Digital twinning simulation and optimization system for product packaging production line

Abstract

The invention discloses a digital twinning simulation and optimization system for a product packaging production line, and particularly relates to the field of digital twinning, the system divides the production line into a plurality of sections with definite functions through a sub-region function end division module, and stable and real-time changing parameters are respectively acquired and stored by means of an acquisition module; a reference model of each sub-region function end is constructed based on the static parameters, and a real-time production state model construction module carries out correction on the reference model by incorporating multi-dimensional variable interference; parameters are called in real time for comparison by adopting an intelligent algorithm; and performing secondary data acquisition based on the repaired attention state data according to the output and parameter comparison result of the sub-region function end, establishing a real-time production state model, performing secondary comparison with the digital twin ideal model, and finishing repair when the difference interval of the attention state data accords with the theoretical difference. And if not, outputting the number to the user side for manual repair.

Description

[0001] This invention relates to the field of digital twin technology, and more specifically, to a digital twin simulation and optimization system. Background Technology

[0002] Digital twins are virtual mirror images of physical entities, and are dynamic digital models that are completely corresponding to real objects and systems through data-driven construction. The core of digital twins lies in establishing a real-time bidirectional mapping between the physical world and the digital space. The core working mechanism is (1) dynamic mapping, which continuously synchronizes the sensor data of physical entities, such as temperature, pressure, and position, to the virtual model to ensure that the two are in the same state. The mapping relationship is refined layer by layer from geometric level, physical level, behavioral level to rule level to establish the model. (2) simulation and deduction, which predicts future behavior based on the current state input through a physical engine or AI algorithm. By modifying the parameters of the virtual model, such as increasing the rotation speed or changing the material, the feasibility of the solution can be quickly verified and the cost of physical trial and error can be avoided. (3) closed-loop optimization, which compares the deviation between the ideal model and the actual operation, locates the root cause of the fault, and generates optimization strategies at the virtual end, such as adjusting the feed speed and scheduling maintenance work orders. The instructions are sent to the physical end control system for automatic execution, forming a closed loop of "perception-analysis-decision-execution".

[0003] However, in actual use, it still has some shortcomings: (1) There is an idealistic tendency in the modeling level. Due to the lack of reliable parameter basis verified by practice, it is necessary to explore the parameter range from scratch, and the trial and error direction is chaotic. Moreover, the monitoring equipment is often not calibrated, resulting in systematic deviation or distortion of the measurement data. When modeling with inaccurate data, the calculated ideal operating range will deviate from the true range of parameters, causing the model to be unable to accurately identify anomalies, resulting in false alarms or missed alarms, and ultimately causing the process monitoring and decision-making based on the model to fail. (2) From the modeling process, it is necessary to collect and accurately transform multi-dimensional information, which involves a lot of tedious work. The lack of information or error in each link may cause the model to deviate from the actual production scenario, and it is necessary to repeatedly verify and adjust it. (3) When adjusting the production sequence based on the actual production results, the mode of uniformly adjusting the entire production line is often adopted. Differential optimization is not carried out for the capacity differences of different processes, which easily causes some processes to have redundant output, that is, the output exceeds the actual demand. Summary of the Invention

[0004] A digital twin simulation and optimization system for product packaging production lines includes a sub-region functional division module: used to divide the entire production line into several sub-region functional ends according to the process flow of the product packaging production line; Parameter acquisition module: used to acquire static parameters required to build an ideal digital twin model for any sub-region functional terminal, mark the parameters corresponding to the static parameters in the real-time production process as dynamic parameters, and transmit and store the static parameter information and dynamic parameters to the system data storage unit; Model building module: Constructs a digital twin ideal model of the sub-region functional terminal based on static parameter information, and constructs a real-time production status model of the sub-region functional terminal based on dynamic parameter information; Real-time intelligent comparison module: Based on the ideal operating range of all parameters of the digital twin ideal model, the parameters of the real-time production status model that do not fall within the ideal operating range are recorded as imbalance data; The comparison result output module matches imbalanced keywords to imbalanced data, outputs corresponding repair instructions based on the imbalanced keywords, and completes the repair. The data for which repair instructions are given is recorded as data in the state of concern, and the data in the state of concern is continuously monitored. Comparison Result Detection Module: Based on the repaired data of concern, secondary data collection is performed to establish a new real-time production status model and compare it with the ideal model of digital twin. If the difference range of the data of concern conforms to the theoretical difference, the repair is completed. If it does not conform to the theoretical difference, the numbers are output to the user terminal for manual repair.

[0005] The technical effects and advantages of this invention are as follows: 1. The modular design of sub-region functional terminals breaks down the entire line into clearly defined independent sub-region functional terminals according to process logic, with independent parameter acquisition and optimization targets, retaining the information flow logic between segments, avoiding global model overload, realizing local optimization of local problems, and reducing the scope of fault diagnosis.

[0006] 2. Separate Acquisition of Static and Dynamic Parameters: Static parameters serve as the baseline anchor, remaining stable over a longer period and unaffected by short-term fluctuations in operating conditions, ensuring the stability of the baseline model. Dynamic parameters rapidly update their values ​​as operating conditions change, promptly reflecting the current state of the system and providing accurate real-time data for production decisions, enabling flexible control of the production process.

[0007] 3. At regular intervals, when no materials are running, the drift rate of the monitoring equipment is calculated. This drift rate is then combined with the actual production model to assess the degree of equipment wear and generate the current dynamic parameters of the equipment. When calculating the deviation of the actual parameters, this table can be used to specifically eliminate interference caused by changes in the performance of the equipment itself, making the deviation results more consistent with the actual production situation and providing a more reliable basis for production adjustments and quality control.

[0008] 4. By adjusting parameters based on historical high pass rate models, reliable parameter bases that have been verified in practice can be directly reused, greatly reducing the waste of resources and the risk of non-compliance caused by blind trial and error. It can quickly focus on key fine-tuning directions, significantly shortening the parameter optimization cycle while ensuring the stability of results. It is especially suitable for mass production or experimental scenarios with high requirements for both efficiency and quality. Attached Figure Description

[0009] Figure 1 This is a system structure framework diagram of the present invention.

[0010] Figure 2 This is a schematic diagram of the overall process of the present invention. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] like Figure 1 The system shown is a digital twin simulation and optimization system for product packaging production lines, including a sub-region functional division module, a parameter acquisition module, a model building module, a real-time intelligent comparison module, a comparison result output module, and a comparison result detection module.

[0013] like Figure 2 The digital twin simulation and optimization system for product packaging production lines shown divides the functional areas into sub-regions, collects static parameters to construct an ideal digital twin model, and calculates the drift rate and relative deviation of dynamic parameters of the monitoring equipment by comparing the actual production status with the ideal digital twin model. Based on the actual production status and production plan, the speed of the functional areas in the sub-regions is adjusted and optimized.

[0014] The sub-region functional division module is used to divide the entire production line into several sub-region functional ends with clearly defined functional boundaries and operational objectives, based on the product packaging production line's technological flow. Each sub-region functional end is dedicated to performing a specific function. These sub-region functional ends maintain both process continuity and targeted parameter collection. The division information for each sub-region functional end is stored in the sub-region functional end division unit. While maintaining process continuity, these sub-region functional ends also consider the targeted nature of parameter collection. Process continuity ensures that each sub-region functional end is connected in an orderly manner according to the production flow, avoiding process breaks or duplication. Targeted parameter collection means that each sub-region functional end can focus on collecting its own core process parameters, ensuring that the entire digital twin system can achieve refined management and optimization of the production line based on clear functional division. Stored data is saved in a field format, ensuring that the division results are traceable and retrievable.

[0015] The parameter acquisition module is used to collect static parameters required for building an ideal digital twin model at any sub-region functional end. Parameters corresponding to the static parameters during real-time production are marked as dynamic parameters. The static and dynamic parameter information is transmitted and stored in the system data storage unit. The static parameters are preset baseline values ​​that remain constant and do not change with any variables within the model during model building. The dynamic parameters are the deviations of the static parameters from the baseline values ​​obtained through real-time monitoring after variables influencing the parameters are included in the model; these deviations correspond one-to-one with the static parameters.

[0016] The model building module is used to read static parameters from the system's data storage unit. The digital twin ideal model, based on a 3D modeling engine, establishes a benchmark reference model for product packaging production lines. Its core is achieved through 1:1 geometric topological mapping, ideal production line operation modes, and conflict-free logical rule mapping. The digital twin ideal model is built based on factors affecting product yield, such as mold wear, sub-region functional end temperature, and sub-region functional end product flow coordination values. Mold wear causes deviations in mold size, shape, and surface accuracy from design standards, leading to product dimensional errors, appearance defects, and functional failures, ultimately directly lowering the yield rate. Sub-region functional end temperature directly affects key material properties during production; insufficient melting temperature results in poor melt flowability, while excessively high heat treatment temperatures cause material embrittlement, ultimately leading to product performance or molding defects. When the speed of the previous sub-region's functional end is faster than that of the next sub-region's functional end, the material will accumulate in the intermediate stage, which may lead to physical deformation or damage of the material, and will be directly judged as unqualified; when the speed of the previous sub-region's functional end is slower than that of the next sub-region's functional end, the next sub-region's functional end will enter intermittent idling due to material shortage, and incomplete processing is likely to occur when restarting processing.

[0017] The method for establishing an ideal digital twin model is as follows: S1: Digital Twin Model Mold Wear Calibration: Select a mold that meets production standards, use a contact roughness meter, select a probe suitable for the mold material hardness, and read the surface roughness, maximum surface height, and minimum surface height of the new production mold based on the measurement results. Read the mold surface hardness from the equipment manual and calculate the standard wear degree of the mold in the ideal digital twin model according to the formula, using the current wear degree of the production mold as a static parameter. Quantify the mold wear degree according to the core wear degree formula. Where Ra is the surface roughness, in μm or nm, and must be consistent with the hardness unit; rp is the maximum surface height, in μm or nm, a positive value calculated from the average baseline; rv is the minimum surface height, in μm or nm, a positive value calculated from the average baseline, representing the depth; and H is the surface hardness, in MPa or HV, and must be consistent with the length unit.

[0018] S2: Digital Twin Ideal Model Sub-region Functional End Temperature: Based on the process flow of the product packaging production line, the optimal temperature is set for each sub-region functional end based on the operating temperature of the production equipment; based on historical data, a temperature-pass rate overview table is established for the sub-region functional ends, showing the product pass rate corresponding to different production temperatures under the condition that all other production conditions are exactly the same. S3: Digital Twin Model Sub-region Functional Terminal Product Flow Coordination: Establish a stable and controllable product flow, ensuring that the output of the preceding sub-region functional terminal is completely equivalent to the processing volume of the following sub-region functional terminal. Based on the current operating speed, record the maximum output, actual output, maximum processing volume, actual processing volume, and maximum buffer capacity of the preceding and following sub-region functional terminals to calculate the sub-region functional terminal product flow coordination value, and record the current production efficiency as a static parameter; the formula is as follows: C act C max These represent the actual output and maximum output of the previous sub-region's functional end, respectively, Q. act Q max These are the actual output and maximum output of the next sub-region's functional end, respectively, and β is the ratio of the buffer inventory to the maximum buffer capacity.

[0019] The ideal digital twin model constructs a fixed skeleton for the production line. The real-time production status model does not change this skeleton, but only corrects the geometric model after each maintenance, thus escaping the pressure brought by a large number of algorithms.

[0020] The real-time production status model is based on and built upon the core framework of the ideal digital twin model. It utilizes real-time dynamic parameter acquisition and processing of the physical entities of the production line to calibrate the static parameter values ​​in the ideal digital twin model to reflect the actual operating status. This accurately and dynamically reproduces the digital model of the real-time operating status of the physical packaging production line, achieving real-time mapping and linkage between the physical production line and the digital model. In this example, dynamic parameters are collected every 20 seconds to establish the real-time production status model.

[0021] The real-time production status model is constructed using the same method as the ideal digital twin model. The mold wear level, sub-region functional end temperature, and sub-region functional end product flow coordination value are calculated using dynamic parameters based on real-time data transmitted from monitoring equipment, as follows: S1: Actual production mold wear calibration: Using a contact roughness meter, select a probe that matches the hardness of the mold material. Based on the measurement results, read the real-time surface roughness, real-time maximum surface height, and real-time minimum surface height of the production mold. Use the scratch method to measure the surface hardness of the production mold. Use a set of pencils with known hardness from soft to hard, and scratch the mold surface at a 45-degree angle. Find the hardest pencil that cannot scratch the coating, and use its hardness as the hardness of the mold surface.

[0022] S2: Real-time production status model sub-area functional end temperature: Set a contact sensor to read the production condition temperature of the sub-area functional end in real time and update it in real time; S3: Real-time production status model sub-region functional end product flow coordination value: Calculated by reading the maximum output and actual output of the previous sub-region functional end, the maximum processing volume and actual processing volume of the next sub-region functional end, and the maximum buffer capacity during the production process. Real-time intelligent comparison module: Based on the ideal operating range of all static parameters of the digital twin ideal model, parameters of the real-time production model that do not fall within the ideal operating range are recorded as imbalance data. The real-time intelligent comparison module periodically calibrates the offset value of the monitoring equipment, effectively eliminating the interference of equipment drift on dynamic parameter measurement and ensuring the authenticity of dynamic parameters.

[0023] The formula for calculating the drift value of monitoring equipment is: D: Represents the percentage of natural performance degradation per day; P t0 : This refers to the equipment's operating data immediately after maintenance; P t1 : No-load operation data of the equipment after an interval Δt; Δt: time interval between two no-load operations; After obtaining the offset value D of the monitoring equipment, the dynamic data is corrected using the offset value D of the monitoring equipment. The correction formula is: δ 正 : is the correction value after calibration; t is the number of days from the calibration date; δ is the measurement value of the equipment on day t.

[0024] The ideal operating range is set based on static parameters. The calculation method is as follows: For any dynamic parameter X, the ideal operating range is defined with the static parameter as the benchmark value. The calculation method for the ideal operating range is as follows: All product pass rates are sorted from best to worst, and the static parameters X1, X2, X3...X corresponding to the pass rates of the top n products are taken. n Calculate the sample mean Calculate the sample standard deviation Then the lower limit of the ideal operating range of the dynamic parameter X is The upper limit is Where n represents the first n historical data points; : The average of the static parameters corresponding to the first n pass rates; Z: The Z-value corresponding to the confidence level.

[0025] Lower limit of the prediction interval Let it be L i Predict the upper limit of the interval Let it be U i， When the dynamic parameter X of the monitoring equipment is calibrated i ⊂[L i U i When the value of this dynamic parameter is within the ideal operating range, it is considered acceptable. If the value of this dynamic parameter does not fall within the ideal operating range, it is marked as unbalanced data. The degree of imbalance h of the extreme value of the ideal operating range is calculated for the unbalanced data S. Data with an imbalance of h less than 8% is marked as slightly imbalanced, and data with an imbalance of h greater than 8% is marked as severely imbalanced. Imbalance keywords are compiled based on the data type, sub-region functional end, and imbalance data value.

[0026] The comparison result output module matches imbalance keywords to the imbalanced data, outputs corresponding repair instructions based on the imbalance keywords, and completes the repair. This applies to imbalanced data X that is not within the ideal operating range. i Set different processing methods when X i Greater than U i In such cases, the issue might be due to a deviation in the monitoring equipment, rather than the actual process reaching an unexpectedly high level of compliance. Instead of immediately adjusting production parameters, maintain the current equipment settings and reconfirm the monitoring equipment offset. If the deviation is not due to the monitoring equipment, record and analyze all dynamic parameters from this run. If it is due to the monitoring equipment, handle the situation according to the degree of imbalance. When the imbalance level h remains within 8%, it is often due to short-term parameter fluctuations or occasional measurement errors, rather than equipment failure or process inefficiency. Trigger an alert without interrupting production, and mark an "X" on the real-time production status model interface. i An anomaly is detected, but production is not interrupted. The sampling period for dynamic parameters is shortened from 20 seconds to 10 seconds. The pass rate is calculated. If ten consecutive samples show imbalanced data, imbalance keywords are read, and solutions in the solution library are matched and executed. When the imbalance level h remains above 8%, imbalance keywords are immediately read, and solutions in the solution library are matched and executed. If no perfect match is found, an approximate solution is provided, and the solution is manually determined. Imbalanced data after a repair instruction is given is marked as data of concern for continuous monitoring. For all sub-regions that have given repair instructions, the product pass rate after completing the repair instruction is calculated. If the product pass rate does not increase, the repair instruction is marked and manually judged.

[0027] The system determines the cause of imbalance based on imbalance keywords. If the imbalance is determined to be caused by the operating environment, the system generates environmental control instructions to eliminate interference. If the imbalance is determined to be caused by factors of the production machine itself, the system automatically generates an operating parameter adjustment plan or outputs a component replacement instruction. After the repair instruction is executed, the system marks the imbalance data of the corresponding module as data of concern, includes it in a special monitoring list, and continuously tracks its changing trend to ensure that the imbalance problem is completely resolved and recurrence is avoided.

[0028] The comparison result detection module performs secondary data collection based on the repaired data of concern, establishes a new real-time production status model, and compares it with the ideal digital twin model. If the difference range of the data of concern conforms to the theoretical difference, the repair is completed, and the instruction is recorded and archived in the solution library. If it does not conform to the theoretical difference, the numbers are output to the user for manual repair. The data after manual repair is automatically converted into new data of concern. The above process is repeated until the difference conforms to the theoretical range, and all manual repair instructions are archived in the solution library.

[0029] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A digital twin simulation and optimization system for product packaging production lines, characterized in that, Includes a sub-region functional division module: used to divide the entire production line into several sub-region functional ends according to the process flow of the product packaging production line; Parameter acquisition module: used to acquire static parameters required to build an ideal digital twin model for any sub-region functional terminal, mark the parameters corresponding to the static parameters in the real-time production process as dynamic parameters, and transmit and store the static parameter information and dynamic parameters to the system data storage unit; Model building module: Constructs a digital twin ideal model of the sub-region functional terminal based on static parameter information, and constructs a real-time production status model of the sub-region functional terminal based on dynamic parameter information; Real-time intelligent comparison module: Based on the ideal operating range of all parameters of the digital twin ideal model, the parameters of the real-time production status model that do not fall within the ideal operating range are recorded as imbalance data; The comparison result output module matches imbalanced keywords to imbalanced data, outputs corresponding repair instructions based on the imbalanced keywords, and completes the repair. The data for which repair instructions are given is recorded as data in the state of concern, and the data in the state of concern is continuously monitored. Comparison Result Detection Module: Based on the repaired data of concern, secondary data collection is performed to establish a new real-time production status model and compare it with the ideal model of digital twin. If the difference range of the data of concern conforms to the theoretical difference, the repair is completed. If it does not conform to the theoretical difference, the numbers are output to the user terminal for manual repair.

2. The digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The static parameters include mold wear level, sub-region functional end temperature, and sub-region functional end product flow coordination value.

3. The digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The dynamic parameters are obtained by considering the degree of mold wear, the temperature of the sub-region functional end, and the deviation of the product flow coordination value of the sub-region functional end from the static parameter value after being affected by external factors during real-time production.

4. The digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The ideal model for the digital twin is established as follows: S1: Digital Twin Model Mold Wear Calibration: Select a mold that meets production standards, use a contact roughness meter, select a probe suitable for the mold material hardness, and read the surface roughness, maximum surface height, and minimum surface height of the new production mold based on the measurement results. Read the mold surface hardness from the equipment manual and calculate the mold wear degree according to the formula, using the current production mold wear degree as a static parameter. The calculation method is as follows: Where Ra is the surface roughness, in μm or nm, and must be consistent with the hardness unit; rp is the maximum surface height, in μm or nm, a positive value calculated from the average baseline; rv is the minimum surface height, in μm or nm, a positive value calculated from the average baseline, representing the depth; H is the surface hardness, in MPa or HV, and must be consistent with the length unit. S2: Digital Twin Ideal Model Sub-region Functional End Temperature: Based on the process flow of the product packaging production line, the optimal temperature is set for each sub-region functional end based on the operating temperature of the production equipment, and the optimal temperature at this time is used as the static parameter; S3: Digital Twin Model Sub-region Functional Terminal Product Flow Coordination Value: Establish a stable and controllable product flow, ensuring that the output of the previous sub-region functional terminal is completely equivalent to the processing volume of the next sub-region functional terminal. Based on the current operating speed, record the maximum output, actual output, maximum processing volume, actual processing volume, and maximum buffer capacity of the previous sub-region functional terminal to calculate the production efficiency. Record this production efficiency as a static parameter. The calculation method is to quantify it according to the sub-region functional terminal product flow coordination value formula. The calculation formula is C act C max These represent the actual output and maximum output of the previous sub-region's functional end, respectively, Q. act Q max These are the actual output and maximum output of the next sub-region's functional end, respectively, and β is the ratio of the buffer inventory to the maximum buffer capacity.

5. A digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The real-time production status model is established using the same method as the ideal digital twin model. The ideal digital twin model uses static parameters, while the real-time production status model uses dynamic parameters.

6. A digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The offset value of the monitoring equipment is periodically calibrated, and the drift value of the monitoring equipment is used to correct the dynamic data. The formula for correcting is D: Represents the percentage of natural performance degradation per day; P t0 : This refers to the equipment's operating data immediately after maintenance; P t1 : No-load operation data of the equipment after an interval Δt; Δt: time interval between two no-load operations; After obtaining the offset value D of the monitoring equipment, the dynamic data is corrected using the offset value D of the monitoring equipment. The correction formula is: δ 正 : is the correction value after calibration; t is the number of days from the calibration date; δ is the measurement value of the equipment on day t.

7. A digital twin simulation and optimization system for product packaging production lines according to claim 1, characterized in that, The imbalance data refers to dynamic parameters that do not fall within the ideal operating range. The ideal operating range is set using static parameters as the core, and is calculated as follows: All product pass rates are sorted from best to worst, and the static parameters X1, X2, X3...X corresponding to the top n product pass rates are taken. n Calculate the sample mean Calculate the sample standard deviation Then the ideal operating range of the dynamic parameter X is [ ]; where n: the first n historical data; : The average value of the static parameters corresponding to the first n pass rates; Z: The Z value corresponding to the confidence level; Compare the corrected dynamic parameters with the ideal operating range one by one. If the dynamic parameter value falls within the ideal operating range, it is marked as normal and not included in the imbalance data; if the dynamic parameter value does not fall within the ideal operating range, it is marked as imbalance data.

8. A digital twin simulation and optimization system for product packaging production lines according to claim 7, characterized in that, Lower limit of the prediction interval Let it be L i Predict the upper limit of the interval Let it be U i， When the dynamic parameter X of the monitoring equipment is calibrated i ⊂[L i U i When the value of the dynamic parameter S falls within the ideal operating range, it is considered acceptable; if the value of the dynamic parameter S does not fall within the ideal operating range, it is marked as unbalanced data. The degree of imbalance h of the extreme value within the ideal operating range is then calculated for the unbalanced data S. Data with an imbalance of h less than 8% is marked as slightly imbalanced, and data with an imbalance of h greater than 8% is marked as severely imbalanced. Imbalance keywords are compiled based on the data attributes, sub-region functional ends, and imbalance data values.

9. A digital twin simulation and optimization system for product packaging production lines according to claim 8, characterized in that, For sub-regional functional terminals with slightly unbalanced data, shorten the dynamic parameter sampling period. If the data falls within the ideal operating range after shortening the sampling period, no further processing is required. If mildly imbalanced data occurs ten times consecutively or severely imbalanced data occurs, the imbalance keyword is read, and a repair instruction is given based on the processing solution in the solution library. The imbalanced data after the repair instruction is given is marked as data of concern and continuously monitored.

Images