High-efficiency stamping control method and system based on rapid die change

Through multi-feature operation prediction and mold change decision optimization, the problem of low mold change efficiency of stamping production lines is solved, production efficiency and stability are improved, and production cycle and cost are reduced.

CN118655861BActive Publication Date: 2024-11-15QIDONG HAISHENG STAMPING PARTS CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411133855.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-15
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

Traditional stamping production lines are inefficient during mold replacement, resulting in extended production cycles and increasing the risk of production costs and production interruptions.

Method used

Through multi-feature operation prediction, determine the completion time node of the mold unloading, perform feature combing after the mold unloading, form a mold change node chain, and use the mold change decision-making and multi-feature mold change optimization algorithm to optimize the mold change scheme to improve the mold change efficiency .

Benefits of technology

The mold replacement efficiency of stamping production lines has been improved, the production cycle has been reduced, the production interruption and cost have been reduced, and the stability and flexibility of the production lines have been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118655861B_ABST
    Figure CN118655861B_ABST
Patent Text Reader

Abstract

The present invention discloses an efficient stamping control method and system based on rapid die change, and relates to the field of intelligent control technology. The method comprises: obtaining a first stamping production task being executed; obtaining a second stamping production task to be executed; performing multi-feature operation prediction on the first stamping die, and determining the first die unloading completion time node; performing feature combing on the stamping die change process information after die unloading, and obtaining a first stamping die change node chain and a second stamping die change node chain; performing die change decision optimization, and obtaining a first node stamping die change plan; performing multi-feature die change optimization, and obtaining a second node stamping die change plan; and performing die change according to the first node stamping die change plan and the second node stamping die change plan. The technical problem of low die change efficiency in the stamping production process leading to an extension of the production cycle in the prior art is solved, and the die change process is optimized through intelligent control, so as to achieve the technical effect of improving the die change efficiency of the stamping production line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a high-efficiency stamping control method and system based on rapid die change. Background Art

[0002] In today's highly competitive and rapidly changing manufacturing environment, stamping production is one of the core processes of metal processing and parts manufacturing. Its efficiency and flexibility are directly related to the company's market response speed and cost competitiveness. However, traditional stamping production lines face many challenges in mold replacement. Mold replacement is usually a complex and time-consuming process. It not only requires operators to have high professional skills, but also requires precise coordination and cooperation to ensure the accurate installation and commissioning of the mold. In addition, with the continuous increase in product variety and frequent changes in production orders, the frequency of mold replacement is also gradually increasing. This further exacerbates the negative impact of mold replacement on production efficiency. Every mold replacement requires downtime, which not only reduces the effective production time, but also increases production costs. Summary of the invention

[0003] The present application provides an efficient stamping control method and system based on rapid die change, which solves the technical problem in the prior art that the low die change efficiency in the stamping production process leads to a prolonged production cycle.

[0004] In view of the above problems, the present application provides an efficient stamping control method and system based on rapid die change.

[0005] In a first aspect of the present application, an efficient stamping control method based on rapid die change is provided, the method comprising:

[0006] A first stamping production task being executed is obtained, wherein the first stamping production task corresponds to a first stamping die; a second stamping production task to be executed is obtained, wherein the second stamping production task corresponds to a second stamping die; a multi-feature operation prediction is performed on the first stamping die according to the first stamping production task, and a first die unloading completion time node is determined; a feature combing is performed on the stamping die changing process information after die unloading according to the first die unloading completion time node, and a first stamping die changing node chain and a second stamping die changing node chain are obtained; based on the first die unloading completion time node, a die changing decision optimization is performed according to the first stamping die changing node chain, and a first node stamping die changing plan is obtained; a multi-feature die changing optimization is performed according to the second stamping die changing node chain, and a second node stamping die changing plan is obtained; based on the first stamping die and the second stamping die, a die change is performed according to the first node stamping die changing plan and the second node stamping die changing plan.

[0007] The second aspect of the present application provides an efficient stamping control system based on rapid die change, the system comprising:

[0008] A first task acquisition module, the first task acquisition module is used to obtain a first stamping production task being executed, wherein the first stamping production task corresponds to a first stamping die; a second task acquisition module, the second task acquisition module is used to obtain a second stamping production task to be executed, wherein the second stamping production task corresponds to a second stamping die; a prediction module, the prediction module is used to perform multi-feature operation prediction on the first stamping die according to the first stamping production task, and determine the first die unloading completion time node; a feature combing module, the feature combing module is used to perform stamping die change process information according to the first die unloading completion time node After mold unloading, feature combing is performed to obtain a first stamping mold change node chain and a second stamping mold change node chain; a first optimization module, the first optimization module is used to optimize the mold change decision based on the first mold unloading completion time node and the first stamping mold change node chain to obtain a first node stamping mold change plan; a second optimization module, the second optimization module is used to perform multi-feature mold change optimization according to the second stamping mold change node chain to obtain a second node stamping mold change plan; a mold changing module, the mold changing module is used to change the mold based on the first stamping mold and the second stamping mold according to the first node stamping mold change plan and the second node stamping mold change plan.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, the first stamping production task being executed is obtained, wherein the first stamping production task corresponds to the first stamping die; the second stamping production task to be executed is obtained, wherein the second stamping production task corresponds to the second stamping die. Then, according to the first stamping production task, a multi-feature operation prediction is performed on the first stamping die to determine the first die unloading completion time node. Next, according to the first die unloading completion time node, the stamping die change process information is subjected to feature combing after die unloading to obtain the first stamping die change node chain and the second stamping die change node chain. Further, based on the first die unloading completion time node, the die change decision is optimized according to the first stamping die change node chain to obtain the first node stamping die change plan; according to the second stamping die change node chain, a multi-feature die change optimization is performed to obtain the second node stamping die change plan. Finally, based on the first stamping die and the second stamping die, the die is changed according to the first node stamping die change plan and the second node stamping die change plan. The technical problem of low die change efficiency in the stamping production process leading to extended production cycle in the prior art is solved, and the die change process is optimized through intelligent control, so as to achieve the technical effect of improving the die change efficiency of the stamping production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] 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.

[0012] Figure 1 A schematic flow chart of an efficient stamping control method based on rapid die change provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of an efficient stamping control system based on rapid die change provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: first task acquisition module 11 , second task acquisition module 12 , prediction module 13 , feature combing module 14 , first optimization module 15 , second optimization module 16 , mold changing module 17 . DETAILED DESCRIPTION

[0015] The present application solves the technical problem in the prior art that the low efficiency of die changing in the stamping production process leads to a prolonged production cycle by providing an efficient stamping control method and system based on rapid die changing.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides an efficient stamping control method based on rapid die change, wherein the method comprises:

[0019] A first stamping production task being executed is obtained, wherein the first stamping production task corresponds to a first stamping die.

[0020] In the stamping production process, the first stamping production task currently being executed is obtained. The first stamping production task describes the details of the stamping operation that needs to be completed, including but not limited to product type, production quantity, quality requirements, and required processing steps, etc. The first stamping production task is associated with the first stamping die, which determines the shape and size of the stamped part. By obtaining the first stamping production task being executed and its corresponding first stamping die information, a solid foundation can be provided for subsequent production scheduling and die replacement processes.

[0021] A second stamping production task to be executed is obtained, wherein the second stamping production task corresponds to a second stamping die.

[0022] While the first stamping production task is being executed, the second stamping production task to be executed will be obtained in advance. The second stamping production task also includes detailed operation requirements, such as product type, specifications, quantity and quality standards, and the second stamping production task corresponds to the second stamping die.

[0023] A multi-feature operation prediction is performed on the first stamping die according to the first stamping production task to determine a first die removal completion time node.

[0024] In the stamping production process, in order to efficiently and accurately arrange the mold replacement, the first stamping mold will be predicted for multiple features according to the first stamping production task currently being executed, including but not limited to the current working status of the mold, the remaining processing volume, the processing speed, etc. By analyzing these features, it is possible to predict the time required for the first stamping mold to complete the current production task, and determine the first mold removal completion time node, which marks the end of the current production task and the beginning of the mold replacement process. By accurately predicting the mold removal completion time, production scheduling can be optimized, waiting time can be reduced, and the mold replacement process can be ensured to be seamlessly connected with the production plan. At the same time, this also helps to avoid production interruptions and delays and improve the overall stability and reliability of the production line.

[0025] Further, performing multi-feature operation prediction on the first stamping die according to the first stamping production task to determine a first die removal completion time node includes:

[0026] Obtain real-time stamping monitoring data corresponding to the first stamping production task; based on the first stamping production task, predict the stamping task operation time according to the real-time stamping monitoring data to obtain the first stamping task completion time node; collect the installation parameters of the first stamping die to obtain the first die installation characteristic data; predict the demolding operation time characteristics of the first stamping die according to the first die installation characteristic data to obtain the first predicted demolding time; integrate the first stamping task completion time node and the first predicted demolding time to generate the first demolding completion time node.

[0027] Preferably, real-time stamping monitoring data corresponding to the first stamping production task is obtained, including but not limited to the operating status of the stamping machine, the usage of the mold, the stamping speed, pressure parameters, and production progress; according to the specific requirements of the first stamping production task and the real-time stamping monitoring data, the prediction algorithm is used to predict the operation time of the stamping task to obtain the first stamping task completion time node; by collecting the installation parameters of the first stamping mold, the installation method, tightness, position adjustment, etc. of the mold are obtained, and this information constitutes the first mold installation characteristic data; based on the first mold installation characteristic data, the first stamping mold is subjected to a mold unloading operation time characteristic prediction, and the first predicted mold unloading time can be obtained by combining the historical mold unloading time data and averaging it, and the first predicted mold unloading time refers to the time duration of disassembly of the first stamping mold; the first stamping task completion time node is integrated with the first predicted mold unloading time, and the first mold unloading completion time node is generated through time superposition calculation.

[0028] Furthermore, based on the first stamping production task, the stamping task operation time is predicted according to the real-time stamping monitoring data to obtain the first stamping task completion time node, including:

[0029] Obtain a stamping task operation time feature record library, wherein the stamping task operation time feature record library includes a historical stamping production task record set, a historical stamping monitoring data record set and a historical stamping task completion time node record set; based on the stamping task operation time feature record library, train P stamping operation time prediction feature models, wherein P is a positive integer greater than 1; based on the first stamping production task and the real-time stamping monitoring data, obtain P predicted stamping task completion time nodes according to the P stamping operation time prediction feature models; merge the P predicted stamping task completion time nodes to generate the first stamping task completion time node.

[0030] Preferably, by collecting historical stamping production task records, historical stamping monitoring data records and historical stamping task completion time node records, a historical stamping production task record set, a historical stamping monitoring data record set and a historical stamping task completion time node record set are formed, and a stamping task operation time feature record library is constructed according to the historical stamping production task record set, the historical stamping monitoring data record set and the historical stamping task completion time node record set; based on the stamping task operation time feature record library, P stamping operation time prediction feature models are trained, where P is a positive integer greater than 1, indicating that multiple prediction models are trained, and each model Each model uses different machine learning algorithms to learn and extract features related to stamping operation time from the data to build a prediction model. By training multiple models, the diversity and complexity of the data can be fully utilized to improve the robustness and accuracy of the prediction; the first stamping production task and real-time stamping monitoring data are input into P stamping operation time prediction feature models. Each model will predict the completion time of the first stamping production task and output a predicted stamping task completion time node; through averaging processing, the P predicted stamping task completion time nodes are integrated to obtain the first stamping task completion time node.

[0031] Furthermore, based on the first stamping production task, the stamping task operation time is predicted according to the real-time stamping monitoring data to obtain the first stamping task completion time node, including:

[0032] Obtain mold monitoring data corresponding to the first stamping mold; perform fault prediction on the first stamping mold according to the mold monitoring data to obtain a first mold predicted failure coefficient; determine whether the first mold predicted failure coefficient is greater than / equal to a predetermined mold predicted failure coefficient; if the first mold predicted failure coefficient is greater than / equal to the predetermined mold predicted failure coefficient, generate a first similar mold change instruction; perform similar mold change on the first stamping mold based on the first similar mold change instruction, and correct the first stamping task completion time node based on the first similar mold change instruction.

[0033] In the stamping production process, in order to ensure the stable operation of the mold and the continuity of production, the state of the first stamping mold will be continuously monitored. By obtaining the mold monitoring data, including the key parameters such as the wear, temperature, and vibration of the mold, a basis for subsequent fault prediction is provided. Based on the mold monitoring data, a fault prediction algorithm can be used to predict the failure of the first stamping mold. By analyzing the abnormal patterns, trend changes, and similarities with historical failure cases in the mold monitoring data, the predicted failure coefficient of the first mold is calculated. The predicted failure coefficient of the first mold is a quantitative indicator used to evaluate the possibility of failure of the mold in the future. Next, it is determined whether the predicted failure coefficient of the first mold is greater than or equal to the predicted failure coefficient of the predetermined mold, where the predicted failure coefficient of the predetermined mold is a threshold set after comprehensive consideration of multiple factors such as production safety, cost-effectiveness, and maintenance plan. If the predicted failure coefficient exceeds this threshold, it means that the mold has a high risk of failure and preventive measures need to be taken. Once it is determined that the predicted failure coefficient of the mold exceeds the standard, the first same-type mold change instruction will be immediately generated. The first same-type mold change instruction requires the current first stamping mold to be replaced with a spare mold of the same type to ensure uninterrupted production. At the same time, the completion time node of the first stamping task will be corrected according to the time required for the die change operation to ensure the accuracy and rationality of the time node. In summary, by monitoring the first stamping die, predicting faults, and generating die change instructions, the impact of die failures on production can be effectively reduced, and the continuity and stability of production can be guaranteed. At the same time, by timely correcting the completion time node of the stamping task, production scheduling can be optimized and production efficiency can be improved.

[0034] According to the first die unloading completion time node, the stamping die change process information is unloaded and feature combing is performed to obtain a first stamping die change node chain and a second stamping die change node chain.

[0035] In the stamping production process, after the completion time node of the first stamping production task of die unloading is determined, it is necessary to sort out the stamping die change process after the completion time node of the first die unloading to ensure that the die change process is carried out efficiently and orderly. Specifically, according to the completion time node of the first die unloading, each link in the stamping die change process is carefully analyzed and evaluated, including but not limited to the steps of mold disassembly, cleaning, inspection, replacement, installation and debugging, so as to form the first stamping die change node chain and the second stamping die change node chain. Among them, the first stamping die change node chain refers to the operation nodes performed before or during die unloading, such as the handling and installation preparation of the mold; the second stamping die change node chain refers to the operation nodes performed after die unloading, such as the adjustment and positioning of the mold.

[0036] Based on the first die unloading completion time node, a die change decision optimization is performed according to the first stamping die change node chain to obtain a first node stamping die change plan.

[0037] After determining the first die unloading completion time node and the first stamping die change node chain, it is necessary to perform a die change decision optimization process based on this information to obtain the optimal first node stamping die change plan. Die change decision optimization is a process that comprehensively considers multiple factors, including but not limited to time, cost, efficiency, safety, and resource utilization. According to each node in the first stamping die change node chain, the impact of different die change plans on these factors is evaluated to find a plan that maximizes the overall benefit. Specifically, a variety of optimization algorithms, such as genetic algorithms, simulated annealing, particle swarm optimization, etc., can be used to search and determine the optimal die change plan.

[0038] Furthermore, based on the first die unloading completion time node, the die change decision optimization is performed according to the first stamping die change node chain to obtain the first node stamping die change plan, including:

[0039] A die change decision is made according to the first stamping die change node chain to obtain an initial stamping die change plan for the first node; parallel adjustments are made according to the initial stamping die change plan for the first node to obtain multiple adjusted stamping die change plans for the first nodes; a die change time minimization prediction and optimization is performed according to the multiple adjusted stamping die change plans for the first nodes to obtain a minimum die change time for the first node and a first node winning stamping die change plan corresponding to the minimum die change time for the first node; based on a predetermined tolerance time, the trigger time feature of the first stamping die change node chain is calculated in combination with the first die unloading completion time node and the minimum die change time for the first node to obtain a first node trigger time feature; and a first node stamping die change plan is generated according to the trigger time feature of the first node and the winning stamping die change plan for the first node.

[0040] Preferably, an initial die-changing scheme, i.e., the initial stamping die-changing scheme of the first node, is generated according to the first stamping die-changing node chain in accordance with the conventional or preset die-changing process; by adjusting the initial stamping die-changing scheme of the first node in parallel, including adjusting the order of each die-changing step, merging or splitting certain steps, optimizing resource allocation, etc., through these adjustments, multiple possible first-node adjusted stamping die-changing schemes can be generated, each of which represents a different die-changing path and resource allocation method; for each adjusted die-changing scheme, a die-changing time prediction is performed, and by comparing the predicted times of different schemes, the scheme with the shortest die-changing time is found, i.e., the winning stamping die-changing scheme of the first node corresponding to the minimum die-changing time of the first node; due to production For uncertainties in the process (such as equipment failure, personnel changes, etc.), a tolerance time can be preset to ensure that the mold change can be completed on time even in the event of a minor accident; based on the tolerance time, the first mold unloading completion time node and the minimum mold change time of the first node, the trigger time characteristics of the first stamping mold change node chain are calculated, including determining the earliest and latest trigger time of each key node to ensure that the mold change process is both efficient and flexible; based on the trigger time characteristics of the first node and the winning stamping mold change plan for the first node, the final first node stamping mold change plan is generated. This plan not only includes detailed mold change steps and resource allocation information, but also clarifies the trigger time of each key node, providing clear guidance and support for actual production operations.

[0041] A multi-feature die change optimization is performed according to the second stamping die change node chain to obtain a second node stamping die change plan.

[0042] By performing multi-feature optimization on the second stamping die change node chain, such as using an optimization algorithm (such as genetic algorithm, particle swarm optimization, simulated annealing, etc.) to search for possible die change schemes in the solution space, and selecting the best scheme from a series of die change schemes as the second node stamping die change scheme.

[0043] Furthermore, performing multi-feature die change optimization according to the second stamping die change node chain to obtain a second node stamping die change plan includes:

[0044] According to the predetermined die change production adaptability, the die change optimization is performed in combination with the second stamping die change node chain to obtain the second node optimized stamping die change plan set; according to the second node optimized stamping die change plan set, parallel adjustment is performed to obtain the second node adjusted stamping die change plan set; according to the second node adjusted stamping die change plan set, the die change duration is predicted to obtain multiple second node predicted die change durations; based on the multiple second node predicted die change durations, the second node adjusted stamping die change plan set is optimized to minimize the die change duration, and the second node stamping die change plan is output.

[0045] Preferably, according to the predetermined die-changing production fitness, combined with each link and feature of the second stamping die-changing node chain, a preliminary die-changing optimization is performed to obtain a die-changing scheme that meets the production fitness requirements, namely, a second node optimized stamping die-changing scheme set; the second node optimized stamping die-changing scheme set is adjusted in parallel, such as making detailed adjustments to the die-changing steps, resource allocation, time arrangement, etc., and by trying different adjustment strategies, a second node adjusted stamping die-changing scheme set containing multiple adjusted schemes is generated; for each scheme in the second node adjusted stamping die-changing scheme set, a die-changing duration is predicted to obtain multiple second node predicted die-changing durations; based on the multiple second node predicted die-changing durations, the second node adjusted stamping die-changing scheme set is optimized to minimize the die-changing duration, and by comparing the predicted durations of each scheme, a scheme with the shortest die-changing duration, namely, the second node stamping die-changing scheme, is selected.

[0046] Furthermore, according to the predetermined die change production adaptability, the die change optimization is performed in combination with the second stamping die change node chain to obtain a second node optimization stamping die change solution set, including:

[0047] Obtain the basic mold information corresponding to the second stamping mold, make a mold change decision in combination with the second stamping mold change node chain, and obtain multiple second node initial mold change decisions; perform multi-feature mold change production prediction based on the multiple second node initial mold change decisions, and obtain multiple mold change production prediction results, wherein each mold change production prediction result includes a predicted mold change production quality coefficient and a predicted mold state assessment coefficient; perform normalization processing based on the multiple mold change production prediction results, and establish a mold change production prediction matrix; perform weighted calculation on the mold change production prediction matrix according to the mold change production fitness weight condition, and obtain a mold change production fitness matrix; perform optimization analysis on the multiple second node initial mold change decisions based on the predetermined mold change production fitness and the mold change production fitness matrix, and generate the second node optimal stamping mold change plan set; wherein the plan capacity of the second node optimal stamping mold change plan set is equal to the predetermined plan capacity.

[0048] Preferably, basic mold information corresponding to the second stamping mold is obtained from the database, including but not limited to the specifications, materials, service life, historical maintenance records, etc. of the mold; a preliminary mold change decision analysis is performed in combination with the second stamping mold change node chain, and the mold change sequence, required tools and equipment, personnel configuration and other factors are considered to generate multiple second node initial mold change decisions; for each initial mold change decision, a multi-feature mold change production prediction is performed, including predicting the production quality coefficient in the mold change process, that is, evaluating the expected level of product quality after the mold change, and predicting the mold state evaluation coefficient, that is, evaluating the operating status, wear degree and expected life of the mold after the mold change. The prediction results will form multiple mold change production prediction results, each of which includes a predicted mold change production quality coefficient and a predicted mold state evaluation coefficient; all mold change production prediction results are normalized to eliminate The influence of different dimensions and magnitudes; the normalized data are organized into a mold change production prediction matrix, in which each row represents an initial mold change decision, and each column represents a different prediction feature (such as production quality coefficient, mold state evaluation coefficient); according to the mold change production fitness weight condition, the mold change production prediction matrix is ​​weighted calculated, in which the weight reflects the importance of different prediction features in evaluating the fitness of the mold change plan, and the mold change production fitness matrix is ​​obtained after weighted calculation, in which each element represents the mold change production fitness value of the corresponding initial mold change decision; based on the predetermined mold change production fitness and the mold change production fitness matrix, multiple second-node initial mold change decisions are optimized and analyzed, and by comparing the fitness values ​​of each initial mold change decision, several decisions with fitness greater than / equal to the predetermined mold change production fitness are selected to form a second-node optimal stamping mold change plan set.

[0049] Based on the first stamping die and the second stamping die, die change is performed according to the first node stamping die change plan and the second node stamping die change plan.

[0050] After obtaining the first node stamping die change plan and the second node stamping die change plan, the die change process of the first stamping die and the second stamping die can be guided based on these two plans. By following the guidance of the first node stamping die change plan and the second node stamping die change plan, the die change process can be ensured to proceed smoothly and production interruption and waste can be minimized.

[0051] In summary, the embodiments of the present application have at least the following technical effects:

[0052] First, the first stamping production task being executed is obtained, wherein the first stamping production task corresponds to the first stamping die; the second stamping production task to be executed is obtained, wherein the second stamping production task corresponds to the second stamping die. Then, according to the first stamping production task, a multi-feature operation prediction is performed on the first stamping die to determine the first die unloading completion time node. Next, according to the first die unloading completion time node, the stamping die change process information is subjected to feature combing after die unloading to obtain the first stamping die change node chain and the second stamping die change node chain. Further, based on the first die unloading completion time node, the die change decision is optimized according to the first stamping die change node chain to obtain the first node stamping die change plan; according to the second stamping die change node chain, a multi-feature die change optimization is performed to obtain the second node stamping die change plan. Finally, based on the first stamping die and the second stamping die, the die is changed according to the first node stamping die change plan and the second node stamping die change plan. The technical problem of low die change efficiency in the stamping production process leading to extended production cycle in the prior art is solved, and the die change process is optimized through intelligent control, so as to achieve the technical effect of improving the die change efficiency of the stamping production line.

[0053] Embodiment 2 is based on the same inventive concept as the efficient stamping control method based on rapid die change in the previous embodiment. Figure 2 As shown, the present application provides an efficient stamping control system based on rapid die change, wherein the system includes:

[0054] A first task acquisition module 11, the first task acquisition module 11 is used to obtain a first stamping production task being executed, wherein the first stamping production task corresponds to a first stamping die; a second task acquisition module 12, the second task acquisition module 12 is used to obtain a second stamping production task to be executed, wherein the second stamping production task corresponds to a second stamping die; a prediction module 13, the prediction module 13 is used to perform multi-feature operation prediction on the first stamping die according to the first stamping production task, and determine the first die unloading completion time node; a feature combing module 14, the feature combing module 14 is used to comb the stamping die change process information according to the first die unloading completion time node After the mold unloading is performed, feature combing is performed to obtain a first stamping mold changing node chain and a second stamping mold changing node chain; a first optimization module 15, the first optimization module 15 is used to optimize the mold changing decision based on the first mold unloading completion time node and the first stamping mold changing node chain to obtain a first node stamping mold changing plan; a second optimization module 16, the second optimization module 16 is used to perform multi-feature mold changing optimization according to the second stamping mold changing node chain to obtain a second node stamping mold changing plan; a mold changing module 17, the mold changing module 17 is used to perform mold changing based on the first stamping mold and the second stamping mold according to the first node stamping mold changing plan and the second node stamping mold changing plan.

[0055] Furthermore, the prediction module 13 is used to perform the following method:

[0056] Obtain real-time stamping monitoring data corresponding to the first stamping production task; based on the first stamping production task, predict the stamping task operation time according to the real-time stamping monitoring data to obtain the first stamping task completion time node; collect the installation parameters of the first stamping die to obtain the first die installation characteristic data; predict the demolding operation time characteristics of the first stamping die according to the first die installation characteristic data to obtain the first predicted demolding time; integrate the first stamping task completion time node and the first predicted demolding time to generate the first demolding completion time node.

[0057] Furthermore, the prediction module 13 is used to perform the following method:

[0058] Obtain a stamping task operation time feature record library, wherein the stamping task operation time feature record library includes a historical stamping production task record set, a historical stamping monitoring data record set and a historical stamping task completion time node record set; based on the stamping task operation time feature record library, train P stamping operation time prediction feature models, wherein P is a positive integer greater than 1; based on the first stamping production task and the real-time stamping monitoring data, obtain P predicted stamping task completion time nodes according to the P stamping operation time prediction feature models; merge the P predicted stamping task completion time nodes to generate the first stamping task completion time node.

[0059] Furthermore, the first optimization module 15 is used to execute the following method:

[0060] A die change decision is made according to the first stamping die change node chain to obtain an initial stamping die change plan for the first node; parallel adjustments are made according to the initial stamping die change plan for the first node to obtain multiple adjusted stamping die change plans for the first nodes; a die change time minimization prediction and optimization is performed according to the multiple adjusted stamping die change plans for the first nodes to obtain a minimum die change time for the first node and a first node winning stamping die change plan corresponding to the minimum die change time for the first node; based on a predetermined tolerance time, the trigger time feature of the first stamping die change node chain is calculated in combination with the first die unloading completion time node and the minimum die change time for the first node to obtain a first node trigger time feature; and a first node stamping die change plan is generated according to the trigger time feature of the first node and the winning stamping die change plan for the first node.

[0061] Furthermore, the second optimization module 16 is used to execute the following method:

[0062] According to the predetermined die change production adaptability, the die change optimization is performed in combination with the second stamping die change node chain to obtain the second node optimized stamping die change plan set; according to the second node optimized stamping die change plan set, parallel adjustment is performed to obtain the second node adjusted stamping die change plan set; according to the second node adjusted stamping die change plan set, the die change duration is predicted to obtain multiple second node predicted die change durations; based on the multiple second node predicted die change durations, the second node adjusted stamping die change plan set is optimized to minimize the die change duration, and the second node stamping die change plan is output.

[0063] Furthermore, the second optimization module 16 is used to execute the following method:

[0064] Obtain the basic mold information corresponding to the second stamping mold, make a mold change decision in combination with the second stamping mold change node chain, and obtain multiple second node initial mold change decisions; perform multi-feature mold change production prediction based on the multiple second node initial mold change decisions, and obtain multiple mold change production prediction results, wherein each mold change production prediction result includes a predicted mold change production quality coefficient and a predicted mold state assessment coefficient; perform normalization processing based on the multiple mold change production prediction results, and establish a mold change production prediction matrix; perform weighted calculation on the mold change production prediction matrix according to the mold change production fitness weight condition, and obtain a mold change production fitness matrix; perform optimization analysis on the multiple second node initial mold change decisions based on the predetermined mold change production fitness and the mold change production fitness matrix, and generate the second node optimal stamping mold change plan set; wherein the plan capacity of the second node optimal stamping mold change plan set is equal to the predetermined plan capacity.

[0065] Furthermore, the prediction module 13 is used to perform the following method:

[0066] Obtain mold monitoring data corresponding to the first stamping mold; perform fault prediction on the first stamping mold according to the mold monitoring data to obtain a first mold predicted failure coefficient; determine whether the first mold predicted failure coefficient is greater than / equal to a predetermined mold predicted failure coefficient; if the first mold predicted failure coefficient is greater than / equal to the predetermined mold predicted failure coefficient, generate a first similar mold change instruction; perform similar mold change on the first stamping mold based on the first similar mold change instruction, and correct the first stamping task completion time node based on the first similar mold change instruction.

[0067] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0069] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An efficient stamping control method based on rapid die change, characterized in that: The method comprises: Obtaining a first stamping production task being executed, wherein the first stamping production task corresponds to a first stamping die; Obtaining a second stamping production task to be executed, wherein the second stamping production task corresponds to a second stamping die; Perform multi-feature operation prediction on the first stamping die according to the first stamping production task, and determine a first die unloading completion time node; According to the first die unloading completion time node, the stamping die change process information is feature combed to obtain a first stamping die change node chain and a second stamping die change node chain, wherein the first stamping die change node chain refers to an operation node performed before or during die unloading, including the transportation and installation preparation of the die, and the second stamping die change node chain refers to an operation node performed after die unloading, including the adjustment and positioning of the die; Based on the first die unloading completion time node, performing die change decision optimization according to the first stamping die change node chain to obtain a first node stamping die change plan; Perform multi-feature die change optimization according to the second stamping die change node chain to obtain a second node stamping die change plan; Based on the first stamping die and the second stamping die, die change is performed according to the first node stamping die change plan and the second node stamping die change plan.

2. The efficient stamping control method based on rapid die change according to claim 1, characterized in that: Performing a multi-feature operation prediction on the first stamping die according to the first stamping production task to determine a first die unloading completion time node includes: Obtaining real-time stamping monitoring data corresponding to the first stamping production task; Based on the first stamping production task, predict the stamping task operation time according to the real-time stamping monitoring data to obtain the first stamping task completion time node; Collecting installation parameters of the first stamping die to obtain first die installation feature data; According to the first mold installation characteristic data, a mold unloading operation duration characteristic prediction is performed on the first stamping mold to obtain a first predicted mold unloading duration; The first stamping task completion time node and the first predicted mold unloading duration are integrated to generate the first mold unloading completion time node.

3. The efficient stamping control method based on rapid die change according to claim 2, characterized in that: Based on the first stamping production task, the stamping task operation time is predicted according to the real-time stamping monitoring data to obtain the completion time node of the first stamping task, including: Obtain a stamping task operation time feature record library, wherein the stamping task operation time feature record library includes a historical stamping production task record set, a historical stamping monitoring data record set, and a historical stamping task completion time node record set; Based on the stamping task operation time feature record library, training P stamping operation time prediction feature models, where P is a positive integer greater than 1; Based on the first stamping production task and the real-time stamping monitoring data, and according to the P stamping operation time prediction feature models, P predicted stamping task completion time nodes are obtained; The P predicted stamping task completion time nodes are integrated to generate the first stamping task completion time node.

4. The efficient stamping control method based on rapid die change according to claim 1, characterized in that: Based on the first die unloading completion time node, the die change decision optimization is performed according to the first stamping die change node chain to obtain the first node stamping die change plan, including: Make a die change decision according to the first stamping die change node chain to obtain an initial stamping die change plan for the first node; Perform parallel adjustments according to the initial stamping die change plan of the first node to obtain multiple first node adjusted stamping die change plans; According to the plurality of first nodes, the stamping die change schemes are adjusted to perform die change time minimization prediction and optimization, so as to obtain the minimum die change time of the first node and the first node winning stamping die change scheme corresponding to the minimum die change time of the first node; Based on the predetermined tolerance time, the trigger time characteristic of the first stamping die change node chain is calculated in combination with the first die unloading completion time node and the first node minimum die change time to obtain the first node trigger time characteristic; The stamping die changing plan of the first node is generated according to the triggering time characteristics of the first node and the winning stamping die changing plan of the first node.

5. The efficient stamping control method based on rapid die change according to claim 1, characterized in that: Performing multi-feature die change optimization according to the second stamping die change node chain to obtain a second node stamping die change plan includes: According to the predetermined die change production adaptability, the die change optimization is performed in combination with the second stamping die change node chain to obtain a second node optimization stamping die change solution set; According to the second node optimal stamping die change plan set, parallel adjustment is performed to obtain the second node adjusted stamping die change plan set; According to the second node, the stamping die change plan set is adjusted to predict the die change duration, and a plurality of second node predicted die change durations are obtained; Based on the predicted die change times of the multiple second nodes, the die change time of the second node adjustment stamping die change plan set is minimized and optimized, and the stamping die change plan of the second node is output.

6. The efficient stamping control method based on rapid die change according to claim 5, characterized in that: According to the predetermined die change production adaptability, the die change optimization is performed in combination with the second stamping die change node chain to obtain a second node optimization stamping die change solution set, including: Obtaining basic die information corresponding to the second stamping die, making a die change decision based on the second stamping die change node chain, and obtaining a plurality of second node initial die change decisions; Perform multi-feature mold change production prediction according to the multiple second node initial mold change decisions to obtain multiple mold change production prediction results, wherein each mold change production prediction result includes a predicted mold change production quality coefficient and a predicted mold state evaluation coefficient; Performing normalization processing on the plurality of mold change production prediction results to establish a mold change production prediction matrix; Performing weighted calculation on the mold change production prediction matrix according to the mold change production fitness weight condition to obtain the mold change production fitness matrix; Based on the predetermined die change production fitness and the die change production fitness matrix, an optimization analysis is performed on the plurality of second node initial die change decisions to generate a second node optimal stamping die change solution set; The solution capacity of the second node for optimizing the stamping die change solution set is equal to the predetermined solution capacity.

7. The efficient stamping control method based on rapid die change according to claim 2, characterized in that: Based on the first stamping production task, the stamping task operation time is predicted according to the real-time stamping monitoring data to obtain the completion time node of the first stamping task, including: Obtaining mold monitoring data corresponding to the first stamping mold; Performing fault prediction on the first stamping die according to the die monitoring data to obtain a first die predicted fault coefficient; Determining whether the first mold predicted failure coefficient is greater than / equal to a predetermined mold predicted failure coefficient; If the first mold predicted failure coefficient is greater than / equal to the predetermined mold predicted failure coefficient, generating a first similar mold change instruction; The first stamping die is subjected to the same type of die change based on the first same type of die change instruction, and the completion time node of the first stamping task is corrected based on the first same type of die change instruction.

8. High-efficiency stamping control system based on rapid die change, characterized in that: For implementing the efficient stamping control method based on rapid die change according to any one of claims 1 to 7, the system comprises: A first task acquisition module, the first task acquisition module is used to obtain a first stamping production task being executed, wherein the first stamping production task corresponds to a first stamping die; A second task acquisition module, the second task acquisition module is used to obtain a second stamping production task to be executed, wherein the second stamping production task corresponds to a second stamping die; A prediction module, the prediction module is used to perform multi-feature operation prediction on the first stamping die according to the first stamping production task, and determine a first die unloading completion time node; A feature combing module, wherein the feature combing module is used to perform feature combing on the stamping die change process information according to the first die unloading completion time node, and obtain a first stamping die change node chain and a second stamping die change node chain, wherein the first stamping die change node chain refers to an operation node performed before or during die unloading, including the transportation and installation preparation of the die, and the second stamping die change node chain refers to an operation node performed after die unloading, including the adjustment and positioning of the die; A first optimization module, the first optimization module is used to optimize the die change decision based on the first die unloading completion time node and the first stamping die change node chain to obtain a first node stamping die change plan; A second optimization module, the second optimization module is used to perform multi-feature die change optimization according to the second stamping die change node chain to obtain a second node stamping die change plan; A die changing module is used to change the die based on the first stamping die and the second stamping die according to the first node stamping die changing scheme and the second node stamping die changing scheme.

Citation Information

Patent Citations

  • System and method for predicting metal additive manufacturing time based on data fusion

    CN114580744A

  • Quick die changing method and system for full-automatic forging production line

    CN116748447A

  • Full-process production method and system for intelligent integrated precast beam factory

    CN117944173A

  • Visual mold flexible production scheduling method and system

    CN117973813A

  • Manufacturing method and an injection molding system

    US20220212380A1