Dyeing method and device based on dyeing prediction model, computer device and storage medium

Abstract

The application relates to the field of textile printing and dyeing, and discloses a dyeing method and device based on a dyeing prediction model, computer equipment and a storage medium. The method comprises the following steps: obtaining dyeing requirements; processing the dyeing requirements through a dyeing prediction model to obtain an initial dyeing process and the credibility of the initial dyeing process; setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility; obtaining test results of the dyeing test experiment; and determining a target dyeing process meeting the dyeing requirements according to the test results. The application can solve the problems of few dyeing data and low accuracy of model results.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of textile printing and dyeing, and in particular to a dyeing method and device based on a dyeing prediction model, a computer device and a storage medium. BACKGROUND

[0002] In the textile printing and dyeing industry, accurate color reproduction is crucial for product quality and market competitiveness. Traditional color matching methods rely on experienced technicians to manually mix dyes. This method is not only time-consuming and labor-intensive, but also susceptible to human factors, resulting in unstable color matching results. In recent years, with the development of information technology, data-driven methods have been gradually introduced into the field of textile printing and dyeing to improve the efficiency and accuracy of the color matching process.

[0003] However, on the one hand, due to limited historical data accumulation, high experimental costs, and other reasons, the amount of available printing and dyeing data is relatively small. This limits the learning ability and generalization performance of the model. On the other hand, due to the lack of sufficient data support and complex and variable dyeing process conditions, existing models may not achieve ideal prediction accuracy in certain situations. In particular, when facing new colors or special materials, the performance of the model is often unsatisfactory. Even if the model can give reasonable formula suggestions, due to the presence of many uncontrollable factors in the dyeing process, such as water quality differences, equipment state changes, etc., the final dyeing effect may have some gaps with the expected result. SUMMARY

[0004] Therefore, it is necessary to provide a dyeing method and device based on a dyeing prediction model, a computer device and a storage medium to solve the problems of insufficient dyeing data and low model result accuracy.

[0005] A dyeing method based on a dyeing prediction model, comprising:

[0006] Obtaining a dyeing requirement;

[0007] Processing the dyeing requirement by a dyeing prediction model to obtain an initial dyeing process and a credibility of the initial dyeing process;

[0008] Setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility;

[0009] Obtaining a test result of the dyeing test experiment;

[0010] Determining a target dyeing process meeting the dyeing requirement according to the test result.

[0011] Optionally, before the processing the dyeing requirement by a dyeing prediction model, the method further comprises:

[0012] Obtaining historical dyeing data;

[0013] training a plurality of dyeing index initial models according to the historical dyeing data, to obtain a plurality of dyeing index prediction models; the dyeing prediction model comprises the plurality of dyeing index prediction models.

[0014] Optionally, the dyeing index prediction model comprises a color accuracy prediction model.

[0015] The training of the plurality of dyeing index initial models according to the historical dyeing data, to obtain a plurality of dyeing index prediction models, comprises:

[0016] performing first preprocessing on the historical dyeing data, to obtain a color feature data set;

[0017] training the color feature data set by a support vector regression algorithm, to obtain the color accuracy prediction model.

[0018] Optionally, the dyeing index prediction model comprises a color fastness prediction model.

[0019] The training of the plurality of dyeing index initial models according to the historical dyeing data, to obtain a plurality of dyeing index prediction models, comprises:

[0020] performing second preprocessing on the historical dyeing data, to obtain a color fastness feature data set;

[0021] training the color fastness feature data set by a logistic regression algorithm, to obtain the color fastness prediction model.

[0022] Optionally, the setting of the experimental parameters of the dyeing test experiment according to the initial dyeing process and the reliability comprises:

[0023] extracting a value range and a parameter reliability of each dyeing parameter from the initial dyeing process and the reliability;

[0024] setting a plurality of test points according to the value range and the parameter reliability;

[0025] processing the plurality of test points by the dyeing prediction model, to obtain a simulation test result;

[0026] processing the simulation test result by a response surface method, to obtain the experimental parameters.

[0027] Optionally, the determination of the target dyeing process meeting the dyeing requirement according to the test result comprises:

[0028] if the test result meets the dyeing requirement, determining the target dyeing process according to the experimental parameters.

[0029] Optionally, the determining the target dyeing process meeting the dyeing requirement according to the test result comprises:

[0030] If the test result does not meet the dyeing requirement, the dyeing prediction model is optimized according to the test result to obtain a dyeing prediction optimization model;

[0031] The dyeing prediction optimization model is used to process the dyeing requirement to obtain an optimized dyeing process and a credibility of the optimized dyeing process;

[0032] The optimized dyeing test experiment is set up according to the optimized dyeing process and the optimized dyeing process, and an optimized test result of the optimized dyeing test experiment is obtained;

[0033] If the optimized test result meets the dyeing requirement, the target dyeing process is determined according to the optimized experimental parameters;

[0034] If the optimized test result does not meet the dyeing requirement, the dyeing prediction optimization model is further optimized according to the optimized test result until the finally obtained test result meets the dyeing requirement.

[0035] A dyeing device based on a dyeing prediction model comprises:

[0036] A dyeing requirement obtaining module is configured to obtain a dyeing requirement;

[0037] A model prediction module is configured to use a dyeing prediction model to process the dyeing requirement to obtain an initial dyeing process and a credibility of the initial dyeing process;

[0038] An experimental parameter setting module is configured to set experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility;

[0039] A test result obtaining module is configured to obtain a test result of the dyeing test experiment;

[0040] A target dyeing process determining module is configured to determine a target dyeing process meeting the dyeing requirement according to the test result.

[0041] A computer device comprises a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, and the processor executes the computer readable instructions to implement the dyeing method based on the dyeing prediction model.

[0042] One or more readable storage media storing computer readable instructions, and the computer readable instructions are executed by one or more processors to make the one or more processors execute the dyeing method based on the dyeing prediction model.

[0043] In the dyeing method, the dyeing device, the computer device and the storage medium based on the dyeing prediction model, the dyeing prediction model can quickly simulate different dyeing conditions, and the optimal or better initial dyeing process is screened out, so that the time-consuming and laborious trial-and-error process in the traditional method is avoided, the number of experiments is reduced, and the resource costs such as dyes, energy, water and labor are saved. The dyeing process can be accurately controlled, the uniformity and color fastness of dyeing are improved, the quality of the final product is improved, the standardized dyeing process is established, the production process is more stable and reliable, a large amount of data can be accumulated for further training and optimization of the model through continuous experimental verification, and a virtuous cycle is formed. The present application can solve the problems of few dyeing data and low accuracy of model results. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 is a flowchart of a dyeing method based on a dyeing prediction model in an embodiment of the present application;

[0046] Figure 2 is a structural schematic diagram of a dyeing device based on a dyeing prediction model in an embodiment of the present application;

[0047] Figure 3 is a schematic diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0049] In an embodiment, as shown in Figure 1 a dyeing method based on a dyeing prediction model is provided, including the following steps S10-S50.

[0050] S10, obtaining a dyeing requirement;

[0051] S20, processing the dyeing requirement by a dyeing prediction model to obtain an initial dyeing process and a credibility of the initial dyeing process;

[0052] S30, setting experiment parameters of a dyeing test experiment according to the initial dyeing process and the credibility;

[0053] S40, obtaining experiment results of the dyeing test experiment;

[0054] S50, determining a target dyeing process meeting the dyeing requirement according to the experiment results.

[0055] It can be understood that the dyeing requirement refers to the requirement of color change of the textile, including but not limited to color requirement, fabric type, dye type, and dyeing fastness requirement. In some examples, the dyeing requirement can be set by the user.

[0056] The dyeing prediction model is a prediction model obtained by training historical dyeing data based on a machine learning algorithm. Here, the machine learning algorithm can be selected from support vector machine (SVM), neural network (NN), random forest (RF), etc. The initial dyeing process is the output result of the dyeing prediction model, including pretreatment before dyeing, parameters (such as temperature, time, dye concentration, etc.) during dyeing, and fixation and post-treatment steps after dyeing. The credibility of the initial dyeing process includes the credibility of each parameter in the process. The credibility can be a single value or a confidence interval. In an example, the initial process and its credibility can be represented as:

[0057] Dye type: A, credibility 0.9;

[0058] Dye concentration: 2%, credibility 0.8;

[0059] Dyeing temperature: 80°C, credibility 0.7;

[0060] Dyeing time: 60 minutes, credibility 0.6;

[0061] pH value: 5.0, credibility 0.8.

[0062] After obtaining the initial dyeing process, the experiment parameters of the dyeing test experiment can be set according to the initial dyeing process. Here, the dyeing test experiment is generally a group of test points. After setting the experiment parameters of the dyeing test experiment, the dyeing test experiment can be performed, and the experiment results are recorded.

[0063] Table 1: Experiment results of an example textile dyeing

[0064] Experiment No. Dye concentration (C, %) Dyeing temperature (T, °C) Dyeing time (t, min) L* a* b* Washing fastness Rubbing fastness 1 2 70 30 50 11 21 4 3 2 2 70 60 55 13 23 4 3 3 2 70 90 60 15 25 4 3 4 2 80 30 55 12 22 4 3 5 2 80 60 60 14 24 4 3 6 2 80 90 65 16 26 4 3 7 2 90 30 60 13 23 4 3 8 2 90 60 65 15 25 4 3 9 2 90 90 90 17 27 4 3 ;

[0065] As shown in Table 1, Table 1 is an example of test results of textile dyeing. Among them, L* represents brightness, the larger the value, the brighter the color. a* represents the red-green axis, positive value represents red, negative value represents green. b* represents the yellow-blue axis, positive value represents yellow, negative value represents blue. Wash fastness represents the color retention of dyed fabric during washing. Rubbing fastness represents the color retention of dyed fabric during rubbing.

[0066] After obtaining the test results, it can be judged whether the test results meet the dyeing requirements. If the test results meet the dyeing requirements, the target dyeing process meeting the dyeing requirements can be directly determined according to the experimental parameters of the dyeing test experiment. If the test results do not meet the dyeing requirements, but the deviation from the dyeing requirements is less than a preset threshold (which can be set according to actual conditions), the experimental parameters of the dyeing test experiment can be adjusted according to industry experience, and then the target dyeing process meeting the dyeing requirements is determined. If the test results do not meet the dyeing requirements, and the deviation from the dyeing requirements is greater than or equal to the preset threshold, the dyeing prediction model can be updated using the test results to improve the prediction accuracy of the dyeing prediction model.

[0067] In this embodiment, the dyeing prediction model can quickly simulate different dyeing conditions and screen out the optimal or better initial dyeing process, thereby avoiding the time-consuming and laborious trial-and-error process in the traditional method, reducing the number of experiments, saving resources such as dyes, energy, water and labor, and helping to realize precise control of the dyeing process, improve the uniformity and color fastness of dyeing, thereby improving the quality of the final product, helping to establish a standardized dyeing process, making the production process more stable and reliable, and through continuous experimental verification, a large amount of data can be accumulated for further training and optimization of the model, forming a virtuous cycle. This embodiment can solve the problem of few dyeing data and low accuracy of model results.

[0068] Optionally, before step S20, that is, before processing the dyeing requirements by the dyeing prediction model, the method further comprises:

[0069] S21, obtaining historical dyeing data;

[0070] S22, training a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models; the dyeing prediction model comprises a plurality of dyeing index prediction models.

[0071] Understandably, the historical dyeing data refers to dyeing data obtained through historical dyeing performance experiments, including but not limited to dye information, fabric information, process parameters, auxiliary information, environmental factors, characterization results, cost data, and abnormal records. After sorting, cleaning, standardizing / normalizing the historical dyeing data, a dyeing sample set can be obtained. The dyeing sample set is used to train a plurality of dyeing index initial models to obtain a plurality of dyeing index prediction models. Then, all dyeing index prediction models are combined to form a dyeing prediction model. Here, the dyeing index initial model is an initial model set based on a specific dyeing index, such as color accuracy, color fastness, cost, etc. After training each dyeing index initial model using the dyeing sample set, the prediction accuracy of each dyeing index prediction model can be greatly improved.

[0072] The embodiment constructs a plurality of dyeing index prediction models to form a dyeing prediction model, greatly reduces the complexity of the dyeing prediction model, and improves the training efficiency of the model.

[0073] Optionally, the dyeing index prediction model includes a color accuracy prediction model; and step S22, i.e., training a plurality of dyeing index initial models based on the historical dyeing data to obtain a plurality of dyeing index prediction models, includes:

[0074] S221, first preprocessing the historical dyeing data to obtain a color feature data set;

[0075] S222, training the color feature data set by a support vector regression algorithm to obtain the color accuracy prediction model.

[0076] Understandably, after sorting, cleaning, standardizing / normalizing the historical dyeing data, a preliminary dyeing sample set can be obtained. Correlation analysis, principal component analysis (PCA), etc. can be used to identify key features related to color accuracy in the dyeing sample set to form a color feature data set.

[0077] The support vector regression algorithm (SVR) can be used to train the color feature data set to obtain the color accuracy prediction model. The support vector regression algorithm is a machine learning algorithm for regression analysis. The support vector regression algorithm determines a best hyperplane through an optimization problem, which should predict the target value, i.e., color accuracy, as accurately as possible.

[0078] The embodiment uses the support vector regression algorithm to construct the color accuracy prediction model, which can obtain good prediction results under the condition of less historical dyeing data, can effectively handle nonlinear problems, is not sensitive to outliers, and has good robustness.

[0079] Optionally, the dyeing index prediction model comprises a color fastness prediction model; and step S22, i.e., training a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models, comprises:

[0080] S223, performing second preprocessing on the historical dyeing data to obtain a color fastness feature data set;

[0081] S224, training the color fastness feature data set by a logistic regression algorithm to obtain the color fastness prediction model.

[0082] Understandably, after the historical dyeing data is arranged, cleaned, and standardized / nomalized, a preliminary dyeing sample set can be obtained. Correlation analysis, principal component analysis (PCA), or other methods can be used to identify key features related to color fastness in the dyeing sample set to form a color fastness feature data set.

[0083] The color fastness feature data set can be trained by a logistic regression algorithm (LR) to obtain a color fastness prediction model. The logistic regression algorithm is a classification algorithm that can be used to handle multi-classification problems. The color fastness prediction model can accurately divide the color fastness levels.

[0084] The embodiment uses a logistic regression algorithm to construct a color fastness prediction model, which is high in calculation efficiency, easy to implement and optimize, relatively insensitive to outliers and multicollinearity, and robust.

[0085] Optionally, step S30, i.e., setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility, comprises:

[0086] S301, extracting a value range and a parameter credibility of each dyeing parameter from the initial dyeing process and the credibility;

[0087] S302, setting a plurality of test points according to the value range and the parameter credibility;

[0088] S303, processing the plurality of test points by the dyeing prediction model to obtain simulation test results;

[0089] S304, processing the simulation test results by a response surface method to obtain the experimental parameters.

[0090] Understandably, the value range and the parameter credibility of each dyeing parameter can be extracted from the initial dyeing process and the credibility, and then a plurality of test points can be set according to the value range and the parameter credibility. A central composite design (CCD) method can be used to generate a series of test points.

[0091] Then the dyeing prediction model is used to process the multiple test points to obtain simulation test results. Since the dyeing prediction model comprises multiple dyeing index prediction models, each test point can be predicted by each dyeing index prediction model to obtain corresponding dyeing indexes. The dyeing indexes of each type of each test point form the simulation test results of the test point.

[0092] After obtaining the simulation test results, the simulation test results can be processed by a response surface method (RSM) to obtain experimental parameters of the dyeing test experiment. The response surface method optimizes the combination of multiple parameters by constructing a quadratic polynomial model to obtain the best experimental parameters. The RSM can effectively reduce the number of experiments and provide rich information.

[0093] The embodiment can greatly reduce the number of experiments, save material costs and time costs of experiments, and improve prediction accuracy by processing multiple test points by the dyeing prediction model to obtain simulation test results.

[0094] Optionally, step S50, i.e., determining the target dyeing process meeting the dyeing requirement according to the test results, comprises:

[0095] S501, if the test results meet the dyeing requirement, determining the target dyeing process according to the experimental parameters.

[0096] Understandably, if the test results meet the dyeing requirement, the target dyeing process can be determined according to the experimental parameters. The experimental parameters belong to small-scale test processes, and the target dyeing process can be designed according to industry experience, pilot test is carried out under conditions close to production, and the feasibility and stability of the target dyeing process are verified.

[0097] In the embodiment, the test results meet the dyeing requirement, which indicates that the prediction accuracy of the dyeing prediction model is high, the number of experiments can be greatly reduced, and the material costs and time costs of experiments can be saved.

[0098] Optionally, step S50, i.e., determining the target dyeing process meeting the dyeing requirement according to the test results, comprises:

[0099] S502, if the test results do not meet the dyeing requirement, optimizing the dyeing prediction model according to the test results to obtain a dyeing prediction optimization model;

[0100] S503, processing the dyeing requirement by the dyeing prediction optimization model to obtain an optimized dyeing process and a credibility of the optimized dyeing process;

[0101] S504, setting optimized experimental parameters of an optimized dyeing test experiment according to the optimized dyeing process and the optimized dyeing process, and obtaining optimized test results of the optimized dyeing test experiment;

[0102] S505, if the optimization test result meets the dyeing requirement, determining the target dyeing process according to the optimization experiment parameter;

[0103] S506, if the optimization test result does not meet the dyeing requirement, further optimizing the dyeing prediction optimization model according to the optimization test result until the finally obtained test result meets the dyeing requirement.

[0104] Understandably, if the test result does not meet the dyeing requirement, the dyeing prediction optimization model is optimized according to the test result, and the dyeing prediction optimization model is obtained, which can help to improve the prediction accuracy of the dyeing prediction optimization model. After obtaining the dyeing prediction optimization model, the dyeing prediction optimization model can be used to process the dyeing requirement to obtain a new dyeing process and credibility, i.e. the optimized dyeing process and the credibility of the optimized dyeing process. Then, the optimization experiment parameter of the optimization dyeing test experiment is set according to the optimized dyeing process and the optimized dyeing process, and the optimization test result of the optimization dyeing test experiment is obtained. If the optimization test result meets the dyeing requirement, the target dyeing process is determined according to the optimization experiment parameter. If the optimization test result does not meet the dyeing requirement, the dyeing prediction optimization model is further optimized according to the optimization test result until the finally obtained test result meets the dyeing requirement. In some examples, if the optimization test result does not meet the dyeing requirement, but the deviation from the dyeing requirement is less than a preset threshold (which can be 10%), the experiment parameter of the dyeing test experiment can be adjusted according to the industry experience, and then the target dyeing process meeting the dyeing requirement is determined.

[0105] In the embodiment, if the test result does not meet the dyeing requirement, the dyeing prediction optimization model is optimized according to the test result, and the dyeing prediction optimization model is obtained, which can improve the accuracy of the dyeing prediction optimization model. Through more accurate model prediction, the number of trial and error can be reduced, and the development speed of the dyeing process is accelerated. The optimized dyeing prediction optimization model can guide the design of better dyeing process, and the dyeing efficiency is improved.

[0106] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0107] In an embodiment, a dyeing device based on a dyeing prediction model is provided, which corresponds to the dyeing method based on the dyeing prediction model in the above embodiment. As shown in the figure, the dyeing device based on the dyeing prediction model comprises: Figure 2

[0108] The dyeing requirement acquisition module 10 is used to acquire the dyeing requirement; ​

[0109] a model prediction module 20 configured to process the dyeing demand by a dyeing prediction model to obtain an initial dyeing process and a confidence level of the initial dyeing process;

[0110] a test parameter setting module 30 configured to set test parameters of a dyeing test according to the initial dyeing process and the confidence level;

[0111] a test result acquisition module 40 configured to acquire test results of the dyeing test;

[0112] a target dyeing process determination module 50 configured to determine a target dyeing process meeting the dyeing demand according to the test results.

[0113] Optionally, the dyeing device based on a dyeing prediction model further comprises a model construction module, and the model construction module comprises:

[0114] a historical data acquisition unit configured to acquire historical dyeing data;

[0115] a model construction unit configured to train a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models; the dyeing prediction model comprises the plurality of dyeing index prediction models.

[0116] Optionally, the dyeing index prediction model comprises a color accuracy prediction model; and the model construction unit comprises:

[0117] a first preprocessing unit configured to perform first preprocessing on the historical dyeing data to obtain a color feature data set;

[0118] a color accuracy prediction model construction unit configured to train the color feature data set by a support vector regression algorithm to obtain the color accuracy prediction model.

[0119] Optionally, the dyeing index prediction model comprises a color fastness prediction model; and the model construction unit comprises:

[0120] a second preprocessing unit configured to perform second preprocessing on the historical dyeing data to obtain a color fastness feature data set;

[0121] a color fastness prediction model construction unit configured to train the color fastness feature data set by a logistic regression algorithm to obtain the color fastness prediction model.

[0122] Optionally, the test parameter setting module 30 comprises:

[0123] a range extraction unit configured to extract a value range and a parameter confidence level of each dyeing parameter from the initial dyeing process and the confidence level;

[0124] The test point setting unit is configured to set a plurality of test points according to the value range and the parameter reliability;

[0125] The simulation result obtaining unit is configured to process the plurality of test points by using the dyeing prediction model to obtain simulation test results.

[0126] The experiment parameter obtaining unit is configured to process the simulation test results by using a response surface method to obtain the experiment parameters.

[0127] Optionally, the target dyeing process 50 comprises:

[0128] The first target dyeing process determining unit is configured to determine the target dyeing process according to the experiment parameters if the test results meet the dyeing requirements.

[0129] Optionally, the target dyeing process 50 comprises a second target dyeing process determining unit, which is configured to:

[0130] If the test results do not meet the dyeing requirements, the dyeing prediction model is optimized according to the test results to obtain a dyeing prediction optimization model.

[0131] The dyeing prediction optimization model is used to process the dyeing requirements to obtain an optimized dyeing process and a reliability of the optimized dyeing process.

[0132] The optimized experiment parameters of the optimized dyeing test experiment are set according to the optimized dyeing process and the optimized dyeing process, and the optimized test results of the optimized dyeing test experiment are obtained.

[0133] If the optimized test results meet the dyeing requirements, the target dyeing process is determined according to the optimized experiment parameters.

[0134] If the optimized test results do not meet the dyeing requirements, the dyeing prediction optimization model is further optimized according to the optimized test results until the finally obtained test results meet the dyeing requirements.

[0135] The specific limitations of the dyeing device based on the dyeing prediction model can be referred to the limitations of the dyeing method based on the dyeing prediction model in the above, which will not be repeated here. Each module in the dyeing device based on the dyeing prediction model described above can be realized by software, hardware and a combination thereof in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0136] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes a readable storage medium and internal memory. The readable storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database stores data related to a staining method based on a staining prediction model. The network interface communicates with external terminals via a network connection. When the computer-readable instructions are executed by the processor, they implement a staining method based on a staining prediction model. The readable storage medium provided in this embodiment includes both non-volatile and volatile readable storage media.

[0137] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor performs the following steps when executing the computer-readable instructions:

[0138] Obtain the dyeing requirements;

[0139] The staining requirements are processed by a staining prediction model to obtain the initial staining process and the reliability of the initial staining process;

[0140] The experimental parameters for the staining test are set according to the initial staining process and the confidence level.

[0141] Obtain the experimental results of the staining test;

[0142] Based on the test results, a target dyeing process that meets the dyeing requirements is determined.

[0143] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media stores computer-readable instructions, which, when executed by one or more processors, perform the following steps:

[0144] Obtain the dyeing requirements;

[0145] The staining requirements are processed by a staining prediction model to obtain the initial staining process and the reliability of the initial staining process;

[0146] The experimental parameters for the staining test are set according to the initial staining process and the confidence level.

[0147] obtaining a test result of the dyeing test experiment;

[0148] determining a target dyeing process meeting the dyeing requirement according to the test result.

[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through computer readable instructions, and the computer readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer readable instructions are executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM) and the like.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0151] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A dyeing method based on a dyeing prediction model, characterized in that, The method comprises the following steps: acquiring dyeing requirements; the dyeing requirements comprise color requirements, fabric types, dye types, and dyeing fastness requirements; processing the dyeing requirements by a dyeing prediction model to obtain an initial dyeing process and a credibility of the initial dyeing process; the dyeing prediction model comprises a plurality of dyeing index prediction models, the dyeing prediction model comprises a color accuracy prediction model and a color fastness prediction model; the credibility of the initial dyeing process comprises the credibility of each parameter in the process; setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility; acquiring test results of the dyeing test experiment; determining a target dyeing process meeting the dyeing requirements according to the test results; the step of setting the experimental parameters of the dyeing test experiment according to the initial dyeing process and the credibility comprises: extracting a value range and a parameter credibility of each dyeing parameter from the initial dyeing process and the credibility; setting a plurality of test points according to the value range and the parameter credibility; processing the plurality of test points by the dyeing prediction model to obtain simulated test results; processing the simulated test results by a response surface method to obtain the experimental parameters; the step of determining the target dyeing process meeting the dyeing requirements according to the test results comprises: if the test results do not meet the dyeing requirements, optimizing the dyeing prediction model according to the test results to obtain a dyeing prediction optimization model; processing the dyeing requirements by the dyeing prediction optimization model to obtain an optimized dyeing process and a credibility of the optimized dyeing process; setting optimized experimental parameters of an optimized dyeing test experiment according to the optimized dyeing process and the optimized dyeing process, and acquiring optimized test results of the optimized dyeing test experiment; if the optimized test results meet the dyeing requirements, determining the target dyeing process according to the optimized experimental parameters; if the optimized test results do not meet the dyeing requirements, further optimizing the dyeing prediction optimization model according to the optimized test results until the finally obtained test results meet the dyeing requirements.

2. The dyeing method based on a dyeing prediction model according to claim 1, characterized in that, Before the step of processing the dyeing requirements by the dyeing prediction model, the method further comprises: acquiring historical dyeing data; training a plurality of dyeing index initial models according to the historical dyeing data to obtain a plurality of dyeing index prediction models.

3. The dyeing method based on a dyeing prediction model according to claim 2, characterized in that, The step of training the plurality of dyeing index initial models according to the historical dyeing data to obtain the plurality of dyeing index prediction models comprises: performing first preprocessing on the historical dyeing data to obtain a color feature data set; training the color feature data set by a support vector regression algorithm to obtain the color accuracy prediction model.

4. The dyeing method based on a dyeing prediction model according to claim 2, wherein, The step of training the plurality of dyeing index initial models according to the historical dyeing data to obtain the plurality of dyeing index prediction models comprises: performing second preprocessing on the historical dyeing data to obtain a color fastness feature data set; training the color fastness feature data set by a logistic regression algorithm to obtain the color fastness prediction model.

5. The dyeing method based on a dyeing prediction model according to claim 1, wherein, the step of determining the target dyeing process meeting the dyeing requirements according to the test results comprises: If the test result meets the dyeing requirement, the target dyeing process is determined according to the experimental parameters.

6. A dyeing apparatus based on a dyeing prediction model, characterized by, The method comprises the following steps: an acquisition module for acquiring a dyeing requirement, wherein the dyeing requirement comprises color requirements, fabric types, dye types, and dyeing fastness requirements; a model prediction module for processing the dyeing requirement by using a dyeing prediction model to obtain an initial dyeing process and a credibility of the initial dyeing process, wherein the dyeing prediction model comprises a plurality of dyeing index prediction models, the dyeing prediction model comprises a color accuracy prediction model and a color fastness prediction model, and the credibility of the initial dyeing process comprises the credibility of each parameter in the process; an experimental parameter setting module for setting experimental parameters of a dyeing test experiment according to the initial dyeing process and the credibility; an acquisition module for acquiring a test result of the dyeing test experiment; a target dyeing process determination module for determining a target dyeing process meeting the dyeing requirement according to the test result; the experimental parameter setting module comprises: an extraction range unit for extracting a value range of each dyeing parameter and a parameter credibility from the initial dyeing process and the credibility; a test point setting unit for setting a plurality of test points according to the value range and the parameter credibility; an analog result obtaining unit for processing the plurality of test points by using the dyeing prediction model to obtain analog test results; an experimental parameter obtaining unit for processing the analog test results by using a response surface method to obtain the experimental parameters; the target dyeing process determination module comprises a second target dyeing process determination unit, which is configured to: if the test result does not meet the dyeing requirement, optimize the dyeing prediction model according to the test result to obtain a dyeing prediction optimization model; process the dyeing requirement by using the dyeing prediction optimization model to obtain an optimized dyeing process and a credibility of the optimized dyeing process; set optimized experimental parameters of an optimized dyeing test experiment according to the optimized dyeing process and the optimized dyeing process, and acquire an optimized test result of the optimized dyeing test experiment; if the optimized test result meets the dyeing requirement, determine the target dyeing process according to the optimized experimental parameters; if the optimized test result does not meet the dyeing requirement, further optimize the dyeing prediction optimization model according to the optimized test result until a final test result meeting the dyeing requirement is obtained. 7.A computer device, comprising a memory, a processor, and computer readable instructions stored in the memory and running on the processor, characterized in that, The processor executes the computer readable instructions to implement the dyeing method based on the dyeing prediction model according to any one of claims 1 to 5.

8. One or more readable storage media storing computer readable instructions, wherein, The computer readable instructions are executed by one or more processors to cause the one or more processors to execute the dyeing method based on the dyeing prediction model according to any one of claims 1 to 5.

Images