Fabric dyeing equipment running machine parameter optimization recommendation method, device, equipment and medium

Abstract

The invention discloses a fabric dyeing equipment running machine parameter optimization recommendation method and device, equipment and a medium, and the method comprises the steps: obtaining the cloth type information of a plurality of production batches of an order system and the production information of a corresponding batch in a production execution system, carrying out the coding of the cloth type information and the production information, and obtaining cloth type feature data and process feature data, associating the seed distribution characteristic data with the process characteristic data to form process data items, calculating the seed distribution information of a target production batch by adopting a similarity algorithm when the target production batch information is detected, screening out preliminary process data items in a similarity threshold range, and storing the preliminary process data items in a database; and calculating the process characteristic data of the preliminary process data items by adopting a GBDT gradient decision tree to obtain recommended optimal line machine parameter data, so that the line machine parameter data of the dyeing equipment can be quickly output through system recommendation, and meanwhile, the batch quality problem caused by personal errors is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and in particular to a method, device, equipment and medium for optimizing and recommending machine parameters of a fabric dyeing device. Background Art

[0002] In the textile industry, fabric printing and dyeing is an important link to give fabrics color and enhance their added value. Generally speaking, the dye diffuses, penetrates and adheres to the surface of the fabric through the repeated interaction of the fabric with the dyeing liquid in the dyeing machine to complete the entire dyeing process. During the dyeing process, the machine parameters of the dyeing machine have a great influence on the dyeing effect of the fabric. At present, the machine parameters of most dyeing machine equipment still rely mainly on the personal experience and intuition of the operator. This highly manual method exposes the following pain points: First, the dyeing quality is unstable. Due to the subjectivity and uncertainty of manual settings, even the same batch and the same fabric type may cause uneven color and substandard color fastness during the dyeing process due to slight differences in parameter settings. Second, the production efficiency is low. The process of manually setting parameters is not only time-consuming and labor-intensive, but also difficult to quickly adapt to changes in market demand. When it is necessary to adjust the production batch or change the fabric type, the workers need to re-explore and set the parameters. This process not only prolongs the production cycle, but also increases production costs and reduces overall production efficiency. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, equipment and medium for optimizing and recommending machine parameters of a fabric dyeing device, aiming to solve the problems of low efficiency and unstable batch quality caused by the need to reset machine parameters for each production batch in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a method for optimizing and recommending machine parameters of a fabric dyeing equipment, the method comprising:

[0005] Obtain fabric information of multiple production batches in the order system and production information of corresponding batches in the production execution system;

[0006] Encoding the fabric type information and the production information respectively to obtain fabric type characteristic data and process characteristic data, and associating the fabric type characteristic data and the process characteristic data to form a process data entry;

[0007] When the target production batch information is detected, the cloth type information of the target production batch is calculated using a similarity algorithm, and preliminary process data entries are screened out within a similarity threshold range;

[0008] The GBDT gradient decision tree is used to calculate the process characteristic data of the preliminary process data items to obtain the recommended optimal machine parameter data.

[0009] In a second aspect, an embodiment of the present invention provides a device for optimizing and recommending machine parameters of a fabric dyeing device, the device comprising:

[0010] A data acquisition unit, used to acquire fabric information of multiple production batches in the order system and production information of corresponding batches in the production execution system;

[0011] A data forming unit, used for respectively encoding the fabric type information and the production information to obtain fabric type characteristic data and process characteristic data, and associating the fabric type characteristic data and the process characteristic data to form a process data entry;

[0012] A preliminary calculation unit, for calculating the cloth type information of the target production batch by using a similarity algorithm when the target production batch information is detected, and screening out preliminary process data items within a similarity threshold range;

[0013] The parameter recommendation unit is used to calculate the process characteristic data of the preliminary process data items by using the GBDT gradient decision tree to obtain the recommended optimal machine parameter data.

[0014] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for optimizing and recommending machine parameters of the fabric dyeing equipment described in the first aspect is implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the method for optimizing and recommending machine parameters of fabric dyeing equipment described in the first aspect.

[0016] The embodiment of the present invention provides a method, device, equipment and medium for optimizing and recommending the operation parameters of a fabric dyeing equipment. The method includes: obtaining the fabric type information of multiple production batches in the order system and the production information of the corresponding batches in the production execution system, respectively encoding the fabric type information and the production information to obtain fabric type feature data and process feature data, associating the fabric type feature data and the process feature data to form a process data entry, and when the target production batch information is detected, using a similarity algorithm to calculate the fabric type information of the target production batch, screening out preliminary process data entries within the similarity threshold range, using a GBDT gradient decision tree to calculate the process feature data of the preliminary process data entries, and obtaining the recommended optimal operation parameter data. The present application can quickly output the operation parameter data of the dyeing equipment through system recommendation, and at the same time reduce the batch quality problems caused by human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0018] Figure 1 A diagram of the application environment of the method for optimizing the machine parameters of a fabric dyeing device provided by an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of a process flow of a method for optimizing machine parameters of a fabric dyeing device provided by an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of a sub-process of a method for optimizing and recommending machine parameters of a fabric dyeing device provided by an embodiment of the present invention;

[0021] Figure 4 A schematic diagram of calculating and fitting a certain input parameter of a gradient decision tree model provided in an embodiment of the present invention;

[0022] Figure 5 Another schematic diagram of a process flow of a method for optimizing and recommending machine parameters of a fabric dyeing device provided by an embodiment of the present invention;

[0023] Figure 6 A diagram of a recommended device for optimizing machine parameters of a fabric dyeing device provided by an embodiment of the present invention;

[0024] Figure 7 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0027] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0028] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] In order to facilitate the understanding of the present application scheme, the application environment applicable to the embodiments of the present application is first introduced.

[0030] Figure 1 FIG. 1 is a schematic diagram of an application scenario of a method for optimizing machine parameters of a fabric dyeing device in an embodiment. Figure 1 As shown, the application environment includes a controller 1000 for collecting and issuing machine parameter data of fabric dyeing equipment, databases 2000-200N, a server 3000 and a display terminal 4000. The machine parameter optimization recommendation method for fabric dyeing equipment is applied to the server 3000. The server 3000 can exchange data with the databases 2000-200N through the network and save it in the data processing server. The server 3000 can be a cloud server or a local server. The machine parameters output by the server calculation and processing are displayed in the display terminal 4000. The user can adjust the data. If the confirmation is completed, it can be sent to the dyeing equipment 5000 through the controller 1000. The dyeing equipment PLC controls the operation of the fan, main pump, cloth lifting wheel and other devices according to the input parameters. The optimal machine parameter data is output through the system recommendation, which solves the problem of low efficiency and unstable batch quality caused by the need to reset parameters for new production batches.

[0031] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0032] The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0033] Figure 2 Schematic diagram of a method for optimizing the parameters of a fabric dyeing machine in an embodiment, which can be executed in a local server or a cloud server. The cloud server can be implemented in software and / or hardware, and can be composed of two or more physical entities or one physical entity.

[0034] Specifically, Figure 2 As shown, the method for optimizing the machine parameters of the fabric dyeing equipment may include the following steps:

[0035] S110, obtaining fabric type information of multiple production batches in the order system and production information of corresponding batches in the production execution system.

[0036] In one embodiment, the order system is an enterprise ERP system (Enterprise Resource Planning) enterprise resource planning management. The ERP system is a comprehensive enterprise management software that integrates multiple core business modules such as the company's finance, supply chain, production, and human resources. Its main functions include financial management (such as general ledger, cost, and budget management), supply chain management (purchasing, inventory, and sales), production management (planning and scheduling, workshop operations, and quality control), and human resource management (personnel, attendance, and salary). The ERP system can improve the operational efficiency of the enterprise and break the information island. This system obtains customer order data from the ERP system through the API (Application Programming Interface) interface. The customer order data includes customer name, customer code, fabric information, production batch number, quantity requirements, product delivery date, dark, medium, and light colors, process routes, etc., where the fabric information includes fabric name, yarn count, fiber composition and proportion, gram weight and width, grey fabric manufacturer, etc. Generally speaking, after the dyeing and finishing factory receives the customer's fabric printing and dyeing order, the system will automatically generate a production batch number, which is a unique identifier used to distinguish different production batches. Each production batch may differ in raw materials, production time, process parameters, etc. The production batch number can be used to accurately track and manage the production process.

[0037] In one of the embodiments, the production execution system is the enterprise MES system (Manufacturing Execution System). The MES system (Manufacturing Execution System) is a production information management system for the workshop execution layer of manufacturing enterprises. Its main functions include manufacturing data management, planning and scheduling management, production scheduling management, inventory management, quality management, etc. It collects, organizes and stores various data in the production process, including raw material information, process parameters, equipment parameters, etc., formulates reasonable production plans and schedules according to order requirements and enterprise resource conditions, ensures that production tasks are carried out in an orderly manner, coordinates personnel, equipment, materials and other resources in real time during the production process, solves sudden problems and bottlenecks in the production process, and ensures that product quality meets standards through analysis and real-time monitoring of production data. This system obtains key production information corresponding to the production batch number from the MES system through the API (Application Programming Interface) interface. The production information includes machine parameters, dyeing procedures and dyeing formulas. In one embodiment, the production information may also include information about the corresponding production equipment. The equipment information includes dyeing equipment brand, model, machine name, number of tubes, data collection points, etc.; the machine parameters include fan speed, main pump speed, cloth lifting speed, nozzle opening and closing status, the dyeing procedures include pre-treatment, dyeing, and post-treatment, and the dyeing formula includes the type and weight of dye auxiliaries.

[0038] Furthermore, after obtaining the fabric type information of multiple production batches in the order system and the production information of the corresponding batches in the production execution system, it also includes performing data preprocessing operations on the fabric type information and production information, and the preprocessing operations include cleaning the data set and calibrating the gradient range.

[0039] It should be noted that there may be exactly the same records in the data set, which may be caused by data input errors, repeated data collection, etc. For example, in a data list, there may be multiple records representing the same device and the same collection point, and the recording time and value of these data are exactly the same. It also includes near-duplicate data: some data records may be very similar in some fields, but not exactly the same, such as the speed of fan 1 and fan 2, etc. Furthermore, it also includes irrelevant data. Some data fields may be irrelevant to specific analysis tasks. These fields can be removed to reduce the amount of data and improve the efficiency of data analysis. Methods for removing redundant data include: deduplication processing, data similarity calculation and feature selection, etc.

[0040] Specifically, in a data set, some fields of some data records may have missing values. Missing values ​​may be caused by errors in the data collection process, data loss, data not recorded, etc. Generally, by adopting constant filling, mean filling, median filling, regression filling and interpolation filling methods, this embodiment adopts the mean filling method; outliers refer to data points that are significantly different from other data in the data set. Outliers may be caused by data collection errors, data input errors, abnormal data fluctuations, etc. This embodiment adopts the method of replacing outliers and smoothing. By using moving average method, exponential smoothing method and other methods for smoothing, the outliers are gradually approached to the level of normal data.

[0041] Furthermore, the data preprocessing operation also includes calibration of the gradient range. In one embodiment, according to manual experience, the relationship between the cloth lifting speed and the average cloth weight is a gradient increasing relationship. However, in actual situations, some human factors cause the cloth lifting speed to be inaccurate, too small or too large, and form a non-increasing relationship with the average cloth weight. Therefore, this embodiment selects this part of the data, and calibrates this data, modifies the cloth lifting speed that is out of the gradient range, and uses a gradient historical value closest to the cloth weight as the new cloth lifting speed. After processing, the accuracy of the model prediction is greatly improved. Table 1 is a data anomaly discrimination table. As described in Table 1, the data of sequence numbers 1-3 are gradient increasing. As the average cloth weight increases, the cloth lifting speed increases. However, the data of sequence number 4 has an average cloth weight between 320-330, and the cloth lifting speed is not between 220-240. Therefore, the cloth lifting speed of sequence number 4 belongs to the data within the non-gradient range, and a data correction method is adopted to change the cloth lifting speed data to be within the gradient range.

[0042] Table 1 Data abnormality discrimination

[0043] Serial number Average cloth weight Fabric lifting speed Is it abnormal? 1 310 220 normal 2 320 230 normal 3 330 240 normal 4 325 250 abnormal

[0044] S120, respectively encode the fabric type information and the production information to obtain fabric type characteristic data and process characteristic data, and associate the fabric type characteristic data and the process characteristic data to form a process data entry.

[0045] In one of the embodiments, the fabric type name is encoded, the trained fabric type information is filtered out from the historical data, and the fabric type name is encoded. Table 2 is an encoding example of some fabric type names after desensitization. As described in Table 2, the encoding increases sequentially starting from 0, such as fabric type name: new ** cotton, encoding: 0, fabric type name: luxury ** yarn, encoding: 1. When a new fabric type name is detected, it is automatically filtered out to generate a data dictionary for automatic encoding.

[0046] Table 2 Fabric name code

[0047] Fabric Name Fabric code New cotton 0 Luxury yarn 1 Rice** Velvet 2 New ** velvet 3 New fashion ** velvet 4 After washing** sweatshirt 5 New cool cotton 6 Mocha**cotton 7 Rope pattern 8

[0048] In one of the embodiments, the process name is encoded, and the process refers to the sub-process of dyeing, which is mainly divided into three categories: pre-treatment, dyeing, and post-treatment. Table 3 is an example of the encoding of some process names. As described in Table 3, the encoding increases sequentially starting from 0, such as process name: color correction, encoding: 0; process name: pre-treatment, encoding: 2; the system often subdivides and creates new processes, so the process code will also be dynamically increased, and new sub-process names will be automatically selected according to historical data, and the data dictionary will be automatically encoded. The above-mentioned fabric name code and process name code are fabric feature data.

[0049] Table 3 Process name code

[0050]

[0051]

[0052] In one of the embodiments, the opening and closing status of the nozzles is encoded. Generally, the number of nozzles is determined according to the number of tubes of the dyeing equipment. The number of nozzles of some dyeing equipment corresponds to the number of tubes one by one, and the number of nozzles of some dyeing equipment is 1.5 to 2 times the number of tubes. In this embodiment, there are three nozzles. Whichever nozzle is opened, the model gives the corresponding nozzle number. The process parameter value of the nozzle in the production system data is 1-8, and the corresponding relationship is as follows:

[0053] nozzle_dict["1"]="1"

[0054] nozzle_dict["2"]="2"

[0055] nozzle_dict["3"]="3"

[0056] nozzle_dict["4"]="1+2"

[0057] nozzle_dict["5"]="1+3"

[0058] nozzle_dict["6"]="2+3"

[0059] nozzle_dict["7"]="1+2+3"

[0060] nozzle_dict["8"]=""

[0061] In one of the embodiments, nozzle_dict["1"] = "1" indicates that nozzle 1 is in the open state, and nozzle_dict["4"] = "1+2" ​​indicates that nozzle 1 and nozzle 2 are both in the open state. When performing feature engineering on the open and closed state of each nozzle, nozzle 1, nozzle 2 and nozzle 3 are coded and standardized, represented by a three-digit number [1.1.0], where the three digits represent whether nozzle 1, nozzle 2 and nozzle 3 are opened or not. A value of 1 indicates opening, and 0 indicates not opening. According to the method of this embodiment, the opening and closing state of the nozzle of each historical batch is formed into process feature data. The fabric feature data and the process feature data are associated to form process data entries and stored in the process database. The process data entries can be classified and sub-itemed by color, fabric composition or machine name and stored in the process database, which helps process personnel to quickly retrieve.

[0062] S130. When target production batch information is detected, a similarity algorithm is used to calculate the fabric type information of the target production batch, and preliminary process data items are screened out within a similarity threshold range.

[0063] When the system detects the target production batch information, it will start the similarity algorithm to calculate the fabric information. The fabric information includes fabric name, yarn count, fiber composition and proportion, gram weight, width, grey fabric manufacturer, etc. Through the similarity algorithm, the system compares this information with the existing process database. For example, if the target batch of fabric is similar to a certain process data in the database in terms of fiber composition and yarn count, it will be marked. Within the set similarity threshold range, the system filters out preliminary process data entries from the database. These entries may include dyeing procedures, machine parameters, dyeing formulas and other related content of similar fabrics, providing a basis for further determination of precise process data.

[0064] In one embodiment, if Figure 3 As shown, step S130 includes sub-steps S131, S133 and S135.

[0065] S131. Segment and integrate the cloth type information of the target production batch and a certain historical production batch to form a normalized vector group.

[0066] In one of the embodiments, the system inputs a target batch of fabrics: T1 = {rayon nylon, 40S viscose nylon, viscose 66.0% + nylon 28.3% + spandex 5.7%, 147, 220, manufacturer A}, the target batch of fabrics is the fabric to be produced and processed, and the historical fabric information in the process database is traversed, searched and compared according to the fabric information, and a vector group is formed by combining two of them. Specifically, if the system matches a historical batch of fabrics: T2 = {Yabi cashmere, 40S Yasel viscose, viscose 71.7% + acrylic 24.0% + spandex 4.3%, 157, 257, manufacturer B}, the segmentation data of the grouping vectors of the target batch of fabrics T1 and the historical batch of fabrics T2 are merged and normalized to form a vector group. The execution results are as follows: T = {rayon nylon, Yabi cashmere, 40S, viscose, cotton nylon, Yasser, viscose 66.0%, nylon 28.3%, spandex 5.7%, 147, 220, manufacturer A, viscose 71.7%, acrylic 24.0%, spandex 4.3%, 157, 257, manufacturer B}, and so on. The target batch fabric types and multiple historical batch fabric types in the process database are combined into a vector group in pairs.

[0067] S133. Count the occurrence frequencies of the seed information in the target production batch and a certain historical production batch in the statistical vector group to form a target production batch frequency group and a historical production batch frequency group.

[0068] In one embodiment, the frequency of occurrence of the normalized T vector component words in the original vector group Ti is calculated and marked with Si respectively. For each word Wi in the set, if Wi appears in Ti, it is recorded as 1, otherwise it is 0. The execution result is as follows:

[0069] The frequency array of the vector group T in the target batch seed vector T1: S1 = {1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0}

[0070] The frequency array of the vector group T in the historical batch seeding vector T2: S2 = {0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1}

[0071] S135. Calculate the similarity value between the target production batch frequency group and the historical production batch frequency group using cosine similarity, and select preliminary process data items within the similarity threshold range.

[0072] Calculate the similarity between the two vectors S1 and S2. The cosine similarity formula is: cos(θ) = S1→×S2→ / |S1→|×|S2→|, where S1→ and S2→ are two vectors, S1→×S2→ is the inner product of the two vectors, and |ST1→| and |S2→| are the moduli (lengths) of the two vectors.

[0073] The system can preset historical batch fabrics with a similarity greater than 20% as examples of process parameters for reference. In this embodiment, the similarity between the target batch fabric T1 and the historical batch fabric T2 is calculated to be 30% through the above cosine similarity formula, which is within the preset threshold range. The process characteristic data formed by the production information of the historical batch fabric T2 is then obtained as the input of the next model. If the historical batch fabric with a similarity less than 20% is not within the threshold range, it is excluded. The historical batch fabrics in the process library are calculated and screened one by one in this way, and finally a number of preliminary process data entries are obtained.

[0074] S140, using the GBDT gradient decision tree to calculate the process characteristic data of the preliminary process data items to obtain the recommended optimal machine parameter data.

[0075] Specifically, it also includes inputting the process characteristic data as parameters into the decision tree, and gradually narrowing the optimal parameter range through a tree structure, wherein the objective function constructed by the decision tree includes a loss function and a regularization term, and each time the function trains a new decision tree, it must fit the residual of the previous result, so that the current residual is smaller than the previous one.

[0076] In one of the embodiments, GBDT is an integrated learning algorithm of the Boosting type, which obtains the final prediction result by superimposing the prediction results of multiple decision trees. On the basis of the preliminary process data entries, a number of preliminary process data entries are further trained using the gradient decision tree algorithm to further refine the prediction, taking into account more factors affecting the dyeing effect, such as sub-process type, cloth weight, number of tubes, equipment model, etc., and gradually narrowing the optimal parameter range through the tree structure. This embodiment is based on the classification of GBDT nozzle usage coding and the prediction regression of fan speed, main pump speed, and cloth lifting speed, and the learners used are all CART regression trees.

[0077] Specifically, the ensemble learning algorithm in this embodiment constructs the n-tree model according to formula (1):

[0078]

[0079] The objective function of the model for predicting dyeing machine process parameters includes the loss function and the regularization term as shown in (2):

[0080]

[0081] in is the prediction error of the i-th process parameter sample of the model, the smaller the error, the better;

[0082]

[0083] (3) where Ω(f k ) is a regular term used to control the complexity of the model, where γ and λ are penalty coefficients, T represents the number of leaf nodes in the CART tree, and w represents the score of the leaf node. The smaller the value, the lower the complexity and the stronger the generalization ability.

[0084] Each time the model trains a new tree, it must fit the residual of the previous result. Each time the function increment is increased, the residual of the new round must be reduced as much as possible. When it reaches the tth time, the objective function of the model is (4):

[0085]

[0086] (4)Where: is the prediction result of each process parameter sample of the model for the t-1th time; f t (x i ) is the function increment of the tth iteration; Ω(f t ) is a regular term; the ultimate goal of model training is to find an f that minimizes the objective function t (x i ), the Taylor second-order expansion of equation (4) at x = 0 is used to approximate the approximate objective function as equation (5):

[0087]

[0088] Use Taylor expansion to approximate the original objective function, and change f t (x i ) is regarded as Δx, Yes t (x i )The first derivative at x=0; Yes t (x i ) is the second-order derivative function at x=0; removing the items that do not affect the final optimization of the objective function, the simplified expression is as follows (6):

[0089]

[0090] In one embodiment, Figure 4 A schematic diagram of fitting a certain input parameter of a gradient decision tree provided in an embodiment of the present invention, such as Figure 4As shown, the cloth lifting speed of a certain historical batch of cloth is 180. By training weak learner 1 (decision tree 1), the predicted speed of the target batch of cloth is 150. At this time, the difference between the predicted speed and the actual speed is 30 (residual). Then train weak learner 2 (decision tree 2) to fit the residual 30, and so on, until the residual value is less than the given threshold. According to the above objective function calculation, the final result of the predicted cloth lifting speed of the target batch of cloth is: 150+20+8+2=180.

[0091] In another embodiment, Table 4 shows an example of model input parameters. The target batch of cloth types T1={rayon nylon, 40S viscose nylon, viscose 66.0%+nylon 28.3%+spandex 5.7%, 147, 220, A manufacturer} described in S130 is combined with process characteristic data W1={number of tubes 4, equipment model gas-liquid machine A model, cloth weight 1978, process type pre-treatment}. After model calculation and fitting, the machine parameters are obtained as shown in Table 5, and the recommended machine parameter results are output: cloth lifting speed 240, main pump speed 85, fan speed 98, nozzle [1,1,0]. By predicting and recommending the machine parameters of the dyeing machine, the accuracy of the machine parameters and the one-time success rate of product production are improved, and the batch quality problems caused by human errors are reduced.

[0092] Table 4 Gradient decision tree input parameters

[0093]

[0094]

[0095] Table 5 Output parameters of gradient decision tree

[0096] Cylinder No. Fabric lifting speed Main pump speed Fan speed nozzle t001 240 85 98 [1,1,0]

[0097] The recommended method for optimizing the parameters of the fabric dyeing equipment also includes the following steps. For details, please refer to Figure 5 , Figure 5 Another schematic flow chart of a method for optimizing and recommending machine parameters of a fabric dyeing machine provided in an embodiment of the present invention.

[0098] S150. After the learning model is put into operation, the actual operating parameters of the dyeing equipment are automatically and regularly collected, and the fabric type information and production information of the corresponding production batch are synchronized into the database.

[0099] In one of the embodiments, after the learning model is launched, an efficient data collection and synchronization process is started. Specifically, the system will automatically collect the actual operating parameters of the dyeing equipment at set time intervals such as 1 hour or 2 hours. These parameters include key data such as fan speed, main pump speed, cloth lifting speed, nozzle opening and closing status, etc. At the same time, the model will also synchronize the cloth type information of the current production batch (such as cloth type name, yarn count, fiber composition and proportion, gram weight, width, grey cloth manufacturer, etc.) and production information (such as dyeing process, dyeing formula, etc.) to the database. This series of operations ensures the timeliness and accuracy of database information, and provides comprehensive and reliable data support for subsequent production analysis, quality control, process optimization and other work.

[0100] S160, regularly process the cloth type information and production information, store them in the training table, and mark them with a mark to be trained.

[0101] In one embodiment, the system will periodically perform data processing operations on fabric type information and production information. This information is sorted, analyzed and converted to conform to the format required by the training model. After the processing is completed, the data is stored in the training table and marked with a to-be-trained mark so that the subsequent training model can accurately identify the data to be used and ensure the smooth progress of the training process.

[0102] S170, regularly inputting data with to-be-trained identification into the machine learning model for training, and generating a new version of the model file to be released.

[0103] In one embodiment, the system extracts the data with the to-be-trained identification according to the set time rules and inputs it into the machine learning model. These data contain rich cloth variety information and production information, which are the key materials for model training. During the training process, the model analyzes and learns the data through complex algorithms, and continuously adjusts its own parameters and weights to optimize the model's prediction and decision-making capabilities. When the training is completed, a new version of the model file to be released is generated. This file carries the improved model. After further evaluation and verification, it can be used in process optimization, quality control and other links in actual production, making the production process more accurate and efficient.

[0104] S180. Regularly obtain the model file to be released, and automatically call the model upgrade interface to upgrade.

[0105] In one embodiment, the system will periodically obtain the model file to be released, and this process is automated. After obtaining the file, the model upgrade interface is automatically called to start the upgrade program. This operation does not require manual intervention, which can ensure that the model is updated in time, and the model is continuously optimized to adapt to new cloth type information and production information changes, ensuring that the production process is more efficient and accurate.

[0106] In the method for optimizing and recommending machine parameters of fabric dyeing equipment provided in an embodiment of the present invention, fabric type information of multiple production batches in an order system and production information of corresponding batches in a production execution system are obtained, the fabric type information and production information are respectively encoded to obtain fabric type feature data and process feature data, the fabric type feature data and the process feature data are associated to form process data entries, and when target production batch information is detected, a similarity algorithm is used to calculate the fabric type information of the target production batch, preliminary process data entries are screened out within the similarity threshold range, and a GBDT gradient decision tree is used to calculate the process feature data of the preliminary process data entries to obtain the recommended optimal machine parameter data. The present invention can quickly output the dyeing equipment machine parameter data through system recommendation, and at the same time reduce batch quality problems caused by human errors.

[0107] The embodiment of the present invention also provides a device for optimizing and recommending machine parameters of a fabric dyeing machine. The device for optimizing and recommending machine parameters of a fabric dyeing machine can be configured in a user terminal or a server. The device for optimizing and recommending machine parameters of a fabric dyeing machine is used to execute any embodiment of the aforementioned method for optimizing and recommending machine parameters of a fabric dyeing machine. Figure 6 , Figure 6 A schematic block diagram of a device for optimizing and recommending machine parameters of a fabric dyeing machine provided in an embodiment of the present invention.

[0108] like Figure 6 As shown, the device 200 for optimizing and recommending machine parameters of a fabric dyeing equipment includes a data acquisition unit 201 , a data formation unit 203 , a preliminary calculation unit 205 and a parameter recommendation unit 207 .

[0109] The data collection unit 201 is used to transmit the machine parameter data of a certain production batch of fabric dyeing equipment collected by the gateway to the data warehouse.

[0110] The data preprocessing unit 203 is used to preprocess and standardize the machine parameter data in the data warehouse.

[0111] In a specific embodiment, the data preprocessing unit 203 includes removing redundant data, filling missing values, correcting abnormal values, filtering extreme abnormal data due to sensor failure or noise interference, and standardizing the preprocessed data according to the process characteristics of different equipment to ensure that the data between different equipment and batches are comparable and consistent;

[0112] The data feature extraction unit 205 is used to segment the machine parameter data according to the start time and end time of the batch, extract the process feature data of the batch, and filter out the stable interval of the process feature data during operation according to the set time window.

[0113] In a specific embodiment, the data feature extraction unit 205 includes a sub-unit: a stable interval calculation unit, which is used to obtain the name of the processing equipment corresponding to the batch, retrieve all the collection points of the processing equipment in the data warehouse, and calculate the range with the smallest residual of each collection point within the time range limited by the batch start time and the batch end time as the stable interval.

[0114] The data association unit 207 is used to calculate the optimal parameter value according to the process characteristic data in the stable interval, associate the optimal parameter value with the fabric category information of the batch, form a process data entry and store it in the process library.

[0115] In a specific embodiment, the data feature extraction unit 207 includes subunits: an optimal parameter value calculation unit, which is used to extract the numerical value with the highest frequency of occurrence in the stable interval as the optimal parameter value of the process feature data; a classification storage unit: used to associate the optimal parameter value with the fabric category information of the batch, the fabric category information includes fabric type, fabric composition, color and color depth, and the fabric category information is classified and stored in the process library.

[0116] The data recommendation unit 209 is used to match the fabric category information of the new batch input with the process data entries in the process library when a new production batch is detected. If the match is successful, the machine parameter data of the process data entries is recommended. If the match is unsuccessful, prediction is performed through the equipment learning model, wherein the relationship between the machine parameter data of historical batches and the production effect is learned by the model, and the optimal machine parameter data is recommended.

[0117] In a specific embodiment, the data recommendation unit 209 includes subunits: a data matching unit, which sets a threshold value based on the target fabric type component content and target process parameter in the new production batch, traverses the process data entries in the process library according to the threshold value, and recommends the closest machine parameter data. A device learning unit, which is used to recommend parameter data using one or more combinations of random forest, gradient boosting decision tree and neural network methods.

[0118] In a specific embodiment, the device 200 for optimizing and recommending machine parameters of fabric dyeing equipment further includes a data sending unit, which sends the machine parameter data to the fabric dyeing equipment for execution; an effect evaluation unit: which evaluates the accuracy of the machine parameter data through the fabric production effect after execution. If the evaluation result is unqualified, manual parameter adjustment is performed, and the manually adjusted data is updated to the process library. The production effect includes product quality and production stability.

[0119] The device for optimizing and recommending machine parameters of fabric dyeing equipment provided in the embodiment of the present invention applies the above-mentioned method for optimizing and recommending machine parameters of fabric dyeing equipment, preprocesses and standardizes the collected machine parameter data of fabric dyeing equipment, extracts the process characteristic data of the batch, calculates the optimal parameter value based on the process characteristic data in the stable interval, and associates the optimal parameter value with the fabric category information of the batch. When a new production batch is detected, the fabric category information is matched with the process data entry in the process library. If the match is successful, the machine parameter data is recommended. If the match is unsuccessful, the machine parameter data is predicted through the equipment learning model, and the recommended optimal machine parameter data is output. Through the above-mentioned method, the process parameters can be quickly output through system recommendation, and batch quality problems caused by human errors are reduced.

[0120] The above-mentioned device for optimizing and recommending machine parameters of fabric dyeing equipment can be realized in the form of a computer program. The computer program can be used in Figure 7 Runs on the computer device shown.

[0121] See also Figure 7 , Figure 7 1 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a user terminal or a server for executing a method for optimizing machine parameters of a fabric dyeing device to detect defects in plants.

[0122] See also Figure 7 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0123] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a method for optimizing and recommending machine parameters of a textile dyeing device, wherein the storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0124] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0125] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the method for optimizing the machine parameters of the fabric dyeing equipment.

[0126] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above-mentioned method for optimizing the machine parameters of the fabric dyeing equipment.

[0128] Those skilled in the art will understand that Figure 7 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 7 The embodiments shown are consistent and will not be described again here.

[0129] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0130] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps included in the above-mentioned method for optimizing the machine parameters of the fabric dyeing equipment are implemented.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0132] In the several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. Units with the same function may also be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0134] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a computer-readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a magnetic disk or an optical disk.

[0136] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for optimizing and recommending machine parameters of a fabric dyeing equipment, characterized in that: include: Obtain fabric information of multiple production batches in the order system and production information of corresponding batches in the production execution system; Encoding the fabric type information and the production information to obtain fabric type characteristic data and process characteristic data, and associating the fabric type characteristic data with the process characteristic data to form a process data entry; When the target production batch information is detected, the cloth type information of the target production batch is calculated using a similarity algorithm, and preliminary process data entries are screened out within a similarity threshold range; The GBDT gradient decision tree is used to calculate the process characteristic data of the preliminary process data items to obtain the recommended optimal machine parameter data.

2. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 1, characterized in that: When the target production batch information is detected, the fabric type information of the target production batch is calculated using a similarity algorithm, and preliminary process data items are screened out within the similarity threshold range, including: Perform word segmentation encoding on the fabric information of the target production batch and a certain historical production batch to form a normalized vector group; Counting the occurrence frequencies of the seeding information of the vector group in the target production batch and a certain historical production batch, respectively, to form a target production batch frequency group and a historical production batch frequency group; The cosine similarity is used to calculate the similarity value between the target production batch frequency group and the historical production batch frequency group, and the preliminary process data items within the similarity threshold range are selected.

3. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 2, characterized in that: The GBDT gradient decision tree is used to calculate the process characteristic data of the preliminary process data items to obtain the recommended optimal machine parameter data, including: The process characteristic data is input as parameters into the decision tree, and the optimal parameter range is gradually narrowed through the tree structure, wherein the objective function constructed by the decision tree includes a loss function and a regularization term, and each time the objective function trains a new decision tree, it must fit the residual of the previous result so that the current residual is smaller than the previous one.

4. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 1, characterized in that: Obtain fabric type information of multiple production batches in the order system and production information of corresponding batches in the production execution system, wherein the fabric type information includes fabric type name, yarn count, fiber composition and proportion, gram weight and width, manufacturer, etc., and the production information includes machine parameters, dyeing process, number of tubes, equipment model, fabric weight and dyeing formula.

5. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 4, characterized in that: The machine parameters include fan speed, main pump speed, cloth lifting speed, nozzle opening and closing status, the dyeing process includes pre-treatment, dyeing, and post-treatment, and the dyeing formula includes the type and weight of dye auxiliary agents.

6. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 1, characterized in that: After obtaining the fabric type information of multiple production batches in the order system and the production information of the corresponding batches in the production execution system, it also includes performing data preprocessing operations on the fabric type information and production information, and the preprocessing operations include cleaning the data set and calibrating the gradient range.

7. The method for optimizing and recommending machine parameters of fabric dyeing equipment according to claim 1, characterized in that: The method further comprises the following steps: Step 1: After the learning model is online, the actual operating parameters of the dyeing equipment are automatically collected at regular intervals, and the fabric type information and production information of the corresponding production batch are synchronized to the database; Step 2: Regularly process the cloth type information and production information, store them in a training table, and mark them with a mark to be trained; Step 3: regularly input the data with the to-be-trained identification into the machine learning model for training, and generate a new version of the model file to be released; Step 4: Regularly obtain the model file to be released, and automatically call the model upgrade interface for upgrade.

8. A device for optimizing and recommending machine parameters for fabric dyeing equipment, characterized in that: The device comprises: A data acquisition unit, used to acquire fabric information of multiple production batches in the order system and production information of corresponding batches in the production execution system; A data forming unit, used for respectively encoding the fabric type information and the production information to obtain fabric type characteristic data and process characteristic data, and associating the fabric type characteristic data and the process characteristic data to form a process data entry; A preliminary calculation unit, for calculating the cloth type information of the target production batch by using a similarity algorithm when the target production batch information is detected, and screening out preliminary process data items within a similarity threshold range; The parameter recommendation unit is used to calculate the process characteristic data of the preliminary process data items by using the GBDT gradient decision tree to obtain the recommended optimal machine parameter data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for optimizing and recommending machine parameters of a fabric dyeing equipment according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for optimizing and recommending machine parameters of a fabric dyeing equipment as described in any one of claims 1 to 7 is implemented.

Images