Digital control management method and system for printing and dyeing industry

Abstract

The invention provides a digital control management method and system for the printing and dyeing industry, and relates to the technical field of data processing, and the method comprises the steps: obtaining an order queue which comprises a plurality of printing and dyeing orders; determining a priority parameter of each printing and dyeing order; determining each working procedure required by each printing and dyeing order; in combination with the priority parameters of the printing and dyeing orders, a digital control model is constructed with the purpose of minimizing the order comprehensive completion time, and the printing and dyeing machines are scheduled and controlled to conduct automatic printing and dyeing according to the working procedures; obtaining a printing and dyeing image after the printing and dyeing order is completed; judging whether printing and dyeing flaws exist according to the printing and dyeing image; if yes, a supplementary order is generated, the priority parameter of the supplementary order is set to be the maximum value, and the supplementary order is sent to the order queue again; otherwise, finishing the printing and dyeing order. According to the invention, enterprises can be helped to effectively utilize resources, unnecessary transportation time, production line idle time and machine debugging time are reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a digital control management method and system for the printing and dyeing industry. Background Art

[0002] Printing and dyeing is a very important link in the textile industry, with many complex processes, mainly including: impregnation, bleaching, cleaning, dyeing, color fixing, washing, printing design, plate making, printing, steam setting, rinsing, softening, finishing and packaging. Each process often needs to be completed on different equipment, such as impregnation in an impregnation machine, bleaching in a bleaching machine, cleaning in a washing machine, etc.

[0003] With the growing demand for customized manufacturing, small batch production has gradually become an important aspect of modern manufacturing companies. However, this customized production for different types may result in different processes in the printing and dyeing process to be carried out in different companies, increasing the transportation time during the transfer process. At the same time, customized services also increase the debugging time of the machine.

[0004] At present, faced with the increasing demand for small-batch printing and dyeing, most companies still adopt the method of placing an order first and then arranging production to carry out printing and dyeing operations, which leads to the dispersion of production tasks and the need to frequently transport semi-finished products to the next link, switch production tasks and debug machines, which increases transportation time, production line idle time and machine debugging time, and reduces production efficiency. Summary of the invention

[0005] In order to solve the technical problem that in the prior art, facing the increasing number of small-batch printing and dyeing demands, most companies still adopt the method of placing an order first and then arranging production to carry out printing and dyeing operations, which leads to the dispersion of production tasks, the need to frequently transport semi-finished products to the next link, switch production tasks and debug machines, which increases transportation time, production line idle time and machine debugging time, and reduces production efficiency. The present invention provides a digital control management method and system for the printing and dyeing industry.

[0006] The technical solution provided by the embodiment of the present invention is as follows: First aspect: An embodiment of the present invention provides a digital control management method for the printing and dyeing industry, comprising: S1: obtaining an order queue, wherein the order queue includes a plurality of printing and dyeing orders; S2: Determine the priority parameters of each printing and dyeing order; S3: Determine the various processes required for each printing and dyeing order; S4: Combine the priority parameters of each printing and dyeing order, with the goal of minimizing the overall order completion time, build a digital control model, and schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process; S5: Acquire the printing and dyeing image after the printing and dyeing order is completed; S6: Determine whether there are printing and dyeing defects based on the printing and dyeing image; if so, generate a supplementary order, set the priority parameter of the supplementary order to the maximum value and re-send it to the order queue; otherwise, complete the printing and dyeing order.

[0007] Second aspect: An embodiment of the present invention provides a digital control and management system for the printing and dyeing industry, comprising: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the digital control management method for the printing and dyeing industry as described in the first aspect is implemented.

[0008] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, in the face of the increasing demand for small-batch printing and dyeing, the priority parameters of each printing and dyeing order are combined with the goal of minimizing the comprehensive completion time of the order. A digital control model is constructed to schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process. This can reduce the completion time of each printing and dyeing order as much as possible, help enterprises effectively utilize resources, reduce unnecessary transportation time, production line idle time and machine debugging time, and improve production efficiency.

[0009] (2) In the present invention, the printing and dyeing images after the printing and dyeing order is completed are obtained, and the printing and dyeing image analysis is performed automatically, so as to quickly determine whether there are printing and dyeing defects. Once a defect is found, the system can automatically generate a supplementary order, readjust its priority, and optimize the production scheduling to ensure that the defective printing and dyeing orders are processed in time and maintain the continuity of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a digital control management method for the printing and dyeing industry provided by an embodiment of the present invention; Figure 2A structural schematic diagram of a digital control management system for the printing and dyeing industry provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0013] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0014] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0015] Reference Manual Attached Figure 1 , showing a flow chart of a digital control management method for the printing and dyeing industry provided by an embodiment of the present invention.

[0016] The embodiment of the present invention provides a digital control management method for the printing and dyeing industry, which can be implemented by a digital control management device for the printing and dyeing industry, and the digital control management device for the printing and dyeing industry can be a terminal or a server. The processing flow of the digital control management method for the printing and dyeing industry can include the following steps: S1: Get the order queue.

[0017] Among them, the order queue includes multiple printing and dyeing orders.

[0018] S2: Determine the priority parameters of each printing and dyeing order.

[0019] In a possible implementation, S2 specifically includes: determining the priority parameter of each printing and dyeing order according to the following formula:

[0020] in, P i Indicates i The priority parameters of a printing and dyeing order, le i Indicates i Customer level for printing and dyeing orders, c i Indicates i The order amount of a printing and dyeing order, de i Indicates iThe remaining delivery period of the printing and dyeing orders, α 1 represents the weight coefficient of the customer level, α 2 represents the weight coefficient of the order amount, α 3 represents the weight coefficient of the remaining delivery period.

[0021] It should be noted that customer level is an indicator that reflects the status and importance of a customer in an enterprise. For important customers, enterprises usually pay more attention and attention to maintain their satisfaction and loyalty. By considering customer level, it is possible to ensure that orders from important customers are given priority, improve customer satisfaction and loyalty, and help maintain long-term cooperative relationships. The order amount is directly related to the revenue and profit of an enterprise. Generally speaking, orders with higher amounts mean higher profits and importance. Therefore, taking the order amount as a priority consideration can enable enterprises to prioritize orders that can bring higher profits and maximize profits. The remaining delivery period is an important indicator of order delivery. Considering the remaining delivery period can help enterprises avoid fines or compensation due to order delays. By giving higher priority to orders with shorter remaining delivery periods, it is possible to ensure on-time delivery and maintain the reputation and credibility of the enterprise.

[0022] In the present invention, the priority of the order is comprehensively evaluated based on important factors such as customer level, order amount and remaining delivery period, so that the printing and dyeing production scheduling can be arranged more effectively, making the production scheduling more reasonable and efficient.

[0023] S3: Determine the various processes required for each printing and dyeing order.

[0024] It should be noted that different printing and dyeing orders may have different processes. Some orders do not require printing design, some orders use different dyeing methods, and so on.

[0025] S4: Based on the priority parameters of each printing and dyeing order, with the goal of minimizing the overall order completion time, a digital control model is constructed to schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process.

[0026] In a possible implementation, S4 specifically includes sub-steps S401 to S404: S401: In combination with the priority parameters of each printing and dyeing order, the objective function of the digital control model is constructed with the goal of minimizing the comprehensive completion time of the order.

[0027] Optionally, the objective function of the digital control model is specifically:

[0028] in, f ( ) represents the objective function, XRepresents the scheduling plan, which includes the execution order of printing and dyeing orders and the execution machines of each process required for printing and dyeing orders. T i Indicates i The comprehensive order completion time for each printing and dyeing order, OT i Indicates i The timeout period for a printing and dyeing order, represents the timeout penalty coefficient, I Represents a collection of printing and dyeing orders.

[0029] Among them, technicians in this field can set the timeout penalty coefficient according to actual conditions. The present invention does not limit the size.

[0030] It should be noted that the timeout penalty coefficient is introduced , punishing overdue orders. Such a design can encourage the system to avoid order overtime as much as possible during scheduling, ensure that orders are completed on time, avoid possible fines or compensation, and help maintain the company's reputation and credibility.

[0031] Furthermore, the setting of minimizing the total completion time in the objective function can make the system more inclined to choose orders that can be completed as soon as possible when arranging printing and dyeing orders, thereby effectively reducing the overall order completion time. This helps companies improve production efficiency and meet customer needs more quickly.

[0032] Among them, the calculation method of the comprehensive order completion time of each printing and dyeing order is as follows:

[0033] in, P i Indicates i The priority parameters of a printing and dyeing order, t i Indicates i The completion time of a printing and dyeing order.

[0034] It should be noted that by introducing the priority parameter P i , the priority of different orders can be taken into account when calculating the comprehensive completion time. Orders with higher priority ( P i Larger) will be given a greater weight when calculating the total completion time, making the system more inclined to prioritize these important orders. This helps ensure that important orders are completed in a timely manner and meet customer needs.

[0035] The completion time of each printing and dyeing order is as follows:

[0036] in, tg j Indicates j The operation time of each process, Indicates j The first process and the j +1 The transfer time between processes, when the adjacent j The first process and the j +1 When the process is completed on the same machine , Indicates j The equipment debugging time of a process is when the process parameters of two adjacent processes processed by a machine are exactly the same. , J i Indicates i The collection of processes required for a printing and dyeing order.

[0037] It should be noted that the calculation method of completion time comprehensively considers the operation time, transfer time and equipment debugging time, making the final completion time more comprehensive and accurate. The system can fully consider the relationship between processes and the status of machines when calculating the completion time, so as to better optimize the production scheduling plan, reduce idle time and waiting time, and improve production efficiency.

[0038] S402: Add constraints to the digital control model.

[0039] Optionally, the constraints specifically include: Process execution constraints: Each process can only be processed by one machine, and after completing one process, it will move on to the next process.

[0040] It should be noted that the process execution constraints ensure that each process can only be processed by one machine, and that one process can be transferred to the next process only after one process is completed. Such constraints ensure the reasonable order and flow of the processes in the printing and dyeing process, avoiding confusion and wrong execution order. This is very important for the printing and dyeing industry, because the order and flow of different processes have an important impact on the quality and appearance of the final product.

[0041] Machine execution constraints: Each machine can only execute one process at a time, and will move on to the next process after completing one process.

[0042] It should be noted that the machine execution constraint ensures that each machine can only execute one process at a time. This helps to maximize the use of machine resources and avoid resource waste and conflicts. In a printing and dyeing factory, machines are usually expensive assets. Reasonable constraints can ensure that each machine has a task to execute in the same time period, improving production efficiency and equipment utilization.

[0043] Process uniqueness constraint: Each printing and dyeing order has a unique process, and other processes cannot be executed before the previous process is completed.

[0044] It should be noted that the process uniqueness constraint ensures that each printing and dyeing order has a unique process, and other processes cannot be executed before the previous process is completed. This can avoid process conflicts and errors, and ensure that the printing and dyeing process of each order is clear and orderly. This is very important for quality control and process management in production, and can avoid production problems caused by process duplication or errors.

[0045] S403: Under the constraints of the constraints, with the goal of minimizing the function value of the objective function, the digital control model is solved to obtain the optimal scheduling solution.

[0046] It should be noted that the best production scheduling solution can be obtained by minimizing the value of the objective function, that is, minimizing the comprehensive order completion time. This means that the factory can arrange the execution order of printing and dyeing orders and the use of machines more effectively, thereby minimizing the completion time of each order. Optimized production scheduling can improve production efficiency, shorten delivery cycle, and reduce production costs.

[0047] Optionally, S403 specifically includes: under the constraints of the constraint conditions, with the goal of minimizing the function value of the objective function, solving the digital control model through an improved genetic algorithm to obtain the best scheduling solution.

[0048] Among them, the genetic algorithm (GA) is an optimization algorithm that simulates the biological evolution process in nature and is often used to solve complex optimization problems. It simulates the biological evolution process and gradually optimizes the solution to the problem.

[0049] In a possible implementation, S403 specifically includes: The inverse of the objective function is used as the fitness function of the genetic algorithm.

[0050] It should be noted that using the inverse of the objective function as the fitness function is equivalent to converting the minimization problem into a maximization problem. In genetic algorithms, optimization is usually performed for the maximization problem because it is easier to find a solution with high fitness.

[0051] Initialize the population Q 1. The population contains multiple individuals, each of which represents a feasible scheduling solution.

[0052] Optionally, the method for initializing the population is as follows: According to the priority parameters of each printing and dyeing order, a printing and dyeing order is randomly selected, and the execution machine with the shortest estimated job completion time is selected for each process in the printing and dyeing order. The next printing and dyeing order is randomly selected until the arrangement of all printing and dyeing orders is completed, forming a feasible scheduling plan.

[0053] It should be noted that by randomly selecting and arranging processes according to the priority parameters of the printing and dyeing order, and selecting the execution machine with the shortest current estimated job completion time for each process in the printing and dyeing order, and then generating an initial solution, the reliability of the initial solution can be improved, and the efficiency of subsequent calculations can be improved.

[0054] Among them, the random selection probability of printing and dyeing orders is specifically:

[0055] in, Pr i Indicates i The probability of randomly selecting a printing and dyeing order, P i Indicates i Priority parameter for each printing and dyeing order.

[0056] It should be noted that the use of Sigmoid function as the calculation method for the random selection probability of printing and dyeing orders can ensure the rationality, smoothness and nonlinear characteristics of the probability. It also has certain adjustability and interpretability, which helps to more accurately represent the possibility of the printing and dyeing order being selected.

[0057] The estimated completion time of the job is calculated as follows:

[0058] in, Tr k Indicates the estimated completion time of the job. J k Indicates the process of all printing and dyeing orders k The total number of processes that can be executed on the execution machine, tg j Indicates j The operation time of a process.

[0059] It should be noted that the method of calculating the estimated job completion time as the sum of the operation times of all processes that can be executed on a certain machine is helpful in generating an effective initial solution.

[0060] In traditional genetic algorithms, elite selection or roulette wheel selection is often used, which is easy to converge prematurely and fall into a local optimal solution. In order to solve this problem, the present invention provides an improved genetic algorithm, which is specifically: Based on the Q-Learning algorithm, individuals in the population are selected to form a population. Q 2.

[0061] The gene space constructed by the population is used as the action strategy space of the Q-Learning algorithm, and the change in fitness value after executing the randomly selected action is used as the immediate reward for executing the selected action. The population is randomly selected and the Q-Learning algorithm is updated. Q Matrix, and then the next iteration can be selected based on the updated Q matrix:

[0062] in, S t Indicates t The state at the iteration, A t Indicates t The randomly selected action at the iteration, Indicates in status S t Perform a random selection of actions A t of Q value, β represents the learning rate, R t+1 Indicates in status S t Perform a random selection of actions A t Instant rewards, λ represents the discount factor, Indicates the next state S t+1 Optional actions The largest Q Value, also known as long-term reward.

[0063] In the present invention, the Q-Learning algorithm can dynamically update the Q value according to the individual's behavior and reward situation, so the population is more adaptive when selecting individuals. By taking the change in fitness value after executing a randomly selected action as an immediate reward, the algorithm can be more inclined to select individuals that bring positive rewards, thereby improving the overall adaptability of the population. At the same time, in the Q-Learning algorithm, individuals will consider the current state and Q value when selecting actions, but will also randomly select actions with a certain probability, which helps the population to conduct more extensive exploration in the solution space. This exploratory enhancement helps avoid falling into a local optimal solution, making it more likely to find a global optimal solution.

[0064] For populations Q 2 Perform crossover operation, from the populationQ 2 randomly selects two individuals as parents, generates a random number, and compares the random number with the crossover probability P e Compare the size, if the random number is less than the crossover probability P e , then the parent is cross-operated to generate new individuals to form a population Q 3. New individuals y 1. y 2 is generated as follows:

[0065] in, x 1. x 2 represents the parent body, rand Represents a random number between 0 and 1.

[0066] It should be noted that by randomly selecting two parents for the crossover operation, the diversity of the population can be maintained. The crossover operation combines the genetic information of two different individuals to produce new individuals, which helps to introduce new gene combinations and increase the diversity of the population, thereby making it more likely to search for better solutions. The crossover operation helps to prevent the population from converging to a local optimal solution too early. When the individuals in the population have certain genetic differences, these differences can be integrated through crossover, which may produce better individuals, thus avoiding being trapped in a local optimal solution and being unable to jump out.

[0067] Among them, the crossover probability P e Specifically:

[0068] in, P e represents the crossover probability, P e,max represents the maximum crossover probability, P e,min represents the minimum crossover probability, represents the fitness value of the current individual, represents the average fitness value of the population, Represents the maximum fitness value among individuals.

[0069] It should be noted that the crossover probability is dynamically adjusted according to the current individual fitness value and the average fitness value of the population, making the crossover probability adaptive. When the individual fitness value is higher than the average fitness value of the population, the crossover probability will increase, increasing the possibility of crossover between better individuals; conversely, when the individual fitness value is lower than the average fitness value of the population, the crossover probability will decrease, reducing the possibility of crossover between poor individuals. Such adjustments can more effectively guide the population to develop in a better direction.

[0070] For populations Q 3 Perform mutation operation, from the population Q Randomly select a parent from 3 x 3. Generate a random number and compare it with the mutation probability P m Compare the size, if the random number is smaller than the mutation probability P m , then for the parent x 3 Perform mutation operations to generate new individuals y 3Replace the original individuals to form a population Q 4. New individuals y 3 is generated as follows:

[0071] in, x 3 represents the parent body, rand Represents a random number between 0 and 1.

[0072] It should be noted that the mutation operation introduces randomness, making the gene combination of the new individual different from that of the original individual, thereby increasing the diversity of the population. This helps to prevent the population from falling into a local optimal solution and improves the global search ability of the algorithm. In the mutation operation, the genes of the new individual may come from some parts of the original individual. When the original individual contains excellent genes, these genes may be retained and passed on to the new individual. This helps to retain excellent characteristics and performance during the evolution process.

[0073] Among them, the mutation probability P m Specifically:

[0074] in, P m represents the probability of mutation, P m,max represents the maximum mutation probability, P m,min represents the minimum mutation probability, represents the fitness value of the current individual, represents the average fitness value of the population, Represents the maximum fitness value among individuals.

[0075] It should be noted that the mutation probability is dynamically adjusted according to the current individual fitness value and the average fitness value of the population, making the mutation probability adaptive. When the individual fitness value is higher than the average fitness value of the population, the mutation probability will increase, increasing the possibility of mutation between better individuals; conversely, when the individual fitness value is lower than the average fitness value of the population, the mutation probability will decrease, reducing the possibility of mutation between poor individuals. Such adjustments can more effectively guide the population to develop in a better direction.

[0076] Determine whether the number of iterations has reached the maximum number of iterations. If so, take the individual with the highest fitness value as the best scheduling solution. Otherwise, return to the step of selecting individuals in the population and continue iterating.

[0077] S404: Through the optimal scheduling plan, each printing and dyeing machine is scheduled and controlled to perform automated printing and dyeing according to the process.

[0078] In the present invention, by solving the digital control model through an improved genetic algorithm, a better scheduling solution can be obtained, which can avoid local optimality, adapt to different problem scenarios, handle complex constraints, automate the search process and take advantage of parallelization, thereby improving the efficiency and performance of the digital control management method for the printing and dyeing industry.

[0079] S5: Acquire the printing and dyeing image after the printing and dyeing order is completed.

[0080] S6: Determine whether there are printing and dyeing defects based on the printing and dyeing image. If so, generate a supplementary order, set the priority parameter of the supplementary order to the maximum value and re-send it to the order queue. Otherwise, complete the printing and dyeing order.

[0081] It should be noted that obtaining the printing and dyeing images after the printing and dyeing order is completed and performing automated printing and dyeing image analysis can quickly determine whether there are printing and dyeing defects. Once a defect is found, the system can automatically generate a supplementary order and readjust its priority to optimize production scheduling to ensure that the defective printing and dyeing orders are processed in a timely manner and maintain the continuity of the production process.

[0082] In a possible implementation manner, determining whether the printing and dyeing image has printing and dyeing defects in S6 specifically includes: determining whether the printing and dyeing defects exist through a printing and dyeing defect detection model based on a convolutional neural network.

[0083] Among them, Convolutional Neural Network (CNN) is a type of deep learning neural network that is specifically designed to process data with a grid-like structure, such as images and videos. It is one of the key technologies that has achieved great success in fields such as image recognition and speech recognition.

[0084] Optionally, in S6, judging whether there are printing and dyeing defects in the printing and dyeing image by using a printing and dyeing defect detection model based on a convolutional neural network specifically includes: In the input layer of the printing and dyeing defect detection model, the printing and dyeing image is input.

[0085] In the convolution layer of the printing and dyeing defect detection model, the printing and dyeing image is convolved to obtain a feature image.

[0086] In the pooling layer of the printing and dyeing defect detection model, the feature image is pooled and compressed.

[0087] In the fully connected layer of the printing and dyeing defect detection model, all feature images are summarized.

[0088] In the classification layer of the printing and dyeing defect detection model, the probability of the printing and dyeing image belonging to various categories is determined based on the summarized feature images. The categories include normal categories and various printing and dyeing defect categories:

[0089] in, P y represents a probability set, P iy Indicates that the printed image belongs to i The probability of the category, n Represents the total number of categories, Softmax( ) represents the Softmax activation function, h represents the features summarized by the fully connected layer, W represents the weight between the fully connected layer and the classification layer, b Represents the bias between the fully connected layer and the classification layer.

[0090] In the output layer of the printing and dyeing defect detection model, the category with the largest probability value is taken as the final category of the printing and dyeing image, and whether there is a printing and dyeing defect is determined based on the final category.

[0091] In the present invention, the printing and dyeing defect detection model based on the convolutional neural network realizes the automatic detection of printing and dyeing images, and can detect defects without human intervention. This can save human resources in industrial production and also reduce the errors caused by human factors. At the same time, the model can identify multiple categories of printing and dyeing defects, including various possible abnormal situations, rather than being limited to the binary classification of normal and abnormal. In this way, various problems of printing and dyeing images can be detected more comprehensively, and the comprehensiveness and accuracy of quality control can be improved.

[0092] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, in the face of the increasing demand for small-batch printing and dyeing, the priority parameters of each printing and dyeing order are combined with the goal of minimizing the comprehensive completion time of the order. A digital control model is constructed to schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process. This can reduce the completion time of each printing and dyeing order as much as possible, help enterprises effectively utilize resources, reduce unnecessary transportation time, production line idle time and machine debugging time, and improve production efficiency.

[0093] (2) In the present invention, the printing and dyeing images after the printing and dyeing order is completed are obtained, and the printing and dyeing image analysis is performed automatically, so as to quickly determine whether there are printing and dyeing defects. Once a defect is found, the system can automatically generate a supplementary order, readjust its priority, and optimize the production scheduling to ensure that the defective printing and dyeing orders are processed in time and maintain the continuity of the production process.

[0094] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a digital control management system for printing and dyeing industry provided by the present invention.

[0095] The present invention also provides a digital control management system 20 for the printing and dyeing industry, which is applied to the above-mentioned digital control management method for the printing and dyeing industry, comprising: Processor 201.

[0096] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the digital control management method for the printing and dyeing industry in the method embodiment is implemented.

[0097] The digital control management system 20 for the printing and dyeing industry provided by the present invention can execute the above-mentioned digital control management method for the printing and dyeing industry and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate on it.

[0098] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: (1) In the present invention, in the face of the increasing demand for small-batch printing and dyeing, the priority parameters of each printing and dyeing order are combined with the goal of minimizing the comprehensive completion time of the order. A digital control model is constructed to schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process. This can reduce the completion time of each printing and dyeing order as much as possible, help enterprises effectively utilize resources, reduce unnecessary transportation time, production line idle time and machine debugging time, and improve production efficiency.

[0099] (2) In the present invention, the printing and dyeing images after the printing and dyeing order is completed are obtained, and the printing and dyeing image analysis is performed automatically, so as to quickly determine whether there are printing and dyeing defects. Once a defect is found, the system can automatically generate a supplementary order, readjust its priority, and optimize the production scheduling to ensure that the defective printing and dyeing orders are processed in time and maintain the continuity of the production process.

[0100] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0101] There are a few points to note: (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0102] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0103] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0104] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A digital control management method for printing and dyeing industry, characterized in that: include: S1: obtaining an order queue, wherein the order queue includes a plurality of printing and dyeing orders; S2: Determine the priority parameters of each printing and dyeing order; S3: Determine the various processes required for each printing and dyeing order; S4: Combine the priority parameters of each printing and dyeing order, with the goal of minimizing the overall order completion time, build a digital control model, and schedule and control each printing and dyeing machine to perform automated printing and dyeing according to the process; S5: Acquire the printing and dyeing image after the printing and dyeing order is completed; S6: judging whether there are printing and dyeing defects according to the printing and dyeing image; if so, generating a supplementary order, setting the priority parameter of the supplementary order to the maximum value and re-sending it to the order queue; Otherwise, complete the printing and dyeing order.

2. The digital control management method for printing and dyeing industry according to claim 1 is characterized in that: The S2 is specifically: The priority parameters of each printing and dyeing order are determined according to the following formula: in, P i Indicates i The priority parameters of a printing and dyeing order, le i Indicates i Customer level for printing and dyeing orders, c i Indicates i The order amount of a printing and dyeing order, de i Indicates i The remaining delivery period of the printing and dyeing orders, α 1 represents the weight coefficient of the customer level, α 2 represents the weight coefficient of the order amount, α 3 represents the weight coefficient of the remaining delivery period.

3. The digital control management method for printing and dyeing industry according to claim 1 is characterized in that: The S4 specifically includes: S401: combining the priority parameters of each printing and dyeing order, and taking minimizing the comprehensive order completion time as the goal, constructing the objective function of the digital control model; S402: adding constraints of the digital control model; S403: Under the constraints of the constraint conditions, with the goal of minimizing the function value of the objective function, solving the digital control model to obtain an optimal scheduling solution; S404: Through the optimal scheduling solution, each printing and dyeing machine is scheduled and controlled to perform automated printing and dyeing according to the process.

4. The digital control management method for printing and dyeing industry according to claim 3 is characterized in that: The objective function of the digital control model is specifically: in, f ( ) represents the objective function, X represents a scheduling plan, which includes the execution order of the printing and dyeing orders and the execution machines of each process required for the printing and dyeing orders. T i Indicates i The comprehensive order completion time for each printing and dyeing order, OT i Indicates i The timeout period for a printing and dyeing order, represents the timeout penalty coefficient, and I represents the printing and dyeing order set; Among them, the calculation method of the comprehensive order completion time of each printing and dyeing order is as follows: in, P i Indicates i The priority parameters of a printing and dyeing order, t i Indicates i The completion time of each printing and dyeing order; The completion time of each printing and dyeing order is as follows: in, tg j Indicates j The operation time of each process, Indicates j The first process and the j +1 The transfer time between processes, when the adjacent j The first process and the j +1 When the process is completed on the same machine , Indicates j The equipment debugging time of a process is when the process parameters of two adjacent processes processed by a machine are exactly the same. , J i Indicates i A collection of processes required for a printing and dyeing order.

5. The digital control management method for printing and dyeing industry according to claim 3 is characterized in that: The constraints specifically include: Process execution constraints: Each process can only be processed by one machine, and after completing one process, it will move on to the next process; Machine execution constraints: Each machine can only execute one process at a time, and after completing one process, it will move on to the next process; Process uniqueness constraint: Each printing and dyeing order has a unique process, and other processes cannot be executed before the previous process is completed.

6. The digital control management method for printing and dyeing industry according to claim 3 is characterized in that: The S403 is specifically as follows: Under the constraints of the constraints, with the goal of minimizing the function value of the objective function, the digital control model is solved through an improved genetic algorithm to obtain an optimal scheduling solution.

7. The digital control management method for printing and dyeing industry according to claim 6 is characterized in that: The S403 specifically includes: The inverse of the objective function is used as the fitness function of the genetic algorithm; Initialize the population Q 1. The population contains multiple individuals, each of which represents a feasible scheduling solution; Based on the Q-Learning algorithm, individuals in the population are selected to form a population. Q 2; For populations Q 2 Perform crossover operation, from the population Q In 2, two individuals are randomly selected as parents, a random number is generated, and the random number is compared with the crossover probability. If the random number is less than the crossover probability, a crossover operation is performed on the parents to generate new individuals to form a population. Q 3; For populations Q 3 Perform mutation operation, from the population Q In step 3, an individual is randomly selected, a random number is generated, and the random number is compared with the mutation probability. If the random number is smaller than the mutation probability, a mutation operation is performed on the individual to generate a new individual to replace the original individual to form a population. Q 4; Determine whether the number of iterations has reached the maximum number of iterations; if so, take the individual with the highest fitness value as the optimal parameter; otherwise, return to the step of selecting individuals in the population and continue iterating.

8. The digital control management method for printing and dyeing industry according to claim 1 is characterized in that: The step S6 of judging whether the printing and dyeing image has printing and dyeing defects is specifically as follows: The printing and dyeing defect detection model based on convolutional neural network is used to determine whether there are printing and dyeing defects.

9. The digital control management method for printing and dyeing industry according to claim 8, characterized in that: The step S6 of determining whether the printing and dyeing image has printing and dyeing defects by using a printing and dyeing defect detection model based on a convolutional neural network specifically includes: In the input layer of the printing and dyeing defect detection model, the printing and dyeing image is input; In the convolution layer of the printing and dyeing defect detection model, the printing and dyeing image is convolved to obtain a feature image; In the pooling layer of the printing and dyeing defect detection model, the feature image is subjected to pooling processing to compress the feature image; In the fully connected layer of the printing and dyeing defect detection model, all feature images are summarized; In the classification layer of the printing and dyeing defect detection model, the probability of the printing and dyeing image belonging to various categories is determined based on the summarized feature images, and the categories include normal categories and various printing and dyeing defect categories; In the output layer of the printing and dyeing defect detection model, the category with the largest probability value is taken as the final category of the printing and dyeing image, and whether there is a printing and dyeing defect is determined based on the final category.

10. A digital control and management system for printing and dyeing industry, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the digital control management method for the printing and dyeing industry as claimed in any one of claims 1 to 9 is implemented.

Images