Real-time regulation method and system for intelligent wrapping paper container production process data

Abstract

The present application relates to the field of packaging production, in particular to a real-time regulation method and system for intelligent packaging paper container production process data, comprising the following steps: offline dividing production line function units and identifying key components, calibrating the reference performance parameters of each key component, establishing a process parameter reference library for different product specifications, initializing the running time and yield counter; collecting the running data and product quality data of each key component, sequentially performing outlier rejection, moving average filtering and data normalization processing, and then storing; extracting feature parameters related to the degradation mechanism, calculating the single parameter degradation degree, weighting to obtain the key component degradation index and the overall equipment degradation index, and dividing the equipment running state level; calculating the process parameter adjustment amount according to the degradation index and the preset linear compensation relationship, updating and executing the process parameters after limiting the amplitude, and verifying the compensation effect through quality detection.

Description

Technical Field

[0001] This invention belongs to the field of packaging production, specifically relating to a method and system for real-time control of data in the production process of intelligent packaging paper containers. Background Technology

[0002] Paper containers are widely used packaging materials in the food, beverage, and daily chemical industries, and their production process is characterized by high speed, continuous operation, and automation. Modern paper container production lines can operate at speeds of 200 to 500 products per minute. The entire production line consists of multiple units, including raw paper conveying, printing, die-cutting, forming, box gluing, and inspection. These units work closely together, and fluctuations in the performance of equipment in any stage can directly affect the quality of the final product.

[0003] Paper container production equipment inevitably experiences performance degradation during long-term operation. This degradation is caused by a combination of factors, including mechanical wear, material fatigue, media blockage, and aging of electrical components. Common equipment performance degradation phenomena include: uneven printing pressure distribution and blurred printed patterns due to wear on the printing cylinder surface; dulling of the die-cutting blade leading to incomplete die-cutting and burrs; blockage of the glue gun nozzle resulting in reduced glue output and uneven glue lines; wear of the servo motor transmission mechanism leading to decreased positioning accuracy and increased registration errors; and aging of the heating element leading to insufficient drying temperature and incomplete glue curing.

[0004] These degradation processes have two significant characteristics: first, they are slow, meaning that equipment performance does not suddenly decline, but gradually deteriorates with increasing operating time, and the entire process may last for weeks or even months; second, they are insidious, meaning that in the early stages of degradation, the equipment's operating status does not show any obvious abnormalities, and conventional inspection and testing methods are difficult to detect. Only when the degradation accumulates to a certain extent and causes obvious defects in product quality will it be noticed.

[0005] The current industry standard for equipment maintenance is periodic maintenance, which involves comprehensive overhauling and replacing vulnerable parts according to pre-set time intervals or production output. This model has two fundamental drawbacks: First, over-maintenance leads to waste. Prematurely replacing parts that are still in good working order not only increases maintenance costs and spare parts consumption but also causes unnecessary downtime, reducing the effective utilization rate of the equipment. Second, untimely maintenance leads to quality fluctuations. Since the rate of equipment degradation is affected by various factors such as raw material quality, production load, and environmental conditions, fixed maintenance cycles cannot adapt to actual changes in equipment condition. Often, equipment performance has already significantly deteriorated between maintenance intervals, resulting in a large number of scrap products.

[0006] A more critical issue is that even with a regular maintenance model, the performance degradation of equipment between maintenance sessions cannot be effectively compensated for. The same process parameters may produce qualified products when the equipment is brand new, but as equipment performance gradually degrades, these parameters become ineffective, leading to a slow decline in product quality. Traditional production management methods rely solely on operators' experience to manually adjust process parameters. This approach suffers from high subjectivity, untimely adjustments, and low precision, failing to guarantee long-term product quality stability.

[0007] While some equipment condition monitoring systems exist in the current technology, most of these systems can only provide threshold alarms for a single parameter. That is, they issue an alarm when a parameter exceeds a preset threshold, alerting operators to take action. This approach can only provide warnings when equipment performance has already severely degraded and is about to lead to a quality incident; it cannot intervene in the early stages of degradation, nor can it automatically adjust process parameters to compensate for the decline in equipment performance. Furthermore, existing technologies cannot accurately quantify the degree of equipment degradation, nor can they establish a correlation between equipment degradation and process parameters, thus failing to achieve adaptive adjustment of process parameters. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for real-time control of intelligent packaging paper container production process data, so as to solve the problems mentioned in the background art.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A method for real-time data control during the intelligent packaging paper container production process includes the following steps: S1. Offline division of production line functional units and identification of key components, calibration of the benchmark performance parameters of each key component, establishment of a benchmark library of process parameters for different product specifications, and initialization of running time and output counters. S2. Collect operational data and product quality data of key components online, and store the data after performing outlier removal, moving average filtering and data normalization in sequence. S3. Extract the feature parameters related to the degradation mechanism, calculate the degradation degree of a single parameter, and obtain the degradation index of key components and the overall degradation index of the equipment by weighting, and classify the equipment operating status level. S4. Calculate the process parameter adjustment amount based on the degradation index and the preset linear compensation relationship, update and execute the process parameters after limiting the amplitude, and verify the compensation effect through quality inspection. S5. Regularly analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, recalibrate the benchmarks and update the benchmark library.

[0010] Furthermore, in step S1, the production line functional units include a raw paper conveying unit, a printing unit, a die-cutting unit, a forming unit, a box gluing unit, and a quality inspection unit; the key components include a tension roller, a servo motor, a web-correcting sensor, a printing roller, an impression roller, an ink roller, a drying heating tube, a die-cutting plate, a forming mold, a glue gun, a vision inspection camera, and a weighing sensor.

[0011] Furthermore, in step S1, the benchmark performance calibration of the key components includes benchmark calibration of the printing roller, benchmark calibration of the die-cutting blade, benchmark calibration of the glue gun, and benchmark calibration of the servo motor; all measurements are repeated three times, and the arithmetic mean is taken as the benchmark value.

[0012] Furthermore, in step S4, the linear compensation relationship includes compensation for printing roller wear, die-cutting blade dulling, glue gun clogging, servo motor accuracy reduction, and drying heating tube aging; when multiple components affect the same process parameter, the adjustment amounts are algebraically summed.

[0013] Furthermore, in step S5, the least squares method is used to perform linear regression analysis on the degradation index data of the past 30 days. The formula for calculating the remaining service life is: remaining service life = (1.0 - current degradation index) / slope of degradation trend line; a maintenance reminder is issued when the remaining service life is ≤ 7 days.

[0014] A real-time data control system for the intelligent packaging paper container production process includes: The benchmark calibration module is used to divide the production line into functional units offline and identify key components, calibrate the benchmark performance parameters of each key component, establish a process parameter benchmark library and initialize counters; The data acquisition and preprocessing module is used to collect production process data online, and then perform outlier removal, moving average filtering and data normalization before storing the data. The degradation assessment module is used to extract characteristic parameters related to the degradation mechanism, calculate the degradation degree of a single parameter, the degradation index of key components and the overall degradation index of the equipment, and classify the equipment operating status level. The process compensation module is used to calculate the adjustment amount of process parameters based on the degradation index and the preset linear compensation relationship, update and execute the process parameters after limiting the range, and verify the compensation effect through quality inspection. The maintenance prediction module is used to periodically analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, the baseline is updated.

[0015] Furthermore, the benchmark calibration module includes a unit partitioning submodule, a benchmark calibration submodule, a benchmark library establishment submodule, and a counter initialization submodule; the benchmark calibration submodule is used to perform benchmark performance calibration on the printing roller, die-cutting blade, glue gun, and servo motor.

[0016] Furthermore, the data acquisition and preprocessing module includes a sensor array, a data transmission submodule, a preprocessing submodule, and a data storage submodule; the sensor array includes a pressure sensor, a temperature sensor, a displacement sensor, a current sensor, a vision inspection system, and a quality inspection sensor.

[0017] Furthermore, the degradation assessment module includes a feature extraction submodule, a single-parameter degradation calculation submodule, a component degradation index calculation submodule, and an overall status assessment submodule; the overall status assessment submodule is used to classify the equipment operating status into four levels: normal, slight degradation, moderate degradation, and severe degradation.

[0018] This application also discloses an electronic device, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the above-described method for real-time control of intelligent packaging paper container production process data of the present invention. Beneficial effects

[0019] First, this invention enables real-time monitoring and quantitative assessment of equipment performance degradation. By deploying high-precision sensors in key equipment components, it collects equipment operation data in real time and extracts characteristic parameters directly related to the degradation mechanism based on physical principles. This allows for the calculation of a degradation index that accurately reflects the degree of component degradation, enabling the timely detection of latent performance declines in the early stages of degradation. This overcomes the limitations of traditional methods, which only detect degradation when obvious product defects appear, effectively preventing the generation of large quantities of scrap. Second, this invention establishes a physical mapping relationship between equipment performance degradation and process parameters. It can automatically adjust process parameters according to the degree of equipment degradation, compensating for the impact of equipment performance degradation on product quality in real time. This compensation is a linear compensation based on physical principles, requiring no manual intervention. It is timely and highly accurate, ensuring stable product quality throughout the equipment's entire lifecycle and significantly reducing the scrap rate. Third, this invention enables precise prediction of equipment maintenance timing. By performing linear regression analysis on component degradation trends, it can accurately predict the remaining service life of components and arrange maintenance plans based on the actual degradation status, replacing the traditional periodic maintenance model. This predictive maintenance model avoids both the waste of spare parts and unnecessary downtime caused by over-maintenance, and the equipment failures and quality accidents caused by untimely maintenance, significantly reducing maintenance costs and improving the effective utilization rate of equipment. Fourth, the entire technical solution of this invention is based on physical models and statistical process control methods, without relying on any complex machine learning algorithms, and has the advantages of high reliability, ease of implementation, and simple maintenance. All parameters and coefficients are determined through actual experiments, have clear physical meanings, are easy for operators to understand and master, and lower the system's usage threshold and maintenance difficulty. Fifth, this invention has good versatility and scalability. By adjusting the identification of key components, the extraction of feature parameters, and the establishment of compensation relationships, this method can be applied to paper container production equipment of different types and specifications, and can also be extended to other similar continuous production equipment, such as plastic packaging container production equipment and metal packaging container production equipment, etc., with broad application prospects. Attached Figure Description

[0020] Figure 1 This is an overall flowchart of the intelligent packaging paper container production process data real-time control method of the present invention. Figure 2 This is a schematic diagram of the process for calibrating the equipment reference state and establishing the process parameter reference library in an embodiment of the present invention; Figure 3 This is a schematic diagram of the real-time data acquisition and preprocessing process in the production process according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the real-time assessment of equipment performance degradation and the calculation of degradation index in an embodiment of the present invention; Figure 5This is a schematic diagram of the adaptive compensation calculation and execution process for process parameters in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] This invention relates to a method for real-time data control in the intelligent packaging paper container production process, such as... Figure 1 As shown, the steps include: S1. Offline division of production line functional units and identification of key components, calibration of the benchmark performance parameters of each key component, establishment of a benchmark library of process parameters for different product specifications, and initialization of running time and output counters. S2. Collect operational data and product quality data of key components online, and store the data after performing outlier removal, moving average filtering and data normalization in sequence. S3. Extract the feature parameters related to the degradation mechanism, calculate the degradation degree of a single parameter, and obtain the degradation index of key components and the overall degradation index of the equipment by weighting, and classify the equipment operating status level. S4. Calculate the process parameter adjustment amount based on the degradation index and the preset linear compensation relationship, update and execute the process parameters after limiting the amplitude, and verify the compensation effect through quality inspection. S5. Regularly analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, recalibrate the benchmarks and update the benchmark library.

[0023] The specific steps are as follows: Step 1: Calibrate equipment reference status and establish a process parameter reference library, such as... Figure 2 As shown, this step is an offline execution step. It must be performed after the initial installation and commissioning of the equipment, after each major overhaul, and after each replacement of vulnerable parts. It is used to determine the baseline parameters of the equipment under optimal performance conditions, providing a reference standard for subsequent degradation monitoring and process compensation. The timing of this step, performed before the equipment is officially put into production, forms the foundation of the entire method.

[0024] The production line is divided into units and key components are identified. First, the entire paper container production line is divided into several independent functional units, including the raw paper conveying unit, printing unit, die-cutting unit, forming unit, box gluing unit, and quality inspection unit. For each functional unit, key components that directly affect product quality are identified, specifically including: Paper conveying unit: tension roller, servo motor, web guiding sensor; Printing unit: printing cylinder, impression cylinder, ink roller, drying heating tube, overprinting servo motor; Die-cutting unit: die-cutting blade, die-cutting roller, pressure adjustment mechanism, positioning pin; Forming unit: forming mold, folding mechanism, conveyor chain; Gluing unit: glue gun, glue pump, heating plate, pressing roller; Quality inspection unit: visual inspection camera, weighing sensor, dimensional measurement sensor; The benchmark performance calibration of critical components involves using standard measurement tools and methods to measure various performance parameters of each identified critical component under both no-load and load operating conditions to determine benchmark values. All measurements must be repeated three times, and the arithmetic mean of the three measurements is taken as the final benchmark value. Specific calibration details are as follows: Printing cylinder reference calibration: Use a dial indicator to measure the radial runout and axial movement of the printing cylinder and record the reference values; use a standard pressure sensor to measure the printing pressure between the printing cylinder and the impression cylinder, and measure at different pressure adjustment levels to establish a correspondence table between the pressure adjustment level and the actual printing pressure; use a standard test plate to print, measure the printing density and registration accuracy, and record the reference values.

[0025] Die-cutting blade reference calibration: Use a standard hardness block to measure the blade hardness of the die-cutting blade and record the reference value; use a pressure sensor to measure the die-cutting pressure between the die-cutting cylinder and the anvil roller, and measure at different pressure adjustment levels to establish a correspondence table between the pressure adjustment level and the actual die-cutting pressure; use standard base paper to conduct die-cutting tests, measure the die-cutting depth and burr length, and record the reference value.

[0026] Calibration of glue gun: Use a precision electronic balance to measure the glue output of the glue gun at different opening times and establish a correspondence table between glue gun opening time and glue output; use a vision measurement system to measure the width and continuity of the glue line and record the reference values; measure the surface temperature of the glue gun heating plate at different temperature settings and establish a correspondence table between the temperature setting and the actual surface temperature.

[0027] Servo motor reference calibration: Use a laser interferometer to measure the positioning accuracy and repeatability of the servo motor and record the reference values; measure the current and torque of the servo motor at different speeds and establish a correspondence table between speed and current and torque.

[0028] Other key component benchmark calibration: Using the same method as above, benchmark performance calibration was performed on other key components such as tension roller, drying heating tube, forming mold, and pressing roller, and all benchmark parameters were recorded.

[0029] After establishing a process parameter benchmark library and calibrating the benchmark performance of all key components, trial production tests were conducted for each paper container product specification. During the trial production, the process parameters of each unit were gradually adjusted until all produced products met the quality standards. All process parameters at this point were recorded as the benchmark values ​​for the process parameters of that product specification and stored in the process parameter benchmark library.

[0030] The process parameter benchmark library includes at least the following parameters: raw paper force, printing pressure, printing speed, drying temperature, die-cutting pressure, die-cutting speed, forming temperature, gluing temperature, glue gun opening time, and pressing pressure. Each product specification corresponds to an independent set of process parameter benchmark values, and the process parameter benchmark values ​​for different product specifications are independent of each other and do not affect each other.

[0031] Initialize the equipment runtime and output counters. Initialize the total equipment runtime counter and the individual runtime counters for each key component. Simultaneously, initialize the total equipment output counter and the individual output counters for each product specification. All counter values ​​must be accurately recorded and backed up regularly to prevent data loss.

[0032] Step 2: Real-time data acquisition and preprocessing during the production process, such as... Figure 3 As shown, this step is an online real-time execution step, continuously executed after the equipment is officially put into production. It is used to collect operational data and product quality data of key components during production, and to preprocess the collected data to remove noise and outliers, providing a reliable data source for subsequent equipment degradation assessment. The execution sequence of this step is synchronized with the production process, and the sampling frequency is set according to the characteristics of different parameters to ensure accurate reflection of the equipment's operating status. Data acquisition point layout and sampling frequency settings: Based on the key components identified in step 1, corresponding sensors are deployed on the equipment to collect operational data of each key component. All sensors must be calibrated to ensure that the measurement accuracy meets requirements. The specific data acquisition points and sampling frequency settings are as follows: Pressure sensors: These are placed on printing rollers, die-cutting rollers, pressing rollers, etc., to collect parameters such as printing pressure, die-cutting pressure, and pressing pressure. The sampling frequency is set to 100Hz.

[0033] Temperature sensor: Arranged in the drying heating tube, glue gun heating plate, molding mold, etc., to collect parameters such as drying temperature, glue box temperature, molding temperature, etc., with the sampling frequency set to 1Hz.

[0034] Displacement sensor: Located in servo motors, tension adjustment mechanisms, etc., it is used to collect parameters such as positioning error and tension fluctuation. The sampling frequency is set to 100Hz.

[0035] Current sensor: Arranged in the power supply circuit of each motor to collect motor current parameters, with the sampling frequency set to 10Hz.

[0036] Visual inspection system: Located after the printing unit, die-cutting unit, and box gluing unit, it is used to collect image data such as printing quality, die-cutting quality, and box gluing quality. The sampling frequency is synchronized with the production line speed, that is, an image is collected once for each product.

[0037] Quality inspection sensors: placed at the end of the production line to collect parameters such as product size, weight, and sealing performance. The sampling frequency is synchronized with the production line speed.

[0038] Data is acquired and transmitted in real time. All data collected by the sensors is transmitted to the central controller via industrial Ethernet. The central controller timestamps the acquired data to ensure that all data has a unified time reference. The timestamp accuracy must be at the millisecond level to guarantee time synchronization between data from different sensors.

[0039] Data preprocessing involves the central controller preprocessing the collected raw data to remove noise and outliers, thereby improving data reliability. The preprocessing process includes the following three steps: Outlier removal: The 3σ criterion is used to remove outliers from the original data. For each parameter, its mean and standard deviation over the most recent minute are calculated. Data exceeding the mean ± 3 times the standard deviation are identified as outliers and removed.

[0040] Moving average filtering: This method applies a moving average filter to the data after outlier removal, with a sliding window size of 10 sampling points. The moving average filter removes high-frequency noise from the data while preserving its low-frequency trend.

[0041] Data normalization: Converting preprocessed data into dimensionless relative values. The conversion formula is: Relative value = Actual measured value / Reference value. Data normalization eliminates dimensional differences between different parameters, facilitating subsequent comparison and analysis.

[0042] Data storage involves storing the preprocessed data in chronological order into an industrial database, with a data storage period of at least one year. The stored data includes raw measurement data, preprocessed data, timestamps, equipment operating status, product specifications, and other information. All stored data must be backed up regularly to prevent data loss.

[0043] Step 3: Real-time assessment of equipment performance degradation and calculation of degradation index, such as... Figure 4As shown, this step is an online real-time execution step, performed immediately after data preprocessing. It is used to assess the performance degradation degree of each key component based on the preprocessed operational data and calculate the degradation index for each key component. This step follows immediately after step 2, executing once per second to ensure timely reflection of changes in equipment performance.

[0044] Key component degradation feature parameter extraction: For each key component, feature parameters reflecting its performance degradation degree are extracted from the preprocessed data. The selection of feature parameters must be based on physical principles and directly related to the component's degradation mechanism. The specific feature parameter extraction is as follows: Degradation characteristics of printing cylinders: average printing pressure, standard deviation of printing pressure, average registration error, and average printing density.

[0045] Die-cutting blade degradation characteristic parameters: average die-cutting pressure, standard deviation of die-cutting pressure, average die-cutting burr length, and average die-cutting depth.

[0046] Degradation characteristics of glue guns: average glue output, standard deviation of glue output, average glue line width, and standard deviation of glue line width.

[0047] Servo motor degradation characteristic parameters: average positioning error, average repeatability error, and average motor current.

[0048] Degradation characteristic parameters of other key components: Following the same principles as above, degradation characteristic parameters of other key components such as tension roller, drying heating tube, forming mold, and pressing roller are extracted.

[0049] For single-parameter degradation degree calculation, for each extracted feature parameter, its current value is compared with the baseline value determined in step 1 to calculate the degradation degree of that parameter. The formula for calculating the degradation degree is: Degradation level = |Current value - Reference value| / Allowable deviation The allowable deviation value refers to the maximum allowable deviation of the parameter without affecting product quality. This value is determined by product quality standards and process requirements, and is determined simultaneously with the reference value in step 1.

[0050] When the degradation level is less than or equal to 1, it means that the deviation of the parameter is within the allowable range and the component performance is normal; when the degradation level is greater than 1, it means that the deviation of the parameter exceeds the allowable range and the component performance has become abnormal.

[0051] The degradation index of critical components is calculated by weighting and summing the degradation levels of all characteristic parameters for each critical component. The weighting coefficients are determined based on the influence of each characteristic parameter on the component's performance, and the sum of all weighting coefficients equals 1. The weighting coefficients are determined experimentally in step 1 and remain unchanged once determined.

[0052] The formula for calculating the degradation index is: Degradation index = weighted sum of the degree of degradation of the characteristic parameters and the weighting coefficients; The degradation index ranges from 0 to positive infinity. A degradation index of 0 indicates that the component is in brand new baseline condition; a degradation index between 0 and 1 indicates that the component's performance has slightly degraded, but is still within the normal range; a degradation index equal to 1 indicates that the component's performance has reached the maximum allowable degradation level and requires maintenance; a degradation index greater than 1 indicates that the component's performance has severely degraded and must be shut down immediately for maintenance.

[0053] The overall equipment degradation status assessment involves weighted summation of the degradation indices of all key components to obtain the overall equipment degradation index. The weighting coefficients are determined based on the impact of each key component on product quality, and the sum of all weighting coefficients equals 1. Based on the magnitude of the overall equipment degradation index, the equipment's operating status is divided into four levels: Normal condition: The overall degradation index is less than 0.3, the equipment performance is good, and no adjustments are required.

[0054] Slight degradation status: The overall degradation index is between 0.3 and 0.7, indicating a slight degradation in equipment performance, requiring process parameter compensation.

[0055] Moderate degradation status: The overall degradation index is between 0.7 and 1.0, and the equipment performance has deteriorated significantly. In addition to compensating for process parameters, maintenance needs to be arranged in the near future.

[0056] Severe degradation status: The overall degradation index is greater than or equal to 1.0, the equipment performance is severely degraded, and it must be shut down for maintenance immediately.

[0057] Step 4: Adaptive compensation calculation and execution of process parameters, such as... Figure 5 As shown, this step is an online real-time execution step, executed immediately after the equipment degradation index is calculated. It is used to calculate the process parameter values ​​that need adjustment based on the degradation index of each key component and send them to the equipment controller for execution, compensating for the impact of equipment performance degradation on product quality. This step follows immediately after step 3, executing once per second to ensure that process parameters can be adjusted promptly in response to changes in equipment performance.

[0058] The process parameter compensation relationship is established by establishing a linear compensation relationship between the degradation index of each key component and the corresponding process parameter adjustment during the benchmark calibration process in step 1. This compensation relationship is based on physical principles and reflects the intrinsic connection between component performance degradation and process parameter adjustment. The specific compensation relationship is as follows: Printing cylinder wear compensation: Printing cylinder wear can lead to insufficient printing pressure and increased registration errors, thus requiring increased printing pressure and adjustment of registration position. Printing pressure adjustment amount = printing cylinder degradation index × printing pressure compensation coefficient; Registration position adjustment amount = printing cylinder degradation index × registration position compensation coefficient.

[0059] Die-cutting blade dulling compensation: Die-cutting blade dulling can lead to insufficient die-cutting pressure and insufficient die-cutting depth, therefore, it is necessary to increase the die-cutting pressure. Die-cutting pressure adjustment amount = die-cutting blade degradation index × die-cutting pressure compensation coefficient.

[0060] Glue gun clogging compensation: Glue gun clogging leads to reduced glue output and a narrower glue line, thus requiring an increase in the glue gun's operating time. Glue gun operating time adjustment amount = glue gun degradation index × glue gun operating time compensation coefficient.

[0061] Servo motor accuracy degradation compensation: A decrease in servo motor accuracy will lead to an increase in positioning error, therefore it is necessary to adjust the positioning offset of the servo motor. Positioning offset adjustment amount = servo motor degradation index × positioning offset compensation coefficient.

[0062] Drying heating element aging compensation: Aging of the drying heating element can lead to insufficient drying temperature, therefore the drying temperature setting needs to be increased. Drying temperature adjustment amount = drying heating element degradation index × drying temperature compensation coefficient.

[0063] Degradation compensation for other components: Following the same principles as above, establish a compensation relationship between the degradation index of other key components such as tension rollers, forming dies, and pressing rollers and the corresponding process parameter adjustments.

[0064] All the compensation coefficients mentioned above were determined experimentally during the benchmark calibration process in step 1 and remain unchanged once determined. The sign of the compensation coefficient indicates the direction of adjustment; a positive value indicates an increase in the parameter value, and a negative value indicates a decrease in the parameter value.

[0065] The adjustment amount for process parameters is calculated based on the degradation index of each key component obtained in step 3 and the compensation relationship established in step 4.1. When the degradation of multiple components simultaneously affects the same process parameter, the adjustment amounts corresponding to each component are algebraically summed to obtain the total adjustment amount for that process parameter.

[0066] To prevent overcompensation from causing new quality problems, upper and lower limits are set for the adjustment of each process parameter. These limits are determined based on process requirements and equipment performance, and are established simultaneously with the compensation coefficient in step 1. When the calculated adjustment exceeds the upper limit, the upper limit value is taken as the final adjustment; when the calculated adjustment is below the lower limit, the lower limit value is taken as the final adjustment.

[0067] The process parameter update and execution involves adding the calculated process parameter adjustment amount to the baseline process parameter value determined in step 1 to obtain the updated process parameter value. The central controller sends the updated process parameter value to the equipment controllers of each unit in real time, and the equipment controllers immediately execute the new process parameters.

[0068] The effectiveness of the compensation is verified by using a quality inspection system at the end of the production line to monitor the product quality in real time after the process parameters are adjusted. If the quality of 100 consecutive products meets the standards, the compensation is considered effective, and the current process parameters should be maintained. If any products fail to meet the standards, the compensation may be insufficient or excessive, requiring a recalculation of the adjustment amount. During recalculation, the adjustment step size is halved to gradually approach the optimal compensation value.

[0069] Step 5: Equipment Maintenance Timing Prediction and Post-Maintenance Baseline Update. This step is executed offline, periodically during equipment operation, once daily. It is used to predict the time when key components reach their critical maintenance state based on their degradation trends, and to schedule maintenance accordingly. Simultaneously, after equipment maintenance is completed, baseline calibration is performed again, and the process parameter baseline library is updated. The execution sequence of this step is independent of steps 2 to 4 and does not affect the normal operation of the production process.

[0070] Component degradation trend analysis involves extracting degradation index data for each key component over the past 30 days from the industrial database after each day's production. A least squares method is then used to perform linear regression analysis on the degradation index data to obtain a degradation trend line for each component. The slope of the degradation trend line represents the degradation rate of the component; a steeper slope indicates faster degradation.

[0071] Maintenance timing prediction: Based on the degradation trend line of each component, predict when its degradation index will reach 1.0 (the maintenance threshold). The prediction formula is: Remaining useful life = (1.0 - current degradation index) / slope of degradation trend line Convert the predicted remaining service life into specific dates, which will be the recommended maintenance dates for that component. Based on the recommended maintenance dates for all components, develop a maintenance plan for the equipment, prioritizing maintenance for components with shorter remaining service lives. Maintenance should be scheduled during production downtime to avoid disrupting normal operations.

[0072] Maintenance reminders and records: When the remaining service life of a component is less than or equal to 7 days, the system automatically issues a maintenance reminder, notifying maintenance personnel to prepare spare parts and tools. When the degradation index of a component reaches 1.0, the system automatically issues an emergency maintenance reminder, requiring immediate shutdown for maintenance.

[0073] After all maintenance work is completed, detailed records must be kept of the maintenance content, the models of the replaced parts, the maintenance time, the maintenance personnel, and other information, and these records must be stored in the equipment maintenance file.

[0074] After maintenance, the baseline must be updated. Once equipment maintenance is complete, the replaced components must be recalibrated according to the requirements of step 1. If the replaced component affects process parameters, a trial production test must be conducted again, and the corresponding process parameter baseline values ​​in the process parameter baseline library must be updated. Simultaneously, the running time counter for that component must be reset to zero and restarted.

[0075] This invention also provides a real-time data control system for the intelligent packaging paper container production process, used to implement the above method. The system includes: The benchmark calibration module is used to perform offline equipment benchmark state calibration, establish a process parameter benchmark library, and initialize counters; The data acquisition and preprocessing module is used to collect production process data online, perform outlier removal, moving average filtering, and data normalization before storing the data. The degradation assessment module is used to extract degradation characteristic parameters, calculate the degradation degree of single parameters, the degradation index of key components and the overall degradation index of equipment, and classify the equipment operating status level; The process compensation module is used to calculate the adjustment amount of process parameters based on the degradation index and preset compensation relationship, update and execute the process parameters after limiting the range, and verify the compensation effect. The maintenance prediction module is used to periodically analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, the baseline is updated.

[0076] Furthermore, the benchmark calibration module includes a unit partitioning submodule, a benchmark calibration submodule, a benchmark library establishment submodule, and a counter initialization submodule; the benchmark calibration submodule is used to perform benchmark performance calibration on the printing roller, die-cutting blade, glue gun, and servo motor.

[0077] Furthermore, the data acquisition and preprocessing module includes a sensor array, a data transmission submodule, a preprocessing submodule, and a data storage submodule; the sensor array includes a pressure sensor, a temperature sensor, a displacement sensor, a current sensor, a vision inspection system, and a quality inspection sensor.

[0078] Furthermore, the degradation assessment module includes a feature extraction submodule, a single-parameter degradation calculation submodule, a component degradation index calculation submodule, and an overall status assessment submodule; the overall status assessment submodule is used to classify the equipment operating status into four levels: normal, slight degradation, moderate degradation, and severe degradation.

[0079] The following detailed description of the specific implementation of the present invention is based on a typical paper cup production line. The paper cup production line in this embodiment is designed to produce 300 paper cups per minute and mainly consists of a raw paper conveying unit, a six-color printing unit, a die-cutting unit, a paper cup forming unit, a bottom-gluing unit, an online detection unit, and a central controller. The main product specifications of the production line are 250ml and 500ml paper cups.

[0080] Real-time control methods for intelligent packaging paper container production process data include: Equipment baseline calibration and process parameter baseline library establishment: After the initial installation and commissioning of the production line, equipment baseline calibration and process parameter baseline library establishment are carried out.

[0081] First, the production line was divided into units and key components were identified. The production line was divided into six units: paper feeding, printing, die-cutting, forming, gluing, and inspection. The identified key components included: tension rollers, paper feeding servo motors, and web guiding sensors in the paper feeding unit; six printing rollers, six impression rollers, six ink rollers, three sets of drying heating tubes, and six registration servo motors in the printing unit; die-cutting blades, die-cutting rollers, pressure adjustment mechanisms, and positioning pins in the die-cutting unit; forming molds, folding mechanisms, and conveyor chains in the forming unit; four glue guns, glue pumps, heating plates, and pressure rollers in the gluing unit; and six vision inspection cameras, weighing sensors, and dimensional measurement sensors in the inspection unit.

[0082] Next, the baseline performance of key components was calibrated. Taking the printing cylinders as an example, a dial indicator with an accuracy of 0.001 mm was used to measure the radial runout and axial movement of the printing cylinders. Three measurements were taken at each cylinder: the left end, the middle, and the right end. Each measurement was taken three times, and the average of the nine measurements was used as the baseline value. The measurement results showed that the radial runout baseline values ​​of all six printing cylinders were within 0.005 mm, and the axial movement baseline values ​​were all within 0.01 mm. A standard pressure sensor with an accuracy of 0.1 N was used to measure the printing pressure. Measurements were taken every 10 pressure settings from 0 to 100, establishing a correspondence between the pressure setting and the actual printing pressure. The measurement results are shown in the table below.

[0083] Printing was performed using a standard test pattern. Print density was measured using a densitometer with an accuracy of 0.01 mm, and registration accuracy was measured using a registration tester with an accuracy of 0.001 mm. The baseline values ​​were recorded. The measurement results showed that the baseline value for print density was 1.3, and the baseline value for registration accuracy was ±0.01 mm.

[0084] Following the same method, benchmark performance calibrations were performed on other key components such as the die-cutting blade, glue gun, and servo motor. For example, the benchmark values ​​for the die-cutting blade's blade hardness are HRC58-62, the die-cutting depth is 95% of the original paper thickness, and the rough edge length is no more than 0.5mm; the benchmark value for the glue gun's glue dispensing amount at an opening time of 10ms is 0.05g, and the glue line width is 2mm; the benchmark values ​​for the servo motor's positioning accuracy are ±0.01mm, and the repeatability accuracy is ±0.005mm; the benchmark value for the actual surface temperature of the drying heating tube at a set temperature of 80℃ is 80℃±1℃; and the benchmark value for the tension roller's tension fluctuation is no more than ±2N.

[0085] Next, a baseline database of process parameters was established. Initially, 250ml paper cups were produced, and the process parameters for each unit were gradually adjusted until 1000 paper cups were produced continuously and all met the standards. These process parameters were recorded as baseline values ​​for the 250ml paper cups, including: raw paper tension of 50N, printing pressure of 120N, printing speed of 300 cups / minute, drying temperature of 80℃, die-cutting pressure of 2000N, die-cutting speed of 300 cups / minute, forming temperature of 120℃, glue paste temperature of 100℃, glue gun opening time of 10ms, and pressing pressure of 500N.

[0086] Then, following the same method, 500ml paper cups were produced, and the baseline process parameters were determined as follows: raw paper force 60N, printing pressure 130N, printing speed 280 cups / minute, drying temperature 85℃, die-cutting pressure 2200N, die-cutting speed 280 cups / minute, forming temperature 125℃, bottom pasting temperature 105℃, glue gun opening time 12ms, and pressing pressure 550N. These two sets of baseline process parameters were stored in the process parameter baseline library.

[0087] Finally, initialize the total runtime counter for the equipment, the individual runtime counters for each key component, the total output counter, and the individual output counters for each product specification, with all counters initialized to 0. Simultaneously, set the data backup cycle to once daily, with backup storage media consisting of both external hard drives and cloud storage.

[0088] Real-time data acquisition and preprocessing during the production process: After the production line is officially put into production, data from each sensor is first collected according to the set sampling frequency. The sampling frequency of the pressure sensor is 100Hz, that is, data is collected once every 10ms; the sampling frequency of the temperature sensor is 1Hz, that is, data is collected once every 1 second; the sampling frequency of the displacement sensor is 100Hz; the sampling frequency of the current sensor is 10Hz, that is, data is collected once every 100ms; the sampling frequency of the vision inspection system and the quality inspection sensor is synchronized with the production line speed, that is, data is collected once for each paper cup produced. When the production line speed is 300 cups / minute, the sampling frequency is 5Hz.

[0089] All collected data is transmitted to the central controller in real time via industrial Ethernet. The central controller adds a timestamp with an accuracy of 1ms to each data point to ensure that all data have a unified time reference. For example, printing pressure data collected at 10:00:00.000 on May 18, 2026, will be timestamped as "2026-05-1810:00:00.000".

[0090] Then, the central controller preprocesses the raw data. First, it uses the 3σ criterion to remove outliers. For example, for printing pressure parameters, if the average value over the most recent minute is 120N and the standard deviation is 2N, then data exceeding the range of 114N to 126N will be identified as outliers and removed. Suppose that printing pressure data collected at a certain moment is 150N; this value exceeds the range of 114N to 126N and is therefore identified as an outlier and removed.

[0091] Next, a moving average filter is applied to the data after outlier removal, with a moving average window size of 10 sampling points. For example, for printing pressure parameters, the data from the current sampling point and the previous 9 sampling points are taken, and the average of these 10 data points is calculated as the filtered value of the current sampling point. This moving average filter effectively removes high-frequency noise from the data while preserving its low-frequency trend variations.

[0092] Finally, the preprocessed data is converted into relative values. For example, if the current printing pressure measurement is 115N and the reference value is 120N, then the relative value is 115 / 120≈0.958; if the current registration error measurement is 0.015mm and the reference value is 0.01mm, then the relative value is 0.015 / 0.01=1.5.

[0093] The preprocessed data is stored in an industrial database in chronological order, with a data storage period of 3 years. At the end of each production day, the data is backed up and stored on both an external hard drive and cloud storage to ensure data security.

[0094] Real-time assessment of equipment performance degradation and calculation of degradation index, taking a printing cylinder as an example, extracts degradation characteristic parameters including average printing pressure, standard deviation of printing pressure, average registration error, and average printing density. The weighting coefficients for these four characteristic parameters are 0.4, 0.2, 0.3, and 0.1, respectively, with a sum of 1. These weighting coefficients were determined experimentally during the benchmark calibration process in step 1. The average printing pressure has the greatest impact on the printing cylinder performance, hence its largest weighting coefficient; the average printing density has the least impact, hence its smallest weighting coefficient.

[0095] Suppose that at a certain moment, the current values ​​of the four characteristic parameters of the printing cylinder are: average printing pressure 114N, standard deviation of printing pressure 3N, average registration error 0.03mm, and average printing density 1.2. The corresponding baseline values ​​are: printing pressure 120N, standard deviation of printing pressure 1N, registration error 0.01mm, and printing density 1.3. The permissible deviations are: printing pressure ±6N, standard deviation of printing pressure ±2N, registration error ±0.02mm, and printing density ±0.1.

[0096] First, calculate the degree of degradation for each feature parameter: Degradation of printing pressure = |114-120| / 6 = 1.0 Degradation degree of printing pressure standard deviation = |3-1| / 2 = 1.0 Registration error degradation degree = |0.03-0.01| / 0.02 = 1.0 Degradation of print density = |1.2 - 1.3| / 0.1 = 1.0 Then, calculate the degradation index of the printing cylinder: Degradation index = 1.0 × 0.4 + 1.0 × 0.2 + 1.0 × 0.3 + 1.0 × 0.1 = 1.0 This indicates that the printing cylinder's performance has reached its maximum permissible degradation level and requires maintenance.

[0097] Using the same method, calculate the degradation index of other key components. Assume that the degradation index of the die-cutting blade is 0.6, the glue gun is 0.4, the servo motor is 0.3, the drying heating tube is 0.2, and the tension roller is 0.1.

[0098] Finally, the overall degradation index of the equipment was calculated. The weighting coefficients for each key component were as follows: printing roller 0.3, die-cutting blade 0.25, glue gun 0.2, servo motor 0.15, drying heating element 0.06, and tension roller 0.04. These weighting coefficients were determined based on the degree of influence of each key component on product quality. The printing roller has the greatest impact on product quality, hence its largest weighting coefficient; the tension roller has the least impact, hence its smallest weighting coefficient.

[0099] Overall degradation index = 1.0 × 0.3 + 0.6 × 0.25 + 0.4 × 0.2 + 0.3 × 0.15 + 0.2 × 0.06 + 0.1 × 0.04 = 0.3 + 0.15 + 0.08 + 0.045 + 0.012 + 0.004 = 0.591 According to the classification standard of overall equipment degradation index, 0.591 is between 0.3 and 0.7, so the equipment is in a state of slight degradation and process parameter compensation is required.

[0100] Perform adaptive compensation calculations and execution for process parameters.

[0101] First, calculate the adjustment amount for each process parameter. During the baseline calibration process, the compensation coefficients determined experimentally are as follows: Printing pressure compensation coefficient: 6N / unit degradation index; Overprint position compensation coefficient: 0.02mm / unit degradation index; Die-cutting pressure compensation coefficient: 100N / unit degradation index; Glue gun opening time compensation coefficient: 2ms / unit degradation index; Positioning offset compensation coefficient: 0.01mm / unit degradation index; Drying temperature compensation coefficient: 5℃ / unit degradation index; Based on these compensation coefficients and the degradation index of each component, the adjustment amount of the process parameters is calculated: Printing pressure adjustment amount = printing cylinder degradation index × printing pressure compensation coefficient = 1.0 × 6N = 6N; The overprint position adjustment amount = printing cylinder degradation index × overprint position compensation coefficient = 1.0 × 0.02 mm = 0.02 mm; Die-cutting pressure adjustment amount = Die-cutting blade degradation index × Die-cutting pressure compensation coefficient = 0.6 × 100N = 60N; Adjustment amount for glue gun opening time = glue gun degradation index × glue gun opening time compensation coefficient = 0.4 × 2ms = 0.8ms; Positioning offset adjustment amount = servo motor degradation index × positioning offset compensation coefficient = 0.3 × 0.01 mm = 0.003 mm; Drying temperature adjustment = Degradation index of drying heating element × Drying temperature compensation coefficient = 0.2 × 5℃ = 1℃; Then, the adjustment amount is limited. The upper and lower limits of the adjustment amount for each process parameter are as follows: Printing pressure adjustment: upper limit 10N, lower limit -10N; Overprint position adjustment: upper limit 0.05mm, lower limit -0.05mm; Die-cutting pressure adjustment: upper limit 200N, lower limit -200N; Glue gun opening time adjustment: upper limit 5ms, lower limit -5ms; Positioning offset adjustment: upper limit 0.02mm, lower limit -0.02mm; Drying temperature adjustment range: upper limit 10℃, lower limit -10℃; All the calculated adjustment amounts are within the allowable range, therefore no adjustment is required.

[0102] Next, calculate the updated process parameter values: Printing pressure = 120N + 6N = 126N; Overprint position = reference position + 0.02mm; Die-cutting pressure = 2000N + 60N = 2060N; The glue gun opening time = 10ms + 0.8ms = 10.8ms; Positioning offset = reference offset + 0.003mm; Drying temperature = 80℃ + 1℃ = 81℃; The central controller sends the updated process parameter values ​​to the equipment controllers of each unit in real time, and the equipment controllers immediately execute the new process parameters.

[0103] Finally, the compensation effect was verified using an online testing system. The quality of 100 paper cups was continuously tested, including printing density, registration accuracy, die-cutting depth, rough edge length, glue line width, cup size, weight, and sealing performance. The test results showed that all indicators of the paper cups met the standards, indicating that the compensation was effective.

[0104] If any products fail the compensation effect verification process, for example, if 3 out of 100 paper cups have a printing density lower than the standard requirement, it indicates that the compensation amount is insufficient. In this case, the system will automatically recalculate the adjustment amount, halving the step size of the printing pressure adjustment, i.e., from 6N to 3N. The updated printing pressure is 120N + 3N = 123N. Then, the compensation is performed again and the effect is verified until all 100 consecutive products pass the verification.

[0105] To predict equipment maintenance timing and update post-maintenance baselines, degradation index data of printing cylinders over the past 30 days was extracted from an industrial database. Linear regression analysis using the least squares method yielded the equation for the degradation trend line: y = 0.02x + 0.4, where x represents the number of days and y represents the degradation index. The slope of the degradation trend line is 0.02, indicating that the degradation rate of the printing cylinder is 0.02 units of degradation index per day.

[0106] The current degradation index of the printing cylinder is 1.0. Substitute this into the equation to calculate the remaining service life: 1.0 = 0.02x + 0.4; x = (1.0 - 0.4) / 0.02 = 30 days; This indicates that without maintenance, the printing cylinder will reach a severely degraded state in 30 days. However, since the current degradation index of the printing cylinder has already reached 1.0, the system immediately issues an emergency maintenance reminder, requiring the machine to be stopped and the printing cylinder replaced.

[0107] After receiving the notification, maintenance personnel replaced the printing cylinder with a new one during the day's production break. Following the maintenance, the new printing cylinder was recalibrated according to the requirements of step 1. The calibration results showed that the radial runout of the new printing cylinder was 0.004 mm, the axial runout was 0.008 mm, the correspondence between the printing pressure adjustment setting and the actual printing pressure was consistent with the original benchmark, the printing density benchmark value was 1.3, and the registration accuracy benchmark value was ±0.01 mm, all meeting the benchmark requirements.

[0108] Then, a trial production test was conducted, producing 1000 250ml paper cups. The test results showed that the quality of all paper cups met the standards, indicating that the baseline values ​​of the process parameters did not need to be adjusted. Finally, the running time counter of the printing roller was reset to zero and started counting again. The details of this maintenance, the models of the replaced parts, the maintenance time, and the maintenance personnel were recorded in the equipment maintenance file.

[0109] For other components, such as the die-cutting blade, the degradation trend line equation obtained after linear regression analysis of its degradation index data over the past 30 days is: y = 0.01x + 0.3. The current degradation index of the die-cutting blade is 0.6. Substituting these values ​​into the equation, the remaining service life is calculated as follows: 1.0 = 0.01x + 0.3; x = (1.0 - 0.3) / 0.01 = 70 days; Therefore, the recommended maintenance date for the die-cutting blade is 70 days later. The system records this date in the maintenance plan and issues a maintenance reminder when the remaining service life is less than or equal to 7 days.

[0110] This application also provides an embodiment of an electronic device. The electronic device is manifested in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors or processing units, memory, and buses connecting different components (including memory and processing units).

[0111] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0112] The electronic device can also communicate with one or more external devices (e.g., keyboard, pointing device, camera, etc.), may include a display, and may communicate with one or more devices that enable a user to interact with the electronic device, and / or with any device that enables the electronic device to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via an input / output (I / O) interface. Furthermore, the electronic device can also communicate with one or more networks (e.g., Local Area Network (LAN), Wide Area Network (WAN) and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. The processor executes various functional applications and data processing by running programs stored in memory, such as implementing the real-time data control method for the intelligent packaging paper container production process provided in the above embodiments of the present invention.

[0113] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. 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 method for real-time control of data in the intelligent packaging paper container production process, characterized in that, Includes the following steps: S1. Offline division of production line functional units and identification of key components, calibration of the benchmark performance parameters of each key component, establishment of a benchmark library of process parameters for different product specifications, and initialization of running time and output. S2. Collect operational data and product quality data of key components online, and store the data after performing outlier removal, moving average filtering and data normalization in sequence. S3. Extract the feature parameters related to the degradation mechanism, calculate the degradation degree of a single parameter, and obtain the degradation index of key components and the overall degradation index of the equipment by weighting, and classify the equipment operating status level. S4. Calculate the process parameter adjustment amount based on the degradation index and the preset linear compensation relationship, update and execute the process parameters after limiting the amplitude, and verify the compensation effect through quality inspection. S5. Regularly analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, recalibrate the benchmarks and update the benchmark library.

2. The method for real-time control of intelligent packaging paper container production process data according to claim 1, characterized in that, In step S1, the production line functional units include a raw paper conveying unit, a printing unit, a die-cutting unit, a forming unit, a box gluing unit, and a quality inspection unit; the key components include a tension roller, a servo motor, a web-correcting sensor, a printing roller, an impression roller, an ink roller, a drying heating tube, a die-cutting plate, a forming mold, a glue gun, a vision inspection camera, and a weighing sensor.

3. The method for real-time control of intelligent packaging paper container production process data according to claim 1, characterized in that, In step S1, the benchmark performance calibration of the key components includes the benchmark calibration of the printing roller, the benchmark calibration of the die-cutting blade, the benchmark calibration of the glue gun, and the benchmark calibration of the servo motor; all measurements are repeated three times, and the arithmetic mean is taken as the benchmark value.

4. The method for real-time control of intelligent packaging paper container production process data according to claim 1, characterized in that, In step S4, the linear compensation relationship includes compensation for printing roller wear, die-cutting blade dulling, glue gun clogging, servo motor accuracy reduction, and drying heating tube aging; when multiple components affect the same process parameter, the adjustment amounts are algebraically summed.

5. The method for real-time control of intelligent packaging paper container production process data according to claim 1, characterized in that, In step S5, the least squares method is used to perform linear regression analysis on the degradation index data of the past 30 days. The formula for calculating the remaining service life is: remaining service life = (1.0 - current degradation index) / degradation trend line slope; a maintenance reminder is issued when the remaining service life is ≤ 7 days.

6. A system using the real-time data control method for the intelligent packaging paper container production process as described in claim 1, characterized in that, include: The benchmark calibration module is used to divide the production line into functional units offline and identify key components, calibrate the benchmark performance parameters of each key component, establish a process parameter benchmark library and initialize counters; The data acquisition and preprocessing module is used to collect production process data online, and then perform outlier removal, moving average filtering and data normalization before storing the data. The degradation assessment module is used to extract characteristic parameters related to the degradation mechanism, calculate the degradation degree of a single parameter, the degradation index of key components and the overall degradation index of the equipment, and classify the equipment operating status level. The process compensation module is used to calculate the adjustment amount of process parameters based on the degradation index and the preset linear compensation relationship, update and execute the process parameters after limiting the range, and verify the compensation effect through quality inspection. The maintenance prediction module is used to periodically analyze component degradation trends, predict remaining service life, and develop maintenance plans. After maintenance is completed, the baseline is updated.

7. The intelligent packaging paper container production process data real-time control system according to claim 1, characterized in that, The benchmark calibration module includes a cell partitioning submodule, a benchmark calibration submodule, a benchmark library establishment submodule, and a counter initialization submodule; The benchmark calibration submodule is used to perform benchmark performance calibration on the printing roller, die-cutting blade, glue gun, and servo motor.

8. The intelligent packaging paper container production process data real-time control system according to claim 1, characterized in that, The data acquisition and preprocessing module includes a sensor array, a data transmission submodule, a preprocessing submodule, and a data storage submodule; the sensor array includes a pressure sensor, a temperature sensor, a displacement sensor, a current sensor, a vision inspection system, and a quality inspection sensor.

9. The intelligent packaging paper container production process data real-time control system according to claim 1, characterized in that, The degradation assessment module includes a feature extraction submodule, a single-parameter degradation calculation submodule, a component degradation index calculation submodule, and an overall status assessment submodule; the overall status assessment submodule is used to classify the equipment operating status into four levels: normal, slight degradation, moderate degradation, and severe degradation.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the real-time control method for intelligent packaging paper container production process data as described in claim 1.

Images