CN-122022260-A - Intelligent production management software and method with cooperation of multiple printing technologies

CN122022260ACN 122022260 ACN122022260 ACN 122022260ACN-122022260-A

Abstract

The application provides intelligent production management software and method for cooperation of multiple printing processes, which comprise the steps of simulating dynamic influence of fabric characteristics and pattern complexity under multi-dimensional interaction through a general parameter optimization model based on the basis of basic parameter adjustment, obtaining an optimized printing process parameter curve, obtaining estimated data of printing test time from an adjusted equipment scheduling scheme, judging whether the estimated time is lower than a historical average level, determining a textile production efficiency improvement index if the estimated time is lower than the historical average level, updating a printing quality control rule according to the textile production efficiency improvement index, generating a final multi-process cooperation parameter matching result, adopting the final multi-process cooperation parameter matching result to generate a real-time textile production instruction, and determining an automatic execution sequence of printing equipment.

Inventors

WANG YUN
WANG JUNFENG
WANG LIXI
ZHANG LI
CAO LI

Assignees

武汉海润时代印花科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251229

Claims (9)

1. The intelligent production management software and method for cooperation of multiple printing processes are characterized by comprising the following steps: Acquiring textile order related data from a preset textile production database, wherein the data comprise physical characteristics of fabric fibers and complexity information of pattern design, and determining initial fabric and pattern interaction influence factors by analyzing interaction of the fabric characteristics and the pattern complexity; According to the initial fabric and pattern interaction influence factors, a general data cluster analysis method is adopted to group historical printing parameter change curves, and a printing characteristic set with a similar nonlinear change rule is obtained; judging whether printing process parameters with the matching degree with the current order higher than a preset threshold exist for the printing feature set, if so, screening out a printing parameter combination with the best comprehensive performance from the set, and determining the printing parameter combination as a basic parameter adjustment basis; based on the basic parameter adjustment basis, simulating the dynamic influence of the fabric characteristics and the pattern complexity under multi-dimensional interaction through a general parameter optimization model to obtain an optimized printing process parameter curve; Aiming at the optimized printing process parameter curve, analyzing the demand for equipment resource scheduling when the textile order is switched, and if resource conflict is found, re-planning a multi-process collaborative execution sequence through a universal resource optimization algorithm to obtain an adjusted equipment scheduling scheme; Acquiring estimated data of printing test time from the adjusted equipment scheduling scheme, judging whether the estimated time is lower than a historical average level, and if so, determining a textile production efficiency improvement index; updating printing quality control rules according to the textile production efficiency improvement index to generate a final multi-process cooperative parameter matching result; and generating a real-time textile production instruction by adopting the final multi-process cooperative parameter matching result, and determining an automatic execution sequence of printing equipment.
2. The intelligent production management software and method according to claim 1, wherein the acquiring textile order related data from a preset textile production database, the data including physical properties of fabric fibers and complexity information of pattern design, determining an initial fabric-pattern interaction influencing factor by analyzing interactions of fabric properties and pattern complexity, comprises: acquiring fabric fiber physical characteristics and pattern design complexity information in a textile order through a preset textile production database, and determining a preliminary data set; Classifying the physical characteristics of the fabric fibers and the complexity information of pattern design according to the acquired data set to obtain a classified characteristic data set; analyzing interaction between the physical properties of the fabric fibers and the design complexity of the patterns by adopting the classified characteristic data set, and judging the significance level of the interaction; If the significance level of the interaction exceeds a preset threshold, carrying out quantization treatment on the interaction through a logistic regression model to obtain quantized influence factors; according to the quantized influencing factors, determining initial values of fabric and pattern interaction influencing factors in combination with business association of the textile orders; comparing the initial value with historical data in a production database to obtain a deviation range, and determining the application range of the final fabric and pattern interaction influence factor; If the deviation range is within the preset threshold, storing the final fabric and pattern interaction influence factor into a production database to finish data updating.
3. The intelligent production management software and method for cooperation of multiple printing processes according to claim 1, wherein the step of grouping historical printing parameter change curves by a general data cluster analysis method according to the initial fabric and pattern interaction influence factors to obtain a printing characteristic set with similar nonlinear change rules comprises the following steps: acquiring a historical printing parameter change curve; performing distance calculation on the change curves by adopting a hierarchical clustering method to obtain a similarity matrix between the curves; determining clustering dividing points according to the similarity matrix, and classifying the clustering dividing points into the same group if the distance between curves is less than a preset threshold value to obtain a primary curve grouping result; Extracting the average track of each group of curves according to the preliminary curve grouping result to obtain a group-represented change curve; Calculating the deviation square sum of the curves in the group and the representative curves through the group representative change curve, and removing the abnormal curves if the deviation square sum exceeds the average level in the group to obtain a purification grouping result; extracting each group of shared printing parameter range and nonlinear variation paragraphs from the purification grouping result, and determining a printing characteristic set; and constructing a feature index table according to the printing feature set to obtain the printing feature set with a similar nonlinear change rule.
4. The intelligent production management software and method according to claim 1, wherein for the printing feature set, determining whether there are printing process parameters with matching degree with the current order higher than a preset threshold, if so, screening out a printing parameter combination with the best comprehensive performance from the set, and determining as a basic parameter adjustment basis, including: acquiring a printing feature set of a current order; Calculating the matching degree of each group of historical printing process parameters in the current order printing characteristics and the printing characteristic set through cosine similarity to obtain a matching degree list; for each item in the matching degree list, if the matching degree is higher than a preset threshold value, marking the corresponding printing process parameters as candidate parameters to obtain a candidate parameter set; According to the candidate parameter set, sequencing the comprehensive performance of each group of candidate parameters by adopting a multi-target sequencing method to obtain a performance sequencing result; screening the highest-ranking printing process parameter combination from the performance sequencing result, and determining the highest-ranking printing process parameter combination as an optimal parameter combination; Obtaining a parameter deviation value set through the difference comparison of the optimal parameter combination and the current order printing characteristics; And determining a basic parameter adjustment basis according to the parameter deviation value set.
5. The intelligent production management software and method for cooperation of multiple printing processes according to claim 1, wherein the method is characterized in that the method comprises the steps of simulating dynamic influence of fabric characteristics and pattern complexity under multi-dimensional interaction through a general parameter optimization model based on the basic parameter adjustment basis to obtain an optimized printing process parameter curve, and comprises the following steps: Acquiring a data set corresponding to the basic parameters and the fabric attributes; loading basic parameters and adjustment rules through an optimization model; Adopting an optimization model to process the fabric attribute and pattern complexity; constructing a multi-dimensional interaction matrix in the optimization model; triggering dynamic action calculation if the element variation in the multi-dimensional interaction matrix exceeds a preset threshold; updating the technological parameters according to the dynamic action calculation result; Iterating the technological parameters and parameter curves through a simulation process; And obtaining a parameter curve corresponding to the optimization result.
6. The intelligent production management software and method for cooperation of multiple printing processes according to claim 1, wherein the analyzing the demand for equipment resource scheduling when the textile order is switched according to the optimized printing process parameter curve, if resource conflict is found, re-planning the multi-process cooperation execution sequence through a universal resource optimization algorithm to obtain an adjusted equipment scheduling scheme comprises: acquiring equipment resource occupation data during textile order switching, extracting corresponding parameter curve data from a system according to printing process requirements of each order, and determining an initial state of resource allocation; judging whether resource conflict exists or not by analyzing the equipment resource occupation condition in the initial state, and if simultaneous demands of a plurality of processes on the same equipment resource are detected, recording a specific time period of the conflict and the related process types to obtain conflict detail data; Re-planning the execution sequence with the cooperation of the multiple processes by adopting a genetic algorithm aiming at conflict detail data to generate a plurality of candidate execution sequence schemes, and determining a preliminary sequence combination for alleviating the resource conflict; Simulating the occupation condition of equipment resources in different time periods according to the initial sequence combination, judging whether residual resource conflicts exist, and if so, locally adjusting an execution sequence to obtain an optimized sequence scheme; generating a corresponding device scheduling time table through the optimized sequence scheme, and integrating data aiming at the task allocation situation of each device to determine a final device scheduling scheme; and acquiring data of a final equipment scheduling scheme, and carrying out matching verification on the operation time period of each equipment by combining a specific parameter curve of the printing process to obtain a complete mapping relation between process execution and resource allocation.
7. The intelligent production management software and method according to claim 1, wherein the obtaining estimated data of printing test time from the adjusted equipment scheduling scheme, determining whether the estimated time is lower than a historical average level, if so, determining a textile production efficiency improvement index, includes: Extracting estimated data of printing test time from the adjusted equipment scheduling scheme; Calculating the average value of the printing test time in a plurality of history periods according to the estimated data to obtain a history average level; Obtaining a time comparison result by comparing the estimated time with the historical average level; if the time comparison result shows that the estimated time is lower than the historical average level, marking the efficiency improvement state; fitting the historical scheduling scheme and the record corresponding to the printing machine time by adopting a linear regression model to obtain an estimated model; predicting the input characteristics of the adjusted scheme through a prediction model to obtain predicted data of the printing test machine time; If the estimated time is lower than the historical average level, calculating the difference between the estimated time and the historical average level to obtain an efficiency improvement index.
8. The intelligent production management software and method for cooperation of multiple printing processes according to claim 1, wherein updating the printing quality control rule according to the textile production efficiency improvement index to generate a final multi-process cooperation parameter matching result comprises: extracting a key parameter set in a printing quality control rule according to a textile production efficiency improvement index; Obtaining a current threshold range from the key parameter set to obtain a threshold adjustment basis; the adjusted multi-process parameters are obtained by modifying corresponding threshold values in the multi-process cooperative parameters through threshold value adjustment; Training historical multi-process parameters and printing quality records by adopting a random forest model to obtain a parameter prediction model; predicting the adjusted multi-process parameters through a parameter prediction model to obtain a printing quality coincidence rate predicted value; if the printing quality accords with the preset standard, marking the adjusted multi-process parameters as matching states to obtain a multi-process cooperative parameter matching result; and outputting a final parameter configuration set through the multi-process collaborative parameter matching result.
9. The intelligent production management software and method for cooperation of multiple printing processes according to claim 1, wherein the step of generating real-time textile production instructions by using the final multi-process cooperation parameter matching result to determine an automatic execution sequence of printing equipment comprises the steps of: according to the service content and the extracted related attributes, generating a service solution scheme, namely acquiring a final multi-process cooperation parameter matching result, and extracting key data fields related to a textile production process from the final multi-process cooperation parameter matching result, wherein the technical process design comprises multi-process cooperation, parameter matching result, real-time production instructions, textile production process, printing equipment control, automatic execution sequence and the like; Determining the priority and the dependency relationship of each production link by analyzing the process configuration information in the parameter matching result to obtain a preliminary production flow frame; Aiming at a preliminary production flow frame, a pre-established process flow management rule base is adopted to analyze time constraint and resource allocation logic among links; If the resource occupation of a certain link exceeds a preset threshold, adjusting related parameters to balance the load, and determining an optimized production flow structure; Generating real-time textile production instructions according to the optimized production flow structure; mapping each node in the flow structure to a specific operation instruction set, and combining a real-time data processing module to obtain instruction content which is suitable for the current production environment; aiming at the generated real-time production instruction, analyzing execution parameters required by control of printing equipment; Extracting specific requirements of equipment operation from instruction content, and determining a task allocation scheme of each equipment by combining logic rules of equipment cooperative operation; According to the task allocation scheme, constructing an automatic execution sequence of the printing equipment; Optimizing the execution sequence by adopting a genetic algorithm through the priority ordering and time window matching of the equipment tasks to obtain a final equipment operation sequence; generating control signals of an automation execution logic for a final device operation sequence; Extracting equipment starting and stopping instructions at each time point from the operation sequence, and determining a control instruction set which can be directly transmitted to equipment through a signal conversion module; transmitting the generated control instruction set to a printing equipment interface in real time; And distributing the instruction set to corresponding equipment through a data communication protocol, completing the deployment of the automatic execution sequence, judging whether data loss or delay exists in the transmission process, and triggering the standby communication channel to reissue if abnormality exists.

Description

Intelligent production management software and method with cooperation of multiple printing technologies Technical Field The invention relates to the technical field of information, in particular to intelligent production management software and method for cooperation of multiple printing processes. Background In textile printing industry, intelligent production management software with cooperation of multiple printing processes has become a key research field for improving production efficiency and product quality, and the direction directly relates to whether enterprises can respond to diversified order demands rapidly and realize flexible manufacturing. The current management software can record various printing process parameters, but mostly relies on manual experience to set and adjust the parameters, so that the influence caused by frequent change of fabric types and pattern complexity difference is difficult to deal with in actual production. Especially, when the process is carried out in parallel, parameter adjustment is often delayed from order switching, so that the test time is prolonged and the resource scheduling conflicts are caused. The core technical difficulty is that the parameter curves of different printing processes have highly nonlinear characteristics, and the curves are jointly influenced by factors such as hygroscopicity and thickness of the fabric and pattern complexity such as number of color layers and fineness. The multi-dimensional interaction of the fabric characteristics and the pattern complexity makes the optimal parameter combination difference of the same process under different orders obvious, and the interaction effect further amplifies the complexity of parameter adjustment, so that the production parameters are difficult to quickly and accurately match with specific orders. For example, when receiving an order, the design may include multiple layers of gradient and high definition lines, with digital printing requiring lower temperatures and higher color paste concentrations if the fabric is a highly hygroscopic cotton-to-hemp blend, and with completely different pressure and speed combinations when switching to rotary screen printing. If the parameter curves can not accurately reflect the interaction effects, the problems of chromatic aberration, infiltration, screen blockage and the like are easy to occur in production, and frequent shutdown adjustment not only wastes time, but also disturbs the production rhythm of the multi-process cooperation. Therefore, how to automatically match the optimal process parameter combination according to the fabric characteristics and the pattern complexity in the multi-printing process collaborative production becomes a key problem for improving the practicability and the response speed of the intelligent production management software. Disclosure of Invention The invention provides intelligent production management software and method with cooperation of multiple printing processes, which mainly comprise the following steps: Acquiring textile order related data from a preset textile production database, wherein the data comprise physical characteristics of fabric fibers and complexity information of pattern design, and determining initial fabric and pattern interaction influence factors by analyzing interaction of the fabric characteristics and the pattern complexity; According to the initial fabric and pattern interaction influence factors, a general data cluster analysis method is adopted to group historical printing parameter change curves, and a printing characteristic set with a similar nonlinear change rule is obtained; judging whether printing process parameters with the matching degree with the current order higher than a preset threshold exist for the printing feature set, if so, screening out a printing parameter combination with the best comprehensive performance from the set, and determining the printing parameter combination as a basic parameter adjustment basis; based on the basic parameter adjustment basis, simulating the dynamic influence of the fabric characteristics and the pattern complexity under multi-dimensional interaction through a general parameter optimization model to obtain an optimized printing process parameter curve; Aiming at the optimized printing process parameter curve, analyzing the demand for equipment resource scheduling when the textile order is switched, and if resource conflict is found, re-planning a multi-process collaborative execution sequence through a universal resource optimization algorithm to obtain an adjusted equipment scheduling scheme; Acquiring estimated data of printing test time from the adjusted equipment scheduling scheme, judging whether the estimated time is lower than a historical average level, and if so, determining a textile production efficiency improvement index; updating printing quality control rules according to the textile production efficiency improvement inde