A method and system for constructing a fabric color matching database based on printing and dyeing big data

Abstract

The present invention discloses a method and system for constructing a fabric color matching database based on printing and dyeing big data. The present invention relates to the field of data analysis technology, and includes the following steps: collecting various types of raw data in the printing and dyeing process, and preprocessing the collected data, wherein the raw data is divided into historical data and real-time data. The method and system for constructing a fabric color matching database based on printing and dyeing big data significantly improves the accuracy and consistency of color matching by constructing a color matching database based on printing and dyeing big data. Traditional color matching methods often rely on the experience and intuition of technicians, and it is difficult to ensure color consistency between different batches of products. By collecting and analyzing a large amount of historical color matching data, it is possible to identify key factors that affect color changes, train a basic color matching model, generate a color matching scheme according to new printing and dyeing requirements, and ensure that the produced color meets the expected standards.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for constructing a fabric color matching database based on printing and dyeing big data. Background Art

[0002] As consumers pursue more personalized products, the printing and dyeing industry needs to provide more diversified and precise color solutions. This requires printing and dyeing companies to have the ability to quickly respond to market changes and efficiently generate accurate color schemes. The printing and dyeing industry is gradually transforming to intelligent manufacturing and needs to use digitalization and information technology to improve production efficiency and quality levels. The traditional printing and dyeing industry often relies on manual experience and repeated experiments in the color matching process. This method is not only time-consuming and labor-intensive, but also prone to errors, resulting in inconsistent product colors or failure to meet design requirements. The construction of a color matching database is an important part of realizing intelligent manufacturing in printing and dyeing.

[0003] In the prior art, color changes in the printing and dyeing process may be affected by many factors, resulting in the color scheme in the color matching database being unable to fully adapt to actual production needs. Therefore, how to improve the generalization ability of the color matching database and dynamically adjust the color matching scheme of the printing and dyeing process is a problem we need to solve. To this end, a method and system for constructing a fabric color matching database based on printing and dyeing big data are proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: In the first aspect, a method for constructing a fabric color matching database based on printing and dyeing big data comprises the following steps:

[0005] Step 1: Collect various types of raw data in the printing and dyeing process and pre-process the collected data, wherein the raw data is divided into historical data and real-time data. The types of raw data include dye type, fabric type, printing and dyeing process parameters, environmental conditions, and historical color matching results;

[0006] Step 2: extracting printing and dyeing color matching features from the pre-processed raw data, including material features, process parameter features, and environmental condition features, analyzing the relationship between each feature and color change, and obtaining a color matching data sequence table;

[0007] Step 3: Based on the color matching data sequence table, the basic color matching model is trained using the extracted features and historical data, and the trained basic color matching model is used to generate a color matching scheme according to the new printing and dyeing requirements, and the matching degree of the color matching scheme is evaluated;

[0008] Step 4: Store the generated color scheme in the database, integrate the preprocessed data and the basic color matching model, establish a color matching database, and dynamically adjust the color scheme based on real-time data combined with the color matching database.

[0009] Preferably, in step 1, the process of collecting various types of raw data in the printing and dyeing process includes:

[0010] Collect various types of raw data in the printing and dyeing process, including dye types, fabric types, printing and dyeing process parameters, environmental conditions, and historical color matching result information;

[0011] The original data is divided into historical data and real-time data. The historical data of the printing and dyeing process comes from the past printing and dyeing production records, laboratory test data, customer orders and feedback, and is extracted from the enterprise database, production records, and quality reports. The real-time data of the printing and dyeing process includes the process parameters and environmental conditions obtained through sensors and monitoring systems on the production line. The production records include the types of dyes used and fabric types extracted from production logs and report files. Laboratory data includes dye performance test results, color comparison of fabrics before and after dyeing, and color fastness tests. Customer orders and feedback include collecting customer color requirements for printing and dyeing products, actual color evaluation after receipt, and improvement suggestions. The process parameters include the temperature, pressure, and stirring speed in the current dyeing tank, and the environmental conditions include the real-time temperature and humidity in the workshop.

[0012] The collected historical data and real-time data are preprocessed. The preprocessing process includes data cleaning, data conversion and data integration. The data integrity is checked, missing values ​​or incomplete records are eliminated, outliers are identified and processed, such as data points outside the normal range, duplicate data are removed, the uniqueness of the data is ensured, and data in different formats and units are converted into a unified format and unit for subsequent processing. Non-numeric data, such as fabric type and dye type, are coded and converted into numerical data. Historical data and real-time data are integrated to form a complete data set.

[0013] Preferably, in step 2, the process of obtaining the color matching data sequence table includes:

[0014] Perform feature analysis on the preprocessed raw data to extract material features, process parameter features, and environmental condition features, and analyze the relationship between each feature and color change. Material features include fabric type and dye type, process parameter features include temperature, concentration, pH value, and dyeing time, and environmental condition features include workshop temperature and humidity.

[0015] Analyze the material characteristics, extract the sub-features of fabric material, structure, and color basis of fabric type characteristics, and identify the sub-features of dye chemical properties, color intensity, and color light of dye type characteristics, integrate material characteristics and their corresponding color change results, and mark them, analyze the process parameter characteristics, extract the sub-features of initial temperature, maximum temperature, and insulation temperature of temperature characteristics, analyze the changes in dyeing time and insulation time in the dyeing process, as well as the relationship between dye uptake and its concentration, pH value changes in the dyeing process, integrate the color change results of the process parameter characteristic change process, analyze the environmental condition characteristics, analyze the impact of workshop temperature on dye stability and coloring effect, and the impact of humidity on fabric water absorption and dyeing uniformity;

[0016] Analyze the material characteristics and their sub-characteristics data, combine the color change results of the material characteristics, establish a material change model, identify the relationship between material characteristics and color change, and obtain the material change index through comprehensive analysis to evaluate the correlation trend of the change of material characteristics to color change;

[0017] Analyze the correlation data of process parameter characteristics, combine the color change results under process parameter characteristics, establish a color change model, integrate the color change results of the process parameter characteristic change process, and obtain the process parameter change index through comprehensive analysis to evaluate the correlation trend of the change of process parameter characteristics on color change;

[0018] Analyze the correlation data of environmental condition characteristics, combine the color change results under environmental condition characteristics, establish an environmental change model, identify the impact of environmental condition changes on color changes, obtain an environmental change index through comprehensive analysis, and evaluate the correlation trend of environmental condition changes on color changes;

[0019] Each feature is combined with the analysis results of the corresponding color change trend to form a color matching data sequence table. Each sample (i.e., a color matching test) contains a set of features and corresponding color change results.

[0020] Preferably, the expression of the material change index is:

[0021] ;

[0022] in, is the material variation index, It is The weights of the material features are assigned according to the importance of the material features. It is The actual observed value of the material characteristic, It is The reference value of a material characteristic, It is The standard deviation of a material characteristic, is the number of material features, The larger the value, the greater the effect of the change in material characteristics on the color change;

[0023] The expression of the process parameter variation index is:

[0024] ;

[0025] in, is the process parameter variation index, is the size adjustment coefficient, which is used to adjust the initial size of the process parameter variation index. is the process parameter difference adjustment coefficient, which is used to adjust the impact of process parameter differences on the process parameter variation index. It is The color value under the process parameter characteristics, It is The target color value of the process parameter feature, is the number of process parameter characteristics;

[0026] The expression of the environmental change index is:

[0027] ;

[0028] in, is the environmental change index, is the control coefficient, which is used to normalize the value of the environmental change index. It is The actual value of the environmental conditions, It is The minimum ideal value of environmental conditions, is a positive number to prevent the denominator from being zero. is the number of environmental conditions characteristic.

[0029] Preferably, in step 3, the training process of the basic color matching model includes:

[0030] Load data from the color matching data sequence table, including features and corresponding color change results, preprocess the loaded data, remove or process missing values ​​and outliers, encode classification features, form a data set, and divide the data set into a training set and a test set;

[0031] Use the training set data combined with the neural network model to build a basic color matching model, and use the test set data to evaluate the basic color matching model to adjust the performance of the model;

[0032] Using the trained basic color matching model, input the printing and dyeing requirements according to the new printing and dyeing requirements, including the required material characteristics, process parameter characteristics and environmental condition characteristics, perform the same preprocessing and feature encoding on the new data as the training data, input the processed new data into the trained basic color matching model for prediction, and the basic color matching model outputs the predicted color change result, that is, the new color matching scheme;

[0033] Based on the associated data of the color matching data sequence table, the color matching coefficient is calculated in combination with the material change index, the process parameter change index, and the environmental change index, and the matching degree of the predicted color matching effect is analyzed to evaluate the matching degree of the color matching scheme;

[0034] According to the color matching coefficient and historical data, different matching levels are divided into high matching level, medium matching level and low matching level. The matching degree between the color change trend of the printing and dyeing process and the color matching scheme is analyzed, and the corresponding matching threshold is set for each matching level.

[0035] Preferably, the expression of the color matching coefficient is:

[0036] ;

[0037] in, is the color matching coefficient, It is The material variation index corresponding to each material feature, It is The process parameter variation index corresponding to the process parameter characteristics is It is The environmental change index corresponding to each environmental condition characteristic is , , Respectively represent the weight coefficients of material characteristics, process parameter characteristics and environmental condition characteristics, is the number of material features, is the number of process parameter characteristics, is the number of environmental conditions characteristic, is the scale adjustment factor, which is used to adjust The scale of is the impact adjustment coefficient, which is used to adjust the total number of features to The impact of is the total number of features, .

[0038] Preferably, the plurality of matching levels correspond to the plurality of matching thresholds, the matching thresholds include an upper threshold and a lower threshold, and the corresponding relationship between the plurality of matching levels and the plurality of matching thresholds is:

[0039] High matching level ;

[0040] Medium Match Level ;

[0041] Low matchmaking level ;

[0042] in, is the color matching coefficient, is the lower threshold corresponding to the high matching level and the upper threshold corresponding to the medium matching level, The lower threshold corresponding to the medium matching level and the upper threshold corresponding to the low matching level.

[0043] Preferably, in step 4, the process of establishing the color matching database includes:

[0044] Generate color schemes using basic color matching models and record detailed information about the color schemes, including materials used, process parameters, and environmental conditions;

[0045] Configure a unique identifier for the color scheme, and mark the color information, related features, generation time, and matching level in the color scheme;

[0046] Enter the color scheme and related data into the database, build the color database, and create an index, which is associated with the unique identifier of the color scheme. Use the data in the color database for analysis to optimize the basic color model and generate a report on the color scheme for reference by management and users;

[0047] The color matching scheme is dynamically adjusted according to the real-time data combined with the color matching database, and the color matching database is integrated with the control system of the printing and dyeing production line to realize automatic color matching.

[0048] In a second aspect, a system for constructing a fabric color matching database based on printing and dyeing big data is provided, which is used to implement a method for constructing a fabric color matching database based on printing and dyeing big data, and includes an integrated management platform, wherein the integrated management platform is communicatively connected with a data acquisition module, a data preprocessing module, a feature extraction and analysis module, a color matching model training module, a color matching scheme generation module, a color matching effect evaluation module, and a database management module, wherein the modules are connected by electrical signals;

[0049] The data acquisition module is used to collect all relevant data in the printing and dyeing process, including historical data and real-time data, to ensure that the system has comprehensive data support and provide a basis for subsequent data processing and analysis;

[0050] The data preprocessing module is used to clean, convert and integrate the collected data, process missing values ​​and outliers, perform feature encoding, improve data quality, ensure data consistency and availability, and prepare clean and standardized data sets for data analysis and model training;

[0051] The feature extraction and analysis module is used to extract material features, process parameter features, and environmental condition features from the preprocessed data, analyze the relationship between the features and color changes, identify key features that affect the color matching effect, and provide a useful feature set for model training;

[0052] The color matching model training module uses the extracted features and color change results combined with a machine learning algorithm to train a basic color matching model and predict color matching schemes based on input material features, process parameters, and environmental condition parameters;

[0053] The color scheme generation module uses the trained basic color matching model to generate a color scheme according to new printing and dyeing requirements, quickly generates a color scheme that meets specific requirements, and improves production efficiency and flexibility;

[0054] The color matching effect evaluation module is used to evaluate the matching degree of the color matching scheme, calculate the color matching coefficient, divide the matching level, and perform the quality evaluation of the color matching scheme to help users choose the best color matching scheme;

[0055] The database management module is used to store and manage color schemes, feature data, model parameters, and provide data retrieval and update functions to ensure persistent storage of data and support rapid access and effective management of data.

[0056] The present invention provides a method and system for constructing a fabric color matching database based on printing and dyeing big data. It has the following beneficial effects:

[0057] 1. The method and system for constructing a fabric color matching database based on printing and dyeing big data significantly improves the accuracy and consistency of color matching by constructing a color matching database based on printing and dyeing big data. Traditional color matching methods often rely on the experience and intuition of technicians, and it is difficult to ensure color consistency between different batches of products. By collecting and analyzing a large amount of historical color matching data, it is possible to identify the key factors affecting color changes, train a basic color matching model, generate color matching schemes according to new printing and dyeing requirements, and ensure that the produced colors meet the expected standards.

[0058] 2. The method and system for constructing a fabric color matching database based on printing and dyeing big data can quickly generate color matching schemes to reduce the number and time of trial and error. At the same time, through the analysis of historical data, it can optimize the color matching schemes and reduce the waste of raw materials, thereby reducing production costs. In addition, the automation characteristics of the system reduce the dependence on highly skilled labor and further reduce labor costs, which helps printing and dyeing companies to improve production efficiency and optimize cost control while maintaining product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1A method flow chart of a method for constructing a fabric color matching database based on printing and dyeing big data according to the present invention;

[0060] Figure 2 The flowchart of obtaining the color matching data sequence table of the present invention;

[0061] Figure 3 This is a training flow chart of the basic color matching model of the present invention;

[0062] Figure 4 This is a diagram of the module structure of the present invention. DETAILED DESCRIPTION

[0063] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0064] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: a method for constructing a fabric color matching database based on printing and dyeing big data, comprising the following steps:

[0065] Step 1, collect various types of raw data in the printing and dyeing process, and pre-process the collected data, wherein the raw data is divided into historical data and real-time data, and the types of raw data include dye type, fabric type, printing and dyeing process parameters, environmental conditions, and historical color matching results. Collect various types of raw data in the printing and dyeing process, wherein the types of raw data include dye type, fabric type, printing and dyeing process parameters, environmental conditions, and historical color matching results information. The raw data is divided into historical data and real-time data, wherein the historical data of the printing and dyeing process comes from past printing and dyeing production records, laboratory test data, customer orders and feedback, and is extracted from the enterprise database, production records, and quality reports. The real-time data of the printing and dyeing process includes process parameters and environmental conditions obtained through sensors and monitoring systems on the production line. Production records include information on dye usage and fabric type extracted from production logs and report files, and laboratory test data. The laboratory data includes dye performance test results, color comparison of fabrics before and after dyeing, and color fastness test. Customer orders and feedback include collecting customer color requirements for printing and dyeing products, color evaluation after actual receipt, and improvement suggestions. Process parameters include the temperature, pressure, and stirring speed in the current dyeing tank. Environmental conditions include the real-time temperature and humidity in the workshop. The collected historical data and real-time data are preprocessed. The preprocessing process includes data cleaning, data conversion, and data integration. Check the integrity of the data, remove missing values ​​or incomplete records, identify and process abnormal values, such as data points outside the normal range, remove duplicate data, ensure the uniqueness of the data, convert data in different formats and units into a unified format and unit for subsequent processing, and encode non-numeric data, such as fabric type and dye type, and convert them into numerical data. Integrate historical data and real-time data to form a complete data set.

[0066] Step 2: Extract printing and dyeing color matching features from the pre-processed raw data, including material features, process parameter features and environmental condition features, analyze the relationship between each feature and color change, and obtain a color matching data sequence table. Perform feature analysis on the pre-processed raw data, extract material features, process parameter features and environmental condition features, and analyze the relationship between each feature and color change, where material features include fabric type and dye type, process parameter features include temperature, concentration, pH value and dyeing time, and environmental condition features include workshop temperature and humidity. Analyze material features, extract sub-features of fabric material, tissue structure, and color basis of fabric type features, and identify sub-features of dye chemical properties, color intensity, and color light of dye type features, integrate material features and their corresponding color change results, and mark them. Analyze process parameter features, extract sub-features of initial temperature, maximum temperature, and insulation temperature of temperature features, analyze changes in dyeing time and insulation time during the dyeing process, as well as the relationship between dye uptake and its concentration, pH value changes during the dyeing process, integrate color change results of process parameter feature changes, and perform environmental condition features. Analysis: Analyze the influence of workshop temperature on dye stability and coloring effect and the influence of humidity on fabric water absorption and dyeing uniformity; analyze material characteristics and their sub-characteristic data; combine the color change results of material characteristics to establish a material change model; identify the relationship between material characteristics and color change; comprehensively analyze to obtain a material change index; evaluate the correlation trend of material characteristics change on color change; analyze the correlation data of process parameter characteristics; combine the color change results under process parameter characteristics to establish a color change model; integrate the color change results of process parameter characteristics change process; comprehensively analyze to obtain a process parameter change index; evaluate the correlation trend of process parameter characteristics change on color change; analyze the correlation data of environmental condition characteristics; combine the color change results under environmental condition characteristics to establish an environmental change model; identify the influence of environmental condition changes on color change; comprehensively analyze to obtain an environmental change index; evaluate the correlation trend of environmental condition characteristics change on color change; combine each characteristic with the corresponding color change trend analysis results to form a color matching data sequence table; each sample (i.e., a color matching test) contains a set of characteristics and corresponding color change results;

[0067] Furthermore, the expression of the material change index is:

[0068] ;

[0069] in, is the material variation index, It is The weights of the material features are assigned according to the importance of the material features. It is The actual observed value of the material characteristic, It is The reference value of a material characteristic, It is The standard deviation of a material characteristic, is the number of material features, The larger the value, the greater the effect of the change in material characteristics on the color change;

[0070] The expression of process parameter variation index is:

[0071] ;

[0072] in, is the process parameter variation index, is the size adjustment coefficient, which is used to adjust the initial size of the process parameter variation index. is the process parameter difference adjustment coefficient, which is used to adjust the impact of process parameter differences on the process parameter variation index. It is The color value under the process parameter characteristics, It is The target color value of the process parameter feature, is the number of process parameter characteristics, The value of Within the range, when near hour, A larger value indicates that changes in process parameter characteristics have a greater impact on color change;

[0073] The expression of environmental change index is:

[0074] ;

[0075] in, is the environmental change index, is the control coefficient, which is used to normalize the value of the environmental change index. It is The actual value of the environmental conditions, It is The minimum ideal value of environmental conditions, is a positive number to prevent the denominator from being zero. is the number of environmental conditions characteristic, The larger the value, the smaller the difference between the environmental conditions and the ideal state, and the smaller the impact on color change;

[0076] Step 3: Based on the color matching data sequence table, the basic color matching model is trained using the extracted features and historical data, and the trained basic color matching model is used to generate a color matching scheme according to the new printing and dyeing requirements, and the matching degree of the color matching scheme is evaluated;

[0077] Step 4: Store the generated color scheme in the database, integrate the preprocessed data and the basic color matching model, establish a color matching database, and dynamically adjust the color scheme based on real-time data combined with the color matching database.

[0078] The second embodiment is based on the first embodiment. Figure 3 As shown, in step 3, the training process of the basic color matching model includes:

[0079] Load data from the color matching data sequence table, including features and corresponding color change results, preprocess the loaded data, remove or process missing values ​​and outliers, and encode classification features to form a data set, divide the data set into a training set and a test set, use the training set data in combination with the neural network model to build a basic color matching model, and use the test set data to evaluate the basic color matching model to adjust the performance of the model, use the trained basic color matching model, input printing and dyeing requirements according to new printing and dyeing requirements, including the required material characteristics, process parameter characteristics and environmental condition characteristics, perform the same preprocessing and feature encoding on the new data as the training data, and The processed new data is input into the trained basic color matching model for prediction. The basic color matching model outputs the predicted color change result, i.e., the new color matching scheme. The color matching coefficient is calculated based on the associated data of the color matching data sequence table in combination with the material change index, the process parameter change index, and the environmental change index. The matching degree of the predicted color matching effect is analyzed, and the matching degree of the color matching scheme is evaluated. According to the color matching coefficient and historical data, different matching levels are divided into high matching level, medium matching level, and low matching level. The matching degree between the color change trend of the printing and dyeing process and the color matching scheme is analyzed, and the corresponding matching threshold is set for each matching level.

[0080] The expression of color matching coefficient is:

[0081] ;

[0082] in, is the color matching coefficient, It is The material variation index corresponding to each material feature, It is The process parameter variation index corresponding to the process parameter characteristics is It is The environmental change index corresponding to each environmental condition characteristic is , , Respectively represent the weight coefficients of material characteristics, process parameter characteristics and environmental condition characteristics, is the number of material features, is the number of process parameter characteristics, is the number of environmental conditions characteristic, is the scale adjustment factor, which is used to adjust The scale of is the impact adjustment coefficient, which is used to adjust the total number of features to The impact of is the total number of features, , The larger the value, the more closely the color scheme matches the actual needs;

[0083] Furthermore, multiple matching levels correspond to multiple matching thresholds, and the matching thresholds include an upper threshold and a lower threshold. The corresponding relationship between the multiple matching levels and the multiple matching thresholds is:

[0084] High matching level ;

[0085] Medium Match Level ;

[0086] Low matchmaking level ;

[0087] in, is the color matching coefficient, is the lower threshold corresponding to the high matching level and the upper threshold corresponding to the medium matching level, is the lower threshold corresponding to the medium matching level and the upper threshold corresponding to the low matching level;

[0088] In step 4, the process of establishing the color matching database includes:

[0089] Use the basic color matching model to generate a color scheme, record detailed information about the color scheme, including the materials used, process parameters, and environmental conditions, configure a unique identifier for the color scheme, and mark the color information, related features, generation time, and matching level in the color scheme. Enter the color scheme and related data into the database, build a color matching database, and create an index, which is associated with the unique identifier of the color scheme. Use the data in the color matching database for analysis to optimize the basic color matching model, and generate a report on the color scheme for reference by management and users. Dynamically adjust the color scheme based on real-time data combined with the color matching database, and integrate the color matching database with the control system of the printing and dyeing production line to achieve automated color matching.

[0090] The third embodiment is based on the first and second embodiments. Figure 4As shown, the present invention also provides a system for constructing a fabric color matching database based on printing and dyeing big data, which is used to implement a method for constructing a fabric color matching database based on printing and dyeing big data, including an integrated management platform, the integrated management platform is communicatively connected with a data acquisition module, a data preprocessing module, a feature extraction and analysis module, a color matching model training module, a color matching scheme generation module, a color matching effect evaluation module and a database management module, wherein the modules are connected by electrical signals;

[0091] Data acquisition module, used to collect all relevant data in the printing and dyeing process, including historical data and real-time data, to ensure that the system has comprehensive data support and provide a basis for subsequent data processing and analysis;

[0092] Data preprocessing module, which is used to clean, transform and integrate the collected data, handle missing values ​​and outliers, perform feature encoding, improve data quality, ensure data consistency and availability, and prepare clean and standardized data sets for data analysis and model training;

[0093] Feature extraction and analysis module, used to extract material features, process parameter features, and environmental condition features from preprocessed data, analyze the relationship between features and color changes, identify key features that affect color matching effects, and provide useful feature sets for model training;

[0094] The color matching model training module uses the extracted features and color change results combined with machine learning algorithms to train the basic color matching model and predict the color matching scheme based on the input material characteristics, process parameters and environmental condition parameters;

[0095] The color scheme generation module uses the trained basic color matching model to generate color schemes according to new printing and dyeing requirements, quickly generating color schemes that meet specific requirements and improving production efficiency and flexibility;

[0096] The color matching effect evaluation module is used to evaluate the matching degree of the color matching scheme, calculate the color matching coefficient, divide the matching level, and conduct the quality evaluation of the color matching scheme to help users choose the best color matching scheme;

[0097] The database management module is used to store and manage color schemes, feature data, model parameters, and provide data retrieval and update functions to ensure persistent storage of data and support fast access and effective management of data.

[0098] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A method for constructing a fabric color matching database based on printing and dyeing big data, characterized in that: The following steps are involved: Step 1: Collect various types of raw data in the printing and dyeing process and pre-process the collected data, wherein the raw data is divided into historical data and real-time data. The types of raw data include dye type, fabric type, printing and dyeing process parameters, environmental conditions, and historical color matching results; Step 2: extracting printing and dyeing color matching features from the pre-processed raw data, including material features, process parameter features, and environmental condition features, analyzing the relationship between each feature and color change, and obtaining a color matching data sequence table. In step 2, the process of obtaining the color matching data sequence table includes: Perform feature analysis on the preprocessed raw data to extract material features, process parameter features, and environmental condition features, and analyze the relationship between each feature and color change. Material features include fabric type and dye type, process parameter features include temperature, concentration, pH value, and dyeing time, and environmental condition features include workshop temperature and humidity. Analyze the material characteristics, extract the sub-features of fabric material, structure, and color basis of fabric type characteristics, and identify the sub-features of dye chemical properties, color intensity, and color light of dye type characteristics, integrate material characteristics and their corresponding color change results, and mark them, analyze the process parameter characteristics, extract the sub-features of initial temperature, maximum temperature, and insulation temperature of temperature characteristics, analyze the changes in dyeing time and insulation time in the dyeing process, as well as the relationship between dye uptake and its concentration, pH value changes in the dyeing process, integrate the color change results of the process parameter characteristic change process, analyze the environmental condition characteristics, analyze the impact of workshop temperature on dye stability and coloring effect, and the impact of humidity on fabric water absorption and dyeing uniformity; Analyze the material characteristics and their sub-characteristics data, combine the color change results of the material characteristics, establish a material change model, identify the relationship between material characteristics and color change, and obtain the material change index through comprehensive analysis to evaluate the correlation trend of the change of material characteristics to color change; Analyze the correlation data of process parameter characteristics, combine the color change results under process parameter characteristics, establish a color change model, integrate the color change results of the process parameter characteristic change process, and obtain the process parameter change index through comprehensive analysis to evaluate the correlation trend of the change of process parameter characteristics on color change; Analyze the correlation data of environmental condition characteristics, combine the color change results under environmental condition characteristics, establish an environmental change model, identify the impact of environmental condition changes on color changes, obtain an environmental change index through comprehensive analysis, and evaluate the correlation trend of environmental condition changes on color changes; Each feature is combined with the analysis results of the corresponding color change trend to form a color matching data sequence table. Each sample contains a set of features and corresponding color change results. The expression of the material change index is: in, is the material variation index, It is The weights of the material features are assigned according to the importance of the material features. It is The actual observed value of the material characteristic, It is The reference value of a material characteristic, It is The standard deviation of a material characteristic, is the number of material characteristics; The expression of the process parameter variation index is: in, is the process parameter variation index, is the size adjustment coefficient, which is used to adjust the initial size of the process parameter variation index. is the process parameter difference adjustment coefficient, which is used to adjust the impact of process parameter differences on the process parameter variation index. It is The color value under the process parameter characteristics, It is The target color value of the process parameter feature, is the number of process parameter characteristics; The expression of the environmental change index is: in, is the environmental change index, is the control coefficient, which is used to normalize the value of the environmental change index. It is The actual value of the environmental conditions, It is The minimum ideal value of the environmental conditions, is a positive number to prevent the denominator from being zero. is the number of environmental condition characteristics; Step 3: Based on the color matching data sequence table, the basic color matching model is trained using the extracted features and historical data, and the trained basic color matching model is used to generate a color matching scheme according to the new printing and dyeing requirements, and the matching degree of the color matching scheme is evaluated. In step 3, the training process of the basic color matching model includes: Load data from the color matching data sequence table, including features and corresponding color change results, preprocess the loaded data, remove or process missing values ​​and outliers, encode classification features, form a data set, and divide the data set into a training set and a test set; Use the training set data combined with the neural network model to build a basic color matching model, and use the test set data to evaluate the basic color matching model to adjust the performance of the model; Using the trained basic color matching model, input the printing and dyeing requirements according to the new printing and dyeing requirements, including the required material characteristics, process parameter characteristics and environmental condition characteristics, perform the same preprocessing and feature encoding on the new data as the training data, input the processed new data into the trained basic color matching model for prediction, and the basic color matching model outputs the predicted color change result, that is, the new color matching scheme; Based on the associated data of the color matching data sequence table, the color matching coefficient is calculated in combination with the material change index, the process parameter change index, and the environmental change index, and the matching degree of the predicted color matching effect is analyzed to evaluate the matching degree of the color matching scheme; According to the color matching coefficient and historical data, different matching levels are divided into high matching level, medium matching level and low matching level, respectively, the matching degree between the color change trend of the printing and dyeing process and the color matching scheme is analyzed, and the corresponding matching threshold is set for each matching level. The expression of the color matching coefficient is: in, is the color matching coefficient, It is The material variation index corresponding to each material feature, It is The process parameter variation index corresponding to the process parameter characteristics is It is The environmental change index corresponding to each environmental condition characteristic is Respectively represent the weight coefficients of material characteristics, process parameter characteristics and environmental condition characteristics, is the number of material features, is the number of process parameter characteristics, is the number of environmental conditions characteristic, is the scale adjustment factor, which is used to adjust The scale of is the impact adjustment factor, which is used to adjust the total number of features to The impact of is the total number of features, The larger the value, the higher the match between the color scheme and the actual demand; Step 4, store the generated color scheme in the database, integrate the preprocessed data and the basic color matching model, establish a color matching database, and dynamically adjust the color scheme according to the real-time data combined with the color matching database.

2. The method for constructing a fabric color matching database based on printing and dyeing big data according to claim 1, characterized in that: In step 1, the process of collecting various types of raw data in the printing and dyeing process includes: Collect various types of raw data in the printing and dyeing process, including dye types, fabric types, printing and dyeing process parameters, environmental conditions, and historical color matching result information; The original data is divided into historical data and real-time data. The historical data of the printing and dyeing process comes from the past printing and dyeing production records, laboratory test data, customer orders and feedback, and is extracted from the enterprise database, production records, and quality reports. The real-time data of the printing and dyeing process includes the process parameters and environmental conditions obtained through sensors and monitoring systems on the production line. The production records include the types of dyes used and fabric types extracted from production logs and report files. Laboratory data includes dye performance test results, color comparison of fabrics before and after dyeing, and color fastness tests. Customer orders and feedback include collecting customer color requirements for printing and dyeing products, actual color evaluation after receipt, and improvement suggestions. The process parameters include the temperature, pressure, and stirring speed in the current dyeing tank, and the environmental conditions include the real-time temperature and humidity in the workshop. The collected historical data and real-time data are preprocessed. The preprocessing process includes data cleaning, data conversion and data integration. For non-numeric data, encoding processing is performed and converted into numerical data. The historical data and real-time data are integrated to form a complete data set.

3. The method for constructing a fabric color matching database based on printing and dyeing big data according to claim 2, characterized in that: The plurality of matching levels correspond to the plurality of matching thresholds, the matching thresholds include an upper threshold and a lower threshold, and the corresponding relationship between the plurality of matching levels and the plurality of matching thresholds is: in, is the color matching coefficient, is the lower threshold corresponding to the high matching level and the upper threshold corresponding to the medium matching level, The lower threshold corresponding to the medium matching level and the upper threshold corresponding to the low matching level.

4. The method for constructing a fabric color matching database based on printing and dyeing big data according to claim 3, characterized in that: In step 4, the process of establishing the color matching database includes: Generate color schemes using basic color matching models and record detailed information about the color schemes, including materials used, process parameters, and environmental conditions; Configure a unique identifier for the color scheme, and mark the color information, related features, generation time, and matching level in the color scheme; Enter the color scheme and related data into the database, build the color database, create an index, associate it with the unique identifier of the color scheme, use the data in the color database to perform analysis to optimize the basic color model, and generate a report on the color scheme; The color matching scheme is dynamically adjusted according to the real-time data combined with the color matching database, and the color matching database is integrated with the control system of the printing and dyeing production line to realize automatic color matching.

5. A system for constructing a fabric color matching database based on printing and dyeing big data, used to implement a method for constructing a fabric color matching database based on printing and dyeing big data as described in any one of claims 1 to 4, comprising an integrated management platform, characterized in that: The integrated management platform is communicatively connected with a data acquisition module, a data preprocessing module, a feature extraction and analysis module, a color matching model training module, a color matching scheme generation module, a color matching effect evaluation module and a database management module, wherein the modules are connected with electrical signals.

6. The system for constructing a fabric color matching database based on printing and dyeing big data according to claim 5, characterized in that: The data acquisition module is used to collect all relevant data in the printing and dyeing process, including historical data and real-time data; The data preprocessing module is used to clean, convert and integrate the collected data, process missing values ​​and abnormal values, and perform feature coding; The feature extraction and analysis module is used to extract material features, process parameter features and environmental condition features from the preprocessed data, analyze the relationship between the features and color changes, and identify key features that affect the color matching effect; The color matching model training module uses the extracted features and color change results combined with a machine learning algorithm to train a basic color matching model and predict color matching schemes based on input material features, process parameters, and environmental condition parameters; The color scheme generation module generates a color scheme that meets the requirements by using the trained basic color matching model and generating a color scheme according to the new printing and dyeing requirements; The color matching effect evaluation module is used to evaluate the matching degree of the color matching scheme, calculate the color matching coefficient, divide the matching level, and perform quality evaluation of the color matching scheme; The database management module is used to store and manage color schemes, feature data, model parameters, and provide data retrieval and update functions.

Images