Full-process packaging management and control system and method based on digital twinborn model

Abstract

The invention discloses a full-process packaging management and control system and method based on a digital twinborn model, relates to the technical field of packaging management, and forms a full-process closed-loop management and control system from external demand perception to internal packaging process optimization through digital twinborn model and multi-source data fusion. By integrating data such as an order system, market feedback, a production plan and an equipment state, the problem of data islands in traditional packaging production is solved, and real-time fusion of external requirements and internal data is realized; a multi-source data weighting and cleaning fusion mechanism is adopted, and a packaging scheme is ensured to be closer to an actual production environment through digital twinborn simulation and evaluation; through a multi-target optimization algorithm, conflicts and coupling effects among a plurality of targets are accurately captured, and the decision accuracy is improved. Through rapid deployment and a closed-loop feedback mechanism, the production line is monitored and adjusted in real time, the production efficiency and quality are improved, the production cost is reduced, the efficiency and the product quality are improved, and meanwhile the environmental influence is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of packaging management, and specifically to a full-process packaging management and control system and method based on a digital twin model. Background Art

[0002] As the status of the packaging industry in the modern manufacturing system continues to improve, more and more companies have begun to introduce data acquisition systems, industrial Internet of Things platforms, and digital twin models to achieve visualization and optimization management of packaging processes. Traditional packaging lines usually adjust equipment parameters through experience or limited offline experiments, and can maintain production efficiency under single output and less change conditions. However, in the face of the current multi-variety, small-batch order model, as well as the frequent changes in external market demand, such traditional methods are often difficult to follow up in a timely manner. Although some existing technologies can achieve basic monitoring of the operating status of equipment such as packaging machines and labeling machines, and also use certain algorithms for data analysis, when processing multi-source data (such as external orders, material supply batches, ambient temperature, and internal quality inspection results, etc.), there are still widespread limitations such as poor data connection or only single-dimensional analysis. The resulting production decisions lack real-time response to external changes, and the packaging process is still mainly based on "after-the-fact adjustment", making it difficult to form an efficient and flexible packaging management and control system.

[0003] In the Chinese invention patent with application publication number CN115809789A, a product packaging management system based on data analysis is disclosed, which is as follows: obtaining product information to be packaged, transmitting the product information to the analysis and measurement module to analyze the product information and obtain analysis data, measuring the product in the obtained analysis data to obtain measurement data; transmitting the measurement data to the product packaging production module, the product packaging generation module generates product packaging information based on the measurement data and the analysis data; the packaging evaluation module obtains the product packaging information, evaluates the product based on the obtained product packaging information, and selects the highest evaluation groups of packaging price information; the packaging price information and the product packaging information are transmitted to the material calculation module, the material calculation module calculates the materials required for the product. The present invention obtains the packaging product information, generates the product specification information, generates the packaging box body by combining the specification information with the product weight information, and effectively manages the product packaging process.

[0004] However, in actual application, due to the lack of a unified dynamic integration mechanism between external demand information (such as new material batches or order specification changes) and internal production process data, the digital twin model is difficult to adjust the key parameters of each node in a timely manner, which leads to problems such as long switching cycles, increased abnormality rates, or excessive manual intervention in the packaging line. Specifically, when an enterprise receives materials from different batches or different suppliers, if its physical properties or producibility parameters are not updated in a timely manner in the digital twin system, it is easy to produce small but continuously accumulated deviations in key links such as labeling and sealing, thereby affecting the production line rhythm, packaging quality and even the overall yield. At the same time, when making changes to packaging specifications or quickly launching new products, due to the lack of global quantitative evaluation of the actual workload and process constraints of the production line equipment, it often requires multiple attempts or shutdown adjustments to gradually approach a stable state, which significantly reduces the flexibility and efficiency of packaging production.

[0005] To this end, the present invention provides a full-process packaging management and control system and method based on a digital twin model. Summary of the invention

[0006] 1. Technical issues to be resolved In view of the deficiencies of the prior art, the present invention provides a full-process packaging control system and method based on a digital twin model. Through the digital twin model and multi-source data fusion, a full-process closed-loop control system from external demand perception to internal packaging process optimization is formed; by integrating order systems, market feedback, production plans, equipment status and other data, the data island problem in traditional packaging production is solved, and the real-time fusion of external demand and internal data is realized; a multi-source data weighting and cleaning fusion mechanism is adopted, and through digital twin simulation and evaluation, the packaging solution is ensured to be closer to the actual production environment; through a multi-objective optimization algorithm, the conflict and coupling effects between multiple objectives are accurately captured, and the decision-making accuracy is improved. Through rapid deployment and closed-loop feedback mechanism, the production line is monitored and adjusted in real time, which improves production efficiency and quality, while reducing environmental impact. Thereby solving the technical problems recorded in the background technology.

[0007] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The full-process packaging control method based on the digital twin model includes: Collect external demand data and internal packaging data through a unified interface, define the reliability index of each data source, fuse each data source through a weighted algorithm, and generate a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; The fused dataset After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. After determining the optimization goal, the multi-objective optimization algorithm is used to comprehensively evaluate each packaging solution. The constructed comprehensive offset function captures the collaborative conflicts among multiple goals, finds the balance point among multiple goals, and automatically selects the optimal or suboptimal solution based on the optimization results, and generates specific adjustment suggestions. After the selected optimal or suboptimal packaging solution is deployed to the actual packaging production line, a small-batch trial production is carried out to collect production line data and detect deviations from the model prediction. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm for model correction or solution adjustment.

[0008] Furthermore, external demand data and internal packaging data are collected, and a data source set is set ,in, , where each Represents a type of data source and defines the reliability index of each data source , based on the reliability index Calculate the normalized weight coefficient And get the initial data set of weighted fusion , the weighted formula is set as follows: ; Where: is the reliability index of the data source, , For the The nonlinear deviation index of the data source is the preprocessing function performed on the original data. .

[0009] Furthermore, the initial data set of the output weighted fusion Perform outlier detection and consistency correction, and define multi-attribute offset functions The deviation of the i-th record from the reference pattern is measured as follows: ; Where: For the The record is in The actual value of the key attribute, The central value of the benchmark distribution of key attributes, is the total number of attribute dimensions; is the overall sensitivity magnification factor, Separate nonlinear deviation index for each attribute; is the trade-off coefficient of the attribute co-offset term, is the nonlinear index of the cooperative offset term; like If the deviation exceeds the given threshold, the data is considered abnormal and an appropriate correction method is selected based on the business scenario and subsequent usage requirements.

[0010] Furthermore, the format of the dataset after abnormal filtering and correction is normalized, and the fused dataset is finally output. According to the input interface and model requirements of the target digital twin system, the data fields are mapped, data types are converted, and timestamps are aligned. The fused data set after format conversion is named .

[0011] Furthermore, the fusion dataset Load it into the digital twin environment to define the equipment model, process structure, and adjustable packaging solution parameter set involved in the actual production line; Through the device description module of the digital twin system, the device structure and dynamic characteristics are associated, making it possible to call the fusion data set The equipment status field in the digital twin system; register the unique identification of all workstations in the digital twin system ; Introduce the packaging scheme parameters to be evaluated, denoted as , each Corresponding packaging parameter combinations are pre-configured in the digital twin system Matching adjustable machine parameters.

[0012] Furthermore, for each packaging scheme parameter Simulations are performed in the digital twin environment in sequence to obtain the performance indicators of each key workstation under the packaging solution, and the following packaging collaborative efficiency evaluation function is defined : ; in: Indicated in the plan Next, relative to the workstation The offset of the set reference process parameters, For workstation The weight coefficient in the overall packaging process, For workstation The nonlinear amplification factor is is the attribute synergy item trade-off coefficient, is the exponential term of the cooperative offset, is the workstation number; is the total number of workstations; Packaging synergy effectiveness evaluation function The lower the value, the better the solution The smaller the coordination deviation under the current working conditions; For all packaging options The simulation results are summarized; for each packaging solution Produced The results and performance indicators are integrated to form a simulation result table , providing visual display of key indicators and marking special situations or abnormal scenarios.

[0013] Furthermore, from the simulation results table The target dimensions that meet the needs of the enterprise are extracted and clarified as the input of the multi-objective optimization problem, including four target dimensions, among which: Representation scheme Average quality deviation index; Representation scheme Total cost per unit of output; Representation scheme Total production cycle or changeover time at a specified output; Representation scheme Environmental impact indicators; Defining the comprehensive offset function , to quantify the solution The overall performance under the four target dimensions and their interactive effects: ; Where: For the goal reference value or expected value; For the goal The weight factor in the overall evaluation is is the single target nonlinear deviation index; is the amplification factor of the cooperative offset term, is the nonlinear index of the multi-objective interaction term; when the comprehensive offset function The smaller the value, the better the packaging solution. The overall goal is closer to the ideal goal of the enterprise And the multi-objective interaction conflict is smaller than expected, otherwise it means that there is a greater-than-expected comprehensive offset.

[0014] Furthermore, a multi-objective optimization algorithm is executed to search for a set of candidate optimal solutions, and an improved evolutionary algorithm, mixed integer programming or other high-performance solvers may be used; after the iteration is completed, a series of approximate Pareto frontier solutions are output, that is, a set of solutions that achieve a relative balance between multiple objective dimensions; The output multi-objective candidate solutions are screened and visualized, and finally a list of optimal or suboptimal solutions is formed, as follows: the parameter set of all packaging solutions as candidate solutions According to its comprehensive offset function The values ​​are sorted in ascending order, and the top solutions with the best performance are marked; If an enterprise has a strong preference for a certain goal, it can be based on the goal importance factor or reference value Rescreen and narrow down the solution set available for deployment; highlight the solutions that meet the key constraints in the visualization view, and record the optimal or suboptimal solution finally selected as , and attach the corresponding numerical indicators and recommended parameter adjustment information to form a decision list .

[0015] Furthermore, the selected packaging solution Rapid deployment, including: The packaging materials, label design, size specifications and corresponding machine tuning parameters are written into the control system of the actual packaging production line according to the established mapping relationship; the corresponding hardware interface tags are registered ; The optimal or suboptimal solution Packaging into configuration files or container images and loading them into the production line; using a unified parameter management module, optimal or suboptimal solutions are The core variables are injected into each station Next, make a consistency comparison between the hardware parameters and the digital twin model parameters, and enter the trial production state after confirming that there is no conflict.

[0016] Furthermore, the deployed packaging solution Conduct small batch production and monitor in real time through the digital twin system to collect information on deviations between actual output and model predictions. Start the actual operation of the production line and Install high-frequency data acquisition devices to transmit process data back to the digital twin system in real time; Introducing dynamic offset increment function For Real-time records at time If the If the threshold is exceeded, it is considered abnormal and an alarm or automatic rollback strategy is triggered. , that is, the deviation detection results are stored in the intermediate result table .

[0017] Furthermore, a dynamic offset increment function is introduced For Real-time records at time The assessment is conducted as follows: ; Where: Indicates Products in time The corresponding value predicted by the digital twin model represents the quality indicator of the product. Process variables, is the model prediction value; and The relative weights of single indicator deviation and multi-indicator collaborative deviation are controlled respectively; is the number of indicators; and is the nonlinear amplification factor.

[0018] Furthermore, for the abnormal deviation records found, the corresponding process data is compared with the input features of the digital twin model to find out the possible source of the error; according to the deviation distribution, the relevant model parameters or external process assumptions are adaptively updated to reduce future prediction errors; If the deviation is serious enough to affect the plan If the feasibility is confirmed, the newly collected data is returned to the multi-objective optimization algorithm to supplement and update the decision space and use the revised digital twin model to optimize the solution. Or other possible solutions Recalculate the comprehensive offset to determine whether the current deployment plan needs to be switched or fine-tuned; if the deviation of the trial production after correction If it has returned to an acceptable range, it will be set as the default solution for mass production.

[0019] The full-process packaging control system based on the digital twin model includes: The data collection and fusion module collects external demand data and internal packaging data through a unified interface, defines the reliability index of each data source, fuses each data source through a weighted algorithm, and generates a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; Packaging strategy simulation module, which will fuse the data set After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. The multi-objective optimization module, after determining the optimization target, comprehensively evaluates each packaging solution through the multi-objective optimization algorithm, captures the collaborative conflicts among multiple targets through the constructed comprehensive offset function, finds the balance point among multiple targets, automatically selects the optimal or suboptimal solution according to the optimization results, and generates specific adjustment suggestions; The solution deployment verification module deploys the selected optimal or suboptimal packaging solution to the actual packaging production line and then conducts small-batch trial production, collects production line data and detects deviations from model predictions. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm for model correction or solution adjustment.

[0020] (III) Beneficial effects The present invention provides a full-process packaging control system and method based on a digital twin model, which has the following beneficial effects: Through the digital twin model and multi-source data fusion, a full-process closed-loop control system is formed from external demand perception to internal packaging process optimization. By effectively integrating different data sources (such as order systems, market feedback, production plans, and equipment status, etc.), the data island problem in traditional packaging production is solved, and the real-time fusion of external demand and internal packaging data is achieved, providing accurate data support for packaging strategy simulation, evaluation, and optimization decisions.

[0021] The multi-source data weighting and cleaning fusion mechanism is adopted to weight different data sources to ensure that high-quality and timely data are prioritized in decision-making. The consistency between different data sources is ensured by standardizing the data and processing the unified timestamp. The packaging solution is simulated and evaluated by introducing the fused data set into the digital twin system. The synergy effect of multiple stations and multiple dimensions is included in the evaluation by introducing the packaging synergy efficiency evaluation function, ensuring that the simulation results are closer to the actual production environment and improving the feasibility and accuracy of the solution. By considering the synergy effect between stations, the limitations of single-station optimization are avoided.

[0022] The packaging solution is comprehensively evaluated through a multi-objective optimization algorithm to overcome the limitation of traditional methods that only consider a single objective (such as cost or quality). By introducing nonlinear deviation measures and collaborative offset terms, the optimization algorithm can accurately capture the conflicts and coupling effects between multiple objectives, improve the flexibility and accuracy of optimization decisions, and find a reasonable balance between quality, cost, production efficiency and environmental impact.

[0023] The optimization plan is applied to the actual production line through rapid deployment and closed-loop feedback mechanism. Through small-batch trial production and real-time monitoring, it can detect and correct deviations from model predictions in real time, ensure flexible adjustment of packaging solutions, ensure rapid response and continuous optimization of the production line, and improve production efficiency and quality.

[0024] The present invention solves various problems in packaging production through data fusion, digital twin simulation, multi-objective optimization and closed-loop feedback mechanism, and provides an innovative packaging management and control solution to reduce production costs, improve production efficiency and product quality, and reduce environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram of the whole process packaging control method of the present invention; Figure 2 It is a schematic diagram of the structure of the full-process packaging control system of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] See also Figure 1 The present invention provides a full-process packaging control method based on a digital twin model, including: Step 1: Collect external demand data and internal packaging data through a unified interface, define the reliability index of each data source, fuse each data source through a weighted algorithm, and generate a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; The step 1 includes the following contents: Step 101: Collect external demand data and internal packaging data, and weight each data source to reflect the reliability and timeliness of the data. ,in, , where each Represents a type of data source (such as order system, market feedback, production plan, equipment status, etc.); defines the reliability index of each data source , used to characterize the data integrity and update frequency of the data source, based on the reliability index Calculate the normalized weight coefficient And get the initial data set of weighted fusion , Can be positive or negative, the weighting formula is set as follows: ; Where: is the reliability index of the data source, , the larger the value, the more reliable the data is or the more timely the update is. It is an adjustable scale factor used to control the degree of magnification of high-reliability data sources and is the normalized weighting coefficient of the data source; For the The nonlinear deviation index of a data source. The larger the value, the more reliable the data or the more timely the update. It is an adjustable scale factor used to control the degree of amplification of high-reliability data sources and is the normalized weighting coefficient of the data source. ; Preprocessing function performed on raw data (e.g. unified timestamps and field mappings) to ensure the consistency of time series and field names of different data sources, which is the initial data set after weighted fusion; When using it, the data sources are graded and weighted to reduce the negative impact of low-quality or delayed data on the overall decision-making; the fields of each data source are first basically standardized to reduce data structure conflicts in subsequent steps. The form avoids using traditional statistical indicators such as variance or standard deviation, and has more flexible adjustability and nonlinear amplification effect; Step 102: Output the weighted fusion initial data set of step 101 Perform outlier detection and consistency correction, define multi-attribute offset functions to identify outlier records in multiple dimensions The deviation of the i-th record from the reference pattern is measured as follows: ; Where: For the The record is in The actual value of the key attribute, The reference mode or benchmark distribution center value of the key attributes (which can be obtained from business experience or prior models), is the total number of attribute dimensions; is the overall sensitivity magnification factor, It is used to control the overall amplification degree of the deviation accumulation. Separate nonlinear deviation index for each attribute, , The more sensitive the attribute, the It can be set larger to more obviously amplify the abnormality of the attribute; is the trade-off coefficient of the attribute co-offset term, Used to balance the contribution of single attribute bias and multi-attribute collaborative bias; is the nonlinear index of the co-shift term, The larger the value, the more it can amplify the impact of simultaneous deviations of multiple attributes; multi-attribute synergy , used to capture linkage anomalies where multiple attributes deviate from the reference mode at the same time, and can identify complex outliers that are difficult to detect with a single attribute. When this part has a large value, it means that at least two or more attributes have significant deviations together, which should attract extra attention; like If the deviation exceeds the given threshold, the data is considered abnormal and needs to be corrected or removed. For data records that are judged to be abnormal, an appropriate correction method is selected based on the business scenario and subsequent usage requirements. For example, mapping correction is performed according to the reference model. For serious abnormal records that cannot be corrected, they are directly removed. When used, the quality and accuracy of the data set are significantly improved through outlier detection and consistency correction. The introduction of multi-attribute offset functions can accurately detect outliers in multi-dimensional data, especially multi-attribute collaborative deviations, avoiding anomalies that cannot be detected by a single attribute. Classification and correction based on the size of the deviation avoids subsequent simulation errors or decision-making errors caused by data anomalies, providing high-quality input for the output of the final fused data set.

[0028] Step 103: normalize the format of the dataset after abnormal filtering and correction in step 102, and finally output the fused dataset , according to the input interface and model requirements of the target digital twin system, the data fields are mapped, data types are converted, and timestamps are aligned, which can be specifically divided into the following three aspects: Field normalization: align the name and order of each record with the input elements required by the digital twin to avoid ambiguity in the meaning of the field in subsequent models; data type unification: convert possible discrete / continuous mixed fields into numerical or enumeration types that are easy for digital twins to parse; timestamp recalibration: when the external demand data and internal packaging data are inconsistent in the collection frequency or time base, a unified time reference system is achieved through interpolation or truncation to support subsequent simulation and optimization; Finally, the fused dataset after format conversion is named , and clarify its metadata such as field definition, time range and possible value range, so that it can be directly read and simulated in the digital twin system in the next step; When used, the fused dataset after format conversion Match the interface and data model of the digital twin platform to reduce the additional processing cost of the docking link; clarify the meaning and range of each field in the form of metadata to ensure that the meaning can be interpreted consistently when calling subsequent steps, and output the fused data set through the final output Achieve unified expression from external demand to internal packaging data, laying the foundation for the next step of strategy simulation and multi-objective optimization; After completing the weighting and preliminary fusion of multi-source data, the initial data set is obtained ; The above Formula applied to Each record of the data is identified and quantified, and the degree of deviation of each record is determined accordingly, and the retention, correction or elimination is determined accordingly. After the processing is completed, the format conversion and final fusion output of step 103 can be entered. Data set marked The values ​​are evaluated and whether corrections or removals have been made, ensuring traceability and consistency for the next step, which is the packaging strategy simulation of the digital twin system.

[0029] Step 2: Fusion dataset After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. The step 2 includes the following contents: Step 201: In step 201, firstly, the fused data set outputted in step 1 is Load it into the digital twin environment; based on this environment, define the equipment model, process structure and adjustable packaging solution parameter set involved in the actual production line; through the equipment description module of the digital twin system, associate the structure and dynamic characteristics of the packaging machine, labeling machine, conveyor device, etc., so that it can call the fusion data set Equipment status fields related to equipment operating conditions, production capacity limits, etc.; To ensure the connection with the simulation process of subsequent steps, it is necessary to register the unique identification of all workstations or key components in the digital twin system here ; Introduce a set of packaging scheme parameters to be evaluated, denoted as , each A possible combination of packaging parameters such as packaging material, label style, size specifications, etc. is pre-configured and matched in the digital twin system. Matching adjustable machine parameters (such as packaging temperature, labeling accuracy, transmission speed, etc.) to support loading, switching and running one by one during subsequent simulation; When used, it can ensure that the digital twin model is consistent with the actual production line configuration, reduce the modeling deviation of subsequent simulations, and and Marking information can be directly called in subsequent steps without secondary matching or repeated conversion, forming a complete set of equipment-process-parameter set basis, laying a good foundation for parallel simulation of multiple packaging strategies; Step 202: for each packaging solution parameter defined in step 201 Discrete event or hybrid drive simulation is performed in the digital twin environment in turn to obtain performance indicators such as production efficiency, quality indicators, and switching time of each key station under the packaging solution. In order to comprehensively measure the advantages and disadvantages of the solution, the following packaging collaborative efficiency evaluation function can be defined : ; in: Indicated in the plan Next, relative to the workstation The offset of the set reference process parameters can be dynamically calculated by the digital twin during the simulation process based on the actual equipment characteristics or production capacity limit; For workstation The weight coefficient in the overall packaging process, , used to reflect its relative importance to output quality or beat; For workstation The nonlinear amplification factor, which is greater than 0, determines the sensitivity to the single-station offset; It is the attribute coordination item weight coefficient, which is usually a positive number or 0, and is used to control the linkage amplification effect when deviations occur in multiple stations at the same time; is the exponential term of the cooperative offset, , the larger the value, the more it will amplify the impact of multi-station coupling deviation: is the workstation number; is the total number of workstations; Among them, packaging synergy performance evaluation function The lower the value, the better the solution The smaller the coordination deviation under the current working conditions, the higher the overall execution efficiency or quality potential.

[0030] It should be noted that when performing simulation, you need to follow the following process: Scheme loading: Load the current scheme The corresponding parameters are sent to each workstation module in the digital twin system; Scheduling execution: simulate the production process, including process queuing, processing cycle, transmission waiting and other links, and record the actual output quantity, duration and quality inspection information; Index extraction: Calculate for each workstation Equal offset index, and substitute it into the packaging synergy effectiveness evaluation function Perform numerical solutions and record other auxiliary indicators (such as defective rate, unit energy consumption, etc.); When used, by wrapping the synergistic performance evaluation function Including the multi-station coupling effect in the same evaluation function is conducive to quickly identifying efficiency bottlenecks or quality shortcomings on complex production lines; nonlinear exponential amplification and synergy The introduction of can magnify the potential risks caused by the synchronization deviation of key stations and avoid focusing only on single-point optimization: after execution, each packaging solution Each of them will correspond to a clear set of simulation results and deviation indicators, providing a basis for the visualization and summary analysis in the next step.

[0031] Step 203: For all packaging solutions The simulation results (including numerical values ​​and other auxiliary indicators); for each packaging solution Produced The results and performance indicators such as defective rate, switching time, energy consumption, etc. are integrated to form a result table ; For key indicators (such as , output, quality pass rate), providing visual displays such as line graphs, histograms or heat maps, so that subsequent decision-making links can quickly identify advantages and disadvantages; marking special situations or abnormal scenarios (such as workstation shutdowns, excessive deviations) for reference or exclusion when making multi-objective trade-offs in the next stage.

[0032] When used, form the parameters from the program To core assessment value Then to the detailed workstation indicators The complete mapping can be used for comprehensive measurement of subsequent decisions, lower the threshold of understanding through visualization, improve the efficiency of identifying key anomalies or workstation bottlenecks, provide simulation-verified indicator input for multi-objective optimization links, and avoid blind optimization directly on raw data.

[0033] Step 3: After determining the optimization goal, comprehensively evaluate each packaging solution through a multi-objective optimization algorithm. The constructed comprehensive offset function captures the collaborative conflicts among multiple goals, finds the balance point among multiple goals, automatically selects the optimal or suboptimal solution based on the optimization results, and generates specific adjustment suggestions. The step three includes the following contents: Step 301: First, output the simulation result table from step 2. The target dimensions that meet the needs of the enterprise are extracted and defined as the input of the multi-objective optimization problem. In order to more flexibly characterize the complex needs in the packaging process, the main optimization objectives can be defined as four target dimensions: quality, cost, production efficiency and environmental load, which are recorded as: , , , ,in: Representation scheme Average quality deviation indicator (such as nonlinear amplification of defect rate); Representation scheme Total cost per unit of output; Representation scheme Total production cycle or changeover time at a specified output; Representation scheme Environmental impact indicators (such as weighted measurements of carbon emissions and energy consumption).

[0034] In order to better capture the synergistic trade-off effect in multi-objective combined evaluation, a comprehensive offset function is defined , to quantify the solution The overall performance under the four target dimensions and their interactive effects: ; Where: For the goal Reference value or expected value (which can be given by historical data or corporate benchmark strategy); For the goal The weight factor in the overall evaluation is , is the single target nonlinear deviation index, A larger index indicates greater sensitivity to deviations from the target; is the amplification factor of the cooperative offset term, Used to balance the influence of coupling effects among multiple objectives; is the nonlinear index of the multi-objective interaction term, Used to amplify or suppress the cumulative impact when multiple goals deviate from the ideal state at the same time; pass and coproduct It can realize nonlinear amplification of large deviations, and thus more accurately evaluate multi-target conflicts. The smaller the value, the better the packaging solution. The overall goal is closer to the ideal goal of the enterprise and the multi-objective interaction conflict is smaller than expected, otherwise it means that there is a greater-than-expected comprehensive offset; When in use, the comprehensive performance of the packaging strategy is accurately described in a multi-objective form to avoid one-sided optimality under a single indicator. The cumulative impact of multiple targets deviating at the same time is captured through collaborative offset terms. This is more in line with the characteristics of mutual restraint of multiple targets in actual production, clarifies the input source and symbolic meaning, and enables the optimization algorithm of subsequent steps to accurately call the corresponding indicators.

[0035] Step 302: Based on the comprehensive offset function defined in step 301 , execute multi-objective optimization algorithm to search for a set of candidate optimal solutions that take into account quality, cost, cycle and environment. Improved evolutionary algorithm, mixed integer programming or other high-performance solvers can be used. The specific process is as follows: According to the simulation results table , the feasible solution and its corresponding , , , The value is loaded into the initial solution set of the optimization algorithm; if you need to further expand the search space, you can Fine-tune the parameters (such as fine-tuning the sealing temperature, labeling speed, etc.), generate a small number of new solutions and incorporate them into the initial solution set; Set the number of iterations Or convergence criteria, when the algorithm has not yet converged, continue to follow Evaluate and update the solution set. In evolutionary algorithms, operations such as crossover and mutation can be used to generate new solutions. , and according to After comparing their advantages and disadvantages, the better performing solutions are selected. Non-dominated sorting or multi-objective crowding distance calculation is performed on the candidate solutions of each iteration to keep the candidate solutions. After multiple iterations in the target space are completed, a series of approximate Pareto frontier solutions are output, that is, a set of solutions that achieve a relative balance between multiple target dimensions such as quality, cost, cycle, and environment. The parameter set of each packaging solution is You can find them in the algorithm results. Numerical and final Evaluation value, which facilitates visualization and ranking recommendation in the next step; When used, through systematic search and iteration, taking into account the conflict and balance under multi-objective attributes, a variety of potential feasible solutions are provided to enterprises. The use of methods such as non-dominated sorting helps to retain a variety of high-quality solutions in complex target spaces, which is convenient for subsequent solution selection. The simulation results of step 2 are shown in the table. The data are closely connected, achieving an organic connection from numerical simulation to global optimization.

[0036] Step 303: Screen and visualize the multi-objective candidate solutions outputted in step 302, and finally form a list of optimal or suboptimal solutions, as follows: The parameter set for all packaging solutions that are candidate solutions According to its comprehensive offset function The values ​​are sorted in ascending order, and the top solutions with the best performance are marked; if the enterprise has a strong preference for a certain goal (such as emphasizing low cost or high quality), it can be based on the goal importance factor or reference value Rescreen and narrow down the solution set that can be deployed; Select a commonly used multi-objective visualization method (such as parallel coordinates, radar charts, or heat maps) to display the solution concentration. To facilitate subsequent operations, the solutions that have met the key constraints (such as minimum quality deviation and maximum production line utilization) can be highlighted in the visualization view, and the optimal or suboptimal solution finally selected can be recorded as , and attach the corresponding numerical indicators and recommended parameter adjustment information to form a Decision list ; When used, by using the integrated offset function Comprehensive sorting and visualization can quickly identify the best solutions that meet the production strategy and a clear decision list It enables step 4 to be directly deployed, reducing repeated confirmation or data docking. Multi-dimensional visualization provides an intuitive understanding of complex decision-making spaces, helping to timely identify potential risks and make effective trade-offs. By defining a multi-objective integrated migration function Quantitative packaging solutions , the degree of deviation in multiple dimensions such as quality, cost, cycle and environment, and the introduction of the collaborative deviation term in the form of product The method can capture the linkage conflicts between objectives and significantly improve the accuracy of describing the coupling of multiple objectives. It provides richer search space information for evolutionary algorithms or other solution methods. With the help of non-dominated sorting or other high-order optimization strategies, the distribution diversity of each solution in the target space can be maintained under the premise of ensuring the core needs of the enterprise, thereby generating a batch of Pareto frontier solutions to choose from. Finally, it assists managers in making decision suggestions that meet the actual production scenarios through visualization and sorting. Maintaining consistent naming and field mapping allows this step to be closely connected with the data in the previous process.

[0037] Step 4: After the selected optimal or suboptimal packaging solution is deployed to the actual packaging production line, a small batch trial production is carried out to collect production line data and detect deviations from model predictions. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm to correct the model or adjust the solution; The step 4 includes the following contents: Step 401: Decision list output according to step 3 , for the selected packaging solution Rapid deployment, the specific process includes: The packaging materials, label design, size specifications and corresponding machine tuning parameters are written into the control system of the actual packaging production line according to the established mapping relationship; the corresponding hardware interface tags are registered , and keep it in the deployment log for subsequent tracing; If the digital twin system adopts a microservice architecture, the optimal or suboptimal solution can be Packaging into configuration files or container images and loading them into the production line; using a unified parameter management module, optimal or suboptimal solutions are The core variables (such as temperature, pressure, labeling speed, etc.) are injected into each station at one time Ensure that the data fields of the digital twin system correspond to each other; compare the hardware parameters with the digital twin model parameters for consistency. After confirming that there is no conflict, the solution can be declared ready for trial production. When used, the implementation is from the decision list Efficient mapping to the actual parameters of the production line, reducing the risk of repeated manual configuration, retaining mapping logs and interface tags, which helps to quickly locate deployment problems in subsequent small-batch trial production. 3 Microservices or containerization mode makes the deployment process more flexible and more compatible; Step 402: Deploy the packaging solution, i.e., the optimal or suboptimal solution. Carry out small batch production and conduct real-time monitoring through the digital twin system to collect information on deviations between actual output and model predictions, providing a basis for subsequent closed-loop corrections; Set trial production batch Usually much smaller than the official scale), in order to minimize the large-scale losses caused by immature solutions; start the actual operation of the production line and Install high-frequency data acquisition devices to transmit process data (quality inspection, output rhythm, etc.) back to the digital twin system in real time; In order to identify the difference between actual production line performance and model prediction, a dynamic offset increment function is introduced For Real-time records at time Assessments will be conducted at: ; Where: Indicates Products in time The corresponding value predicted by the digital twin model represents the quality index of the product (such as sealing strength). Process variables (such as temperature, viscosity, etc.), is the model prediction value; and Respectively control the relative weights of single indicator deviation and multi-indicator collaborative deviation; the values ​​are all greater than 0. is the number of indicators; and is the nonlinear amplification coefficient, all values ​​are greater than 0, and it is used to significantly amplify large deviations; like If the threshold is exceeded, it is considered abnormal and an alarm or automatic rollback strategy is triggered. , that is, the deviation detection results are stored in the intermediate result table , additional timestamp, batch number and other information are attached, and the deviation distribution is dynamically displayed in the form of trend chart or heat map on the digital twin monitoring panel, which facilitates timely intervention by manual or automatic systems.

[0038] When in use, quickly verify the solution through small batch trial production Applicability in real production environments, reducing large-scale risks, The function provides a quantitative indicator for monitoring the nonlinear difference between actual and predicted values, which is suitable for quickly discovering major deviations in quality or process. Real-time visualization enables decision makers to understand the operation status of the production line at the first time and provides an objective basis for subsequent callbacks or corrections.

[0039] Step 403: For the abnormal deviation records found, the corresponding process data is compared with the input features of the digital twin model to find out the possible sources of the errors (such as equipment aging, inconsistent material batches, abnormal ambient temperature, etc.); according to the deviation distribution, the relevant model parameters (such as Small, equal nonlinear exponents) or external process assumptions (such as the upper limit of the station capacity) are adaptively updated to reduce future prediction errors If the deviation is serious enough to affect the plan If the feasibility is confirmed, the newly collected data is returned to the multi-objective optimization algorithm in step 3 to supplement and update the decision space and use the revised digital twin model to optimize the solution. Or other possible solutions Recalculate the comprehensive offset to determine whether the current deployment plan needs to be switched or fine-tuned; if the deviation of the trial production after correction If the performance has returned to an acceptable range, the production scale will be gradually expanded or set as the default solution for mass production. Otherwise, small batch verification and correction will be performed repeatedly until the solution performance meets the company's established goals or it is confirmed that other alternative solutions need to be replaced.

[0040] When in use, the deviation information obtained through real-time monitoring is immediately applied to the digital twin model, so that the model maintains high consistency with the real production line during continuous iteration: once there is a problem with the deployment, it will immediately return to the agile operation mode of re-searching in the optimization phase. Through multiple rounds of small batch iterations, the packaging strategy that best matches the actual production environment can be found in the shortest time, greatly shortening the development cycle; Through solution deployment, small batch trial production, real-time monitoring and closed-loop feedback, a dynamic correction loop is formed between the digital twin model and the real packaging production line. Different from traditional static decision-making, the nonlinear deviation measurement function is used to Combined with real-time data collection methods, accurate detection and flexible response to deviations can be achieved. It is highly coupled with the multi-objective optimization algorithm in the previous link and can trigger optimization search again based on newly emerging abnormal or deviation data, truly realizing adaptive iteration and continuous improvement.

[0041] Through the digital twin model and multi-source data fusion, a full-process closed-loop control system is formed from external demand perception to internal packaging process optimization. By effectively integrating different data sources (such as order systems, market feedback, production plans, and equipment status, etc.), the data island problem in traditional packaging production is solved, and the real-time fusion of external demand and internal packaging data is achieved, providing accurate data support for packaging strategy simulation, evaluation, and optimization decisions.

[0042] The multi-source data weighting and cleaning fusion mechanism is adopted to weight different data sources to ensure that high-quality and timely data are prioritized in decision-making. The consistency between different data sources is ensured by standardizing the data and processing the unified timestamp. The packaging solution is simulated and evaluated by introducing the fused data set into the digital twin system. The synergy effect of multiple stations and multiple dimensions is included in the evaluation by introducing the packaging synergy efficiency evaluation function, ensuring that the simulation results are closer to the actual production environment and improving the feasibility and accuracy of the solution. By considering the synergy effect between stations, the limitations of single-station optimization are avoided.

[0043] The packaging solution is comprehensively evaluated through a multi-objective optimization algorithm to overcome the limitation of traditional methods that only consider a single objective (such as cost or quality). By introducing nonlinear deviation measures and collaborative offset terms, the optimization algorithm can accurately capture the conflicts and coupling effects between multiple objectives, improve the flexibility and accuracy of optimization decisions, and find a reasonable balance between quality, cost, production efficiency and environmental impact.

[0044] The optimization plan is applied to the actual production line through rapid deployment and closed-loop feedback mechanism. Through small-batch trial production and real-time monitoring, it can detect and correct deviations from model predictions in real time, ensure flexible adjustment of packaging solutions, ensure rapid response and continuous optimization of the production line, and improve production efficiency and quality.

[0045] The present invention solves various problems in packaging production through data fusion, digital twin simulation, multi-objective optimization and closed-loop feedback mechanism, and provides an innovative packaging management and control solution to reduce production costs, improve production efficiency and product quality, and reduce environmental impact.

[0046] See also Figure 2 The present invention provides a full-process packaging management and control system based on a digital twin model, including: The data collection and fusion module collects external demand data and internal packaging data through a unified interface, defines the reliability index of each data source, fuses each data source through a weighted algorithm, and generates a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; Packaging strategy simulation module, which will fuse the data set After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. The multi-objective optimization module, after determining the optimization target, comprehensively evaluates each packaging solution through the multi-objective optimization algorithm, captures the collaborative conflicts among multiple targets through the constructed comprehensive offset function, finds the balance point among multiple targets, automatically selects the optimal or suboptimal solution according to the optimization results, and generates specific adjustment suggestions; The solution deployment verification module deploys the selected optimal or suboptimal packaging solution to the actual packaging production line and then conducts small-batch trial production, collects production line data and detects deviations from model predictions. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm for model correction or solution adjustment.

[0047] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0050] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0051] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A full-process packaging control method based on a digital twin model, characterized by: include, Collect external demand data and internal packaging data through a unified interface, define the reliability index of each data source, fuse each data source through a weighted algorithm, and generate a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; The fused dataset After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. After determining the optimization goal, the multi-objective optimization algorithm is used to comprehensively evaluate each packaging solution. The constructed comprehensive offset function captures the collaborative conflicts among multiple goals, finds the balance point among multiple goals, and automatically selects the optimal or suboptimal solution based on the optimization results, and generates specific adjustment suggestions. After the selected optimal or suboptimal packaging solution is deployed to the actual packaging production line, a small-batch trial production is carried out to collect production line data and detect deviations from the model prediction. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm for model correction or solution adjustment.

2. The full-process packaging control method based on the digital twin model according to claim 1 is characterized in that: Collect external demand data and internal packaging data, with a data source set ,in, , where each Represents a type of data source and defines the reliability index of each data source , based on the reliability index Calculate the normalized weighting coefficient And get the initial data set of weighted fusion , the weighted formula is set as follows: ； Where: is the reliability index of the data source, , For the The nonlinear deviation index of the data source is the preprocessing function performed on the original data. .

3. The full-process packaging control method based on the digital twin model according to claim 2 is characterized in that: Initial dataset for weighted fusion of outputs Perform outlier detection and consistency correction, and define multi-attribute offset functions The deviation of the i-th record from the reference pattern is measured as follows: ； Where: For the The record is in The actual value of the key attribute, The central value of the benchmark distribution of key attributes, is the total number of attribute dimensions; is the overall sensitivity magnification factor, Separate nonlinear deviation index for each attribute; is the trade-off coefficient of the attribute co-offset term, is the nonlinear index of the cooperative offset term; like If the deviation exceeds the given threshold, the data is considered abnormal and an appropriate correction method is selected based on the business scenario and subsequent usage requirements.

4. The full-process packaging control method based on the digital twin model according to claim 3 is characterized in that: Normalize the format of the dataset after anomaly filtering and correction, and finally output the fused dataset According to the input interface and model requirements of the target digital twin system, the data fields are mapped, data types are converted, and timestamps are aligned. The fused data set after format conversion is named .

5. The full-process packaging control method based on the digital twin model according to claim 4 is characterized in that: The fused dataset Load it into the digital twin environment to define the equipment model, process structure, and adjustable packaging solution parameter set involved in the actual production line; Through the device description module of the digital twin system, the device structure and dynamic characteristics are associated, making it possible to call the fusion data set The equipment status field in the digital twin system; register the unique identification of all workstations in the digital twin system ; Introduce the packaging scheme parameters to be evaluated, denoted as , each Corresponding packaging parameter combinations are pre-configured in the digital twin system Matching adjustable machine parameters.

6. The full-process packaging control method based on the digital twin model according to claim 5 is characterized in that: For each packaging scheme parameter Simulations are performed in the digital twin environment in sequence to obtain the performance indicators of each key workstation under the packaging solution, and the following packaging collaborative efficiency evaluation function is defined. : ； in: Indicated in the plan Next, relative to the workstation The offset of the set reference process parameters, For workstation The weight coefficient in the overall packaging process, For workstation The nonlinear amplification factor is is the attribute synergy item trade-off coefficient, is the exponential term of the cooperative offset, is the workstation number; is the total number of workstations; Packaging synergy effectiveness evaluation function The lower the value, the better the solution The smaller the coordination deviation under the current working conditions; For all packaging options The simulation results are summarized; for each packaging solution Produced The results and performance indicators are integrated to form a simulation result table , providing visual display of key indicators and marking special situations or abnormal scenarios.

7. The full-process packaging control method based on the digital twin model according to claim 6 is characterized in that: From the simulation results table The target dimensions that meet the needs of the enterprise are extracted and clarified as the input of the multi-objective optimization problem, including four target dimensions, among which: Representation scheme Average quality deviation index; Representation scheme Total cost per unit of output; Representation scheme Total production cycle or changeover time at a specified output; Representation scheme Environmental impact indicators; Defining the comprehensive offset function , to quantify the solution The overall performance under the four target dimensions and their interactive effects: ； Where: For the goal reference value or expected value; For the goal The weight factor in the overall evaluation is is the single target nonlinear deviation index; is the amplification factor of the cooperative offset term, is the nonlinear index of the multi-objective interaction term; when the comprehensive offset function The smaller the value, the better the packaging solution. The overall goal is closer to the ideal goal of the enterprise And the multi-objective interaction conflict is smaller than expected, otherwise it means that there is a greater-than-expected comprehensive offset.

8. The full-process packaging control method based on the digital twin model according to claim 7 is characterized in that: Execute a multi-objective optimization algorithm to search for a set of candidate optimal solutions. Improved evolutionary algorithms, mixed integer programming or other high-performance solvers can be used. After the iteration is completed, a series of approximate Pareto frontier solutions are output, that is, a set of solutions that achieve a relative balance between multiple objective dimensions. The output multi-objective candidate solutions are screened and visualized, and finally a list of optimal or suboptimal solutions is formed, as follows: the parameter set of all packaging solutions as candidate solutions According to its comprehensive offset function The values ​​are sorted in ascending order, and the top solutions with the best performance are marked; If an enterprise has a strong preference for a certain goal, it can be based on the goal importance factor or reference value Rescreen and narrow down the solution set available for deployment; highlight the solutions that meet the key constraints in the visualization view, and record the optimal or suboptimal solution finally selected as , and attach the corresponding numerical indicators and recommended parameter adjustment information to form a decision list .

9. The full-process packaging control method based on the digital twin model according to claim 8 is characterized in that: For the selected packaging solution Rapid deployment, including: The packaging materials, label design, size specifications and corresponding machine tuning parameters are written into the control system of the actual packaging production line according to the established mapping relationship; the corresponding hardware interface tags are registered ; The optimal or suboptimal solution Packaging into configuration files or container images and loading them into the production line; using a unified parameter management module, optimal or suboptimal solutions are Core variables are injected into each station Next, make a consistency comparison between the hardware parameters and the digital twin model parameters, and enter the trial production state after confirming that there is no conflict.

10. The full-process packaging control method based on the digital twin model according to claim 9 is characterized in that: Deployed packaging solutions Conduct small batch production and monitor in real time through the digital twin system to collect information on deviations between actual output and model predictions. Start the actual operation of the production line and Install high-frequency data acquisition devices to transmit process data back to the digital twin system in real time; Introducing dynamic offset increment function For Real-time records at time If If the threshold is exceeded, it is considered abnormal and an alarm or automatic rollback strategy is triggered. , that is, the deviation detection results are stored in the intermediate result table .

11. The full-process packaging control method based on the digital twin model according to claim 10 is characterized in that: Introducing dynamic offset increment function For Real-time records at time The assessment is conducted as follows: ； Where: Indicates Products in time The corresponding value predicted by the digital twin model represents the quality indicator of the product. Process variables, is the model prediction value; and The relative weights of single indicator deviation and multi-indicator collaborative deviation are controlled respectively; is the number of indicators; and is the nonlinear amplification factor.

12. The full-process packaging control method based on the digital twin model according to claim 11 is characterized in that: For the abnormal deviation records found, the corresponding process data is compared with the input features of the digital twin model to find out the possible source of the error; according to the deviation distribution, the relevant model parameters or external process assumptions are adaptively updated to reduce future prediction errors; If the deviation is serious enough to affect the plan If the feasibility is confirmed, the newly collected data is returned to the multi-objective optimization algorithm to supplement and update the decision space and use the revised digital twin model to optimize the solution. Or other possible solutions Recalculate the comprehensive offset to determine whether the current deployment plan needs to be switched or fine-tuned; if the deviation of the trial production after correction If it has returned to an acceptable range, it will be set as the default solution for mass production.

13. The full-process packaging control system based on the digital twin model is characterized by: include, The data collection and fusion module collects external demand data and internal packaging data through a unified interface, defines the reliability index of each data source, fuses each data source through a weighted algorithm, and generates a fused data set after data cleaning and preprocessing. , for subsequent packaging strategy simulation and multi-objective optimization; Packaging strategy simulation module, which will fuse the data set After importing the digital twin system, a packaging strategy simulation scenario is constructed. In the simulation scenario, simulation analysis is performed based on the solution parameters. After the corresponding performance indicators are generated, the effectiveness of different packaging solutions is evaluated by the constructed packaging synergy effectiveness evaluation function. The multi-objective optimization module, after determining the optimization target, comprehensively evaluates each packaging solution through the multi-objective optimization algorithm, captures the collaborative conflicts among multiple targets through the constructed comprehensive offset function, finds the balance point among multiple targets, automatically selects the optimal or suboptimal solution according to the optimization results, and generates specific adjustment suggestions; The solution deployment verification module deploys the selected optimal or suboptimal packaging solution to the actual packaging production line and then conducts small-batch trial production, collects production line data and detects deviations from model predictions. If an abnormal deviation occurs, the feedback mechanism is immediately triggered to feed the deviation data back to the optimization algorithm for model correction or solution adjustment.

Images