on this technical means.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart speed regulation training method for high-speed air-jet colored looms, characterized in that: Based on an adaptive weaving and printing parameter control and intelligent feedback mechanism, combined with a comprehensive strategy of multi-parameter simulation, quality assessment, and defect detection, a multi-parameter real-time monitoring system and intelligent speed control module for a high-speed air-jet woven fabric are used to achieve precise process control and automated adjustment at different weaving and printing speeds. The specific implementation method includes the following steps: S1: Input the order and pattern to determine the strategy based on the analysis features; S2: Calculate the weights of multiple variables to adjust the overall speed of the fabric; step S2 specifically includes: Based on the layered analysis results of the pattern, a dynamic control algorithm is used to generate precise speed adjustment signals and color control signals. A regional speed adjustment mechanism is used to implement fine speed control of each woven area to ensure the consistency of fabric surface quality and the accuracy of color performance. S3: Automatically prompts speed control parameters and triggers threshold alarm; S4: Adaptive speed adjustment matches real-time changes in multiple parameters; Step S4 specifically includes: The system employs a custom dynamic speed matching strategy. Based on user-defined parameters, including fabric texture, color, and pattern complexity, it uses advanced data analysis and machine learning algorithms to determine the speed adjustment strategy in real time. This method dynamically adjusts the operating speed of the air-jet woven fabric according to changes in these parameters to match pattern variations. During the weaving and printing process, if changes in pattern color or complexity are detected, the system automatically adjusts the speed to ensure weaving and printing quality and efficiency. Simultaneously, the system automatically learns and optimizes the speed adjustment strategy based on real-time operating data, further improving the operating efficiency of the air-jet woven fabric and product quality. S5: Identify fabric defects based on the CLE LAB color difference analysis model; S6: Dynamically adjust the weaving speed and generate reports based on defect detection results.

2. The intelligent speed regulation training method for a high-speed air-jet color loom according to claim 1, characterized in that: Step S1 specifically includes: The system inputs order information and patterns, analyzes the input data using advanced feature extraction algorithms, determines the optimal speed stratification strategy, and selects an appropriate speed adjustment mode based on fabric characteristics and pattern complexity to achieve dynamic optimization and performance improvement of the weaving and printing process.

3. The intelligent speed regulation training method for a high-speed air-jet colored loom according to claim 1, characterized in that: Step S3 specifically includes: The system automatically calculates the dynamic speed requirements of each weaving area and uses an adaptive control algorithm to generate corresponding control signals to achieve consistency and coordination of area speeds. If there is a difference between the actual speed and the predicted speed, the system will automatically prompt the user to ensure the overall quality and performance stability of the fabric during the production process.

4. The intelligent speed regulation training method for a high-speed air-jet color loom according to claim 1, characterized in that: Step S5 specifically includes: Based on the CIE Lab color model, the system analyzes the color features of the fabric surface in real time and uses a convolutional neural network (CNN) algorithm to identify and judge fabric defects that are difficult for the human eye to detect. Through correlation analysis between defect feature data and speed control parameters, a linear regression model algorithm is used to dynamically optimize the speed control strategy. Specifically, this includes constructing a mathematical relationship between defect features and speed control parameters, and optimizing the weaving and printing speed through weight calculation to improve production efficiency and ensure the consistency and stability of product quality. In addition, the system combines machine learning models for predictive analysis to identify potential defect trends and achieve proactive management of fabric quality through feedforward control to optimize quality monitoring in the production process.

5. The intelligent speed regulation training method for a high-speed air-jet colored loom according to claim 4, characterized in that: Step S6 specifically includes: After the layering is completed, the weaving speed is dynamically adjusted based on the multifunctional intelligent simulation model of weaving and printing and the defect information obtained by the real-time defect detection module to compensate for fabric defects. The system generates corresponding speed adjustment strategies by analyzing the type and severity of defects. At the same time, all detected defect data is recorded and a detailed quality report is generated, including the nature, location and handling suggestions of the defects, to ensure the traceability, quality monitoring and optimization of production efficiency of the entire weaving and printing process.

6. An intelligent speed regulation training system for a high-speed air-jet color loom, characterized in that: The invention includes a high-speed air-jet woven machine, a multi-parameter real-time monitoring module integrated into the control unit of the high-speed air-jet woven machine, an intelligent speed control module, and a defect detection module, for implementing the intelligent speed control training method for a high-speed air-jet woven machine as described in any one of claims 1-5. The intelligent speed regulation training method mainly consists of a multi-parameter surface detection algorithm, a linear feature extraction algorithm, a color difference detection algorithm based on color gamut analysis, and a defect detection module; defect data is recorded and saved, and has the function of exporting and viewing to support subsequent quality analysis and management; The dynamic speed matching strategy uses an adaptive optimization algorithm to automatically adjust the weaving and printing speed based on real-time monitored process parameters, ensuring stable fabric output under different production conditions. At the same time, it also supports manual speed adjustment, allowing operators to flexibly adjust the weaving and printing speed according to actual needs, and provides self-prompting optimization suggestions during the speed adjustment process to further improve production efficiency and fabric quality. The color difference detection algorithm uses the CLE LAB color difference analysis model, combined with the program's built-in visual perception model, to automatically detect color changes during speed adjustment and compare them with the target color, generating a real-time color difference evaluation report to ensure color consistency.

Images