Intelligent carton production management system and method

Abstract

The invention relates to the technical field of intelligent production management, in particular to an intelligent carton production management system and method, and the system comprises a production line parameter collection module, a productivity prediction calculation module, an inventory demand analysis module, a quota dynamic adjustment module, and an execution control feedback module. According to the method, the operation parameters of the cutting link and the paperboard characteristics are synchronously marked and processed, so that the production state is presented in a continuous data form, and the mapping relation between output and consumption is constructed based on parameter changes, so that the production efficiency has calculable and comparable characteristics; a state judgment basis linked with inventory requirements is formed by combining time window analysis, so that the production quota is dynamically corrected along with state changes, yield deviation detection and feedback correction are introduced in the execution process, a control instruction is kept consistent with actual operation, production adjustment is changed from experience judgment to data driving, inventory fluctuation is reduced, and the production efficiency is improved. And resource utilization and production stability are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent production management technology, and in particular to an intelligent production management system and method for cardboard boxes. Background Technology

[0002] The field of intelligent production management technology involves technologies related to the information-based organization and control of manufacturing production activities. Its core aspects include production planning and adjustment, process flow organization, equipment operation and maintenance management, material procurement and inventory turnover control, production data collection and recording, quality inspection and traceability, and personnel work arrangement. This technology achieves coordinated operation of the entire production process by uniformly managing elements such as order information, process parameters, equipment status, and material consumption. It is widely used in discrete manufacturing and process manufacturing scenarios to meet the needs of large-scale and customized production.

[0003] The traditional intelligent production management system for cardboard boxes refers to a system that manages the cardboard production process, including order information, cardboard cutting, printing, slotting, gluing, and stapling. It generates production task sheets based on manually entered order information, and distributes production quantity, specifications, and process requirements to multiple processes. Operators then set parameters on the cutting, printing, and forming equipment according to the task sheets. Production progress information is collected through on-site record sheets or terminal input. At the same time, the system schedules the operation time of different equipment according to a predetermined production sequence to manage the cardboard box production process.

[0004] Current cardboard box production management relies on order sheets and fixed process sequences to organize production. Equipment parameters are mainly set based on experience. There is a lack of continuous perception of the cutting tool's operating status and changes in cardboard thickness during the cutting process. Production data is summarized in a post-event reporting manner, and there is a lack of time correlation between parameter changes. Output assessment relies on experience and static statistics, which makes it difficult to reflect actual consumption relationships. Inventory adjustments are mostly based on manual judgment or preset rules. The production rhythm is out of sync with the inventory status. When raw material characteristics or equipment status fluctuate, quota adjustments are prone to lag, resulting in increased output deviations and accumulated inventory risks. Summary of the Invention

[0005] To address the technical problems of existing cardboard box production management that rely on order sheets and fixed process sequences for production organization, equipment parameters are mainly set based on experience, there is a lack of continuous perception of the cutting tool's operating status and changes in cardboard thickness during the cutting process, production data is summarized in a post-event reporting manner, there is a lack of time correlation between parameter changes, output assessment relies on experience and static statistics, which is difficult to reflect actual consumption relationships, inventory adjustments are mostly based on manual judgment or preset rules, production rhythm is out of sync with inventory status, and when raw material characteristics or equipment status fluctuate, quota adjustments are prone to lag, resulting in increased output deviations and accumulated inventory risks, this invention provides an intelligent cardboard box production management system and method.

[0006] On the one hand, an intelligent production management system for cardboard boxes is provided, which includes: The production line parameter acquisition module monitors the changes in the cutting machine's blade speed to obtain instantaneous blade speed values, detects cardboard thickness parameters, timestamps and synchronizes the blade speed and thickness values, performs filtering processing on the blade speed and thickness values, and constructs a carton production status dataset. The capacity prediction and calculation module calls the carton production status dataset, extracts the knife speed change rate and board thickness change rate as feature vectors, uses a support vector machine regression model to train the nonlinear mapping relationship, calculates the ratio of the predicted output of finished carton to the consumption of raw paper, and generates the carton production efficiency coefficient. The inventory demand analysis module calls the carton production efficiency coefficient, uses a sliding window algorithm to perform weighted average calculation, marks the production status according to the preset efficiency threshold, and establishes an index of inventory adjustment strategies corresponding to the current production status. The quota dynamic adjustment module calls the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compares and analyzes it with the current finished carton inventory, and obtains an increase production instruction when the inventory is lower than the strategy requirement and a decrease production instruction when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan.

[0007] As a further aspect of the present invention, the carton production status dataset includes equipment operation stability indicators, production cycle consistency indicators, abnormal working condition classification identifiers, and production time period characteristic information; the carton production efficiency coefficient includes unit paper output rate, capacity utilization rate, and efficiency change trend value; the inventory adjustment strategy index corresponding to the current production status includes inventory safety level, production adjustment response type, and adjustment decision weight coefficient; and the carton production quota adjustment scheme includes target output setting value, capacity allocation ratio coefficient, and output adjustment range level.

[0008] As a further aspect of the present invention, the production line parameter acquisition module includes: The speed acquisition submodule monitors the changes in the cutting machine tool speed to obtain instantaneous sampled values ​​of the tool speed, acquires the pulse time sequence output by the speed sensor, records the corresponding time of the sampling clock, performs first-order difference operation based on the time difference of adjacent pulses and performs pulse timing alignment processing to generate the instantaneous speed value of the tool. The thickness acquisition submodule detects the paperboard thickness parameters, acquires the displacement electrical signal sequence output by the thickness detection device, converts it into a thickness value according to the calibration relationship, organizes it in sequence according to the acquisition time information, filters abnormal jump data according to the thickness change range, and generates the paperboard thickness measurement value. The time-series fusion submodule, based on the paperboard thickness measurement value and the instantaneous speed value of the cutter, calculates the time offset according to the acquisition time information of the two types of data, performs item-by-item alignment on the speed sequence and thickness sequence, performs filtering processing, and combines them in time order to establish a carton production status dataset.

[0009] As a further aspect of the present invention, the capacity prediction calculation module includes: The production status acquisition submodule acquires the carton production status dataset, performs sequential verification on the instantaneous speed value of the cutter and the measured value of the cardboard thickness based on the recorded time identifier information, determines the continuous status based on the time interval between adjacent records, rearranges the order, and generates a production status time series data sequence. The feature vector construction submodule performs differential calculation on the instantaneous speed values ​​of the cutter corresponding to adjacent time markers based on the production state time sequence and calculates the cutter speed change rate by combining the time interval. It also calculates the board thickness change rate based on the paperboard thickness measurement value and combines them according to a unified time index to generate a capacity prediction feature vector. The efficiency coefficient generation submodule calls the capacity prediction feature vector, maps the feature vector to the feature space and constructs a regression constraint relationship, determines the support vector set based on the sample distance and solves the regression function, obtains the predicted value sequence and calculates the ratio with the raw paper consumption item by item to generate the carton production efficiency coefficient. The amount of raw paper consumed is determined by the production volume of cardboard boxes, the thickness and size of the paper used in each cardboard box.

[0010] As a further aspect of the present invention, the inventory demand analysis module includes: The efficiency data processing submodule obtains the time series of the carton production efficiency coefficient, verifies the data continuity based on the time index, removes missing items, divides the data into segments according to the window length, performs weighted and normalized processing, updates the data step by step with the window, and generates a weighted production efficiency value. The status determination and labeling submodule, based on the weighted production efficiency value, calls a preset set of efficiency threshold intervals, compares the efficiency values ​​with the interval boundaries one by one, determines the interval label according to the result, maps the label to a status code and binds it to a time index, and generates a production status identifier value. The preset efficiency threshold interval set is determined based on the statistical results formed by the time series of carton production efficiency coefficients. The statistical results include at least the distribution of weighted production efficiency values ​​obtained within a continuous production cycle. The upper and lower boundaries of the efficiency threshold interval are obtained by dividing the weighted production efficiency values ​​into quantiles. The inventory strategy mapping submodule calls the production status identifier value, performs key-value matching in the inventory adjustment rule table according to the status code, extracts the inventory adjustment parameters, performs consistency verification and combines them for association, and establishes the inventory adjustment strategy index corresponding to the current production status.

[0011] As a further aspect of the present invention, the quota dynamic adjustment module includes: The strategy matching submodule calls the inventory adjustment strategy index corresponding to the current production status, collects the current production status identifier and receives the strategy table index field, performs comparison and verification based on the status identifier and index field, decomposes and verifies the target inventory and fluctuation range parameters, and generates the inventory control benchmark quantity. The inventory deviation calculation submodule obtains the current inventory of finished cartons based on the inventory control benchmark quantity and performs inventory measurement verification. It calculates the difference between the measured inventory value and the inventory control benchmark quantity and identifies the deviation direction. Based on the fluctuation range parameter, it determines the range of the difference and obtains the inventory deviation value. The quota adjustment generation submodule, based on the inventory deviation value, calls the corresponding quota correction rule parameters in the inventory adjustment strategy, performs proportional mapping and numerical conversion for the current production quota, performs boundary condition verification and discretization processing on the conversion result, and generates a carton production quota adjustment scheme.

[0012] As a further aspect of the present invention, the system further includes: The execution control feedback module sends production speed control signals and packaging frequency adjustment instructions according to the carton production quota adjustment scheme. It calculates the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, it triggers parameter correction and generates the carton production management execution status result. The execution status results of the carton production management include the execution achievement rate index, the output deviation classification results, and the system operation effectiveness evaluation indicator.

[0013] As a further aspect of the present invention, the execution control feedback module includes: The production speed control submodule obtains production quota data and receives equipment status parameters according to the carton production quota adjustment scheme, performs production cycle alignment calculation based on the data, compares the deviation between output capacity and operating rhythm, and generates a production speed control signal. The packaging frequency adjustment submodule obtains the packaging line operation status and output data according to the carton production quota adjustment plan, calculates the packaging frequency based on the data, performs consistency verification and mapping instructions on the frequency results and operation status, and generates packaging frequency adjustment instructions. The deviation detection and calculation submodule, based on the packaging frequency adjustment command and production speed control signal, obtains actual and expected output data, performs difference calculation and identifies the direction of the difference, compares it item by item with the preset deviation threshold, triggers production parameter correction for differences exceeding the threshold, and generates the carton production management execution status result.

[0014] As a further aspect of the present invention, the preset deviation threshold is based on the original production quota data recorded in the carton production quota adjustment scheme and the actual output data within the corresponding period. The deviation interval is statistically processed according to a unified statistical period to obtain the maximum allowable deviation value of the stable operating interval, and the maximum allowable deviation value is used as the preset deviation threshold.

[0015] On the other hand, the intelligent production management method for cardboard boxes, which is executed based on the aforementioned intelligent production management system for cardboard boxes, includes the following steps: S1: Monitor the change in the cutting machine's blade speed to obtain the instantaneous value of the blade speed, detect the paperboard thickness parameter, timestamp and synchronize the blade speed value and thickness value, perform filtering processing on the blade speed value and thickness value, and construct a carton production status dataset. S2: Call the carton production status dataset, extract the knife speed change rate and board thickness change rate as feature vectors, use a support vector machine regression model to train the nonlinear mapping relationship, calculate the ratio of the predicted output of finished carton to the consumption of raw paper, and generate the carton production efficiency coefficient. S3: Call the carton production efficiency coefficient, use the sliding window algorithm to perform weighted average calculation, mark the production status according to the preset efficiency threshold, and establish an inventory adjustment strategy index corresponding to the current production status. S4: Call the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compare and analyze it with the current finished carton inventory, and obtain an increase production instruction when the inventory is lower than the strategy requirement, and obtain a decrease production instruction when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan. S5: Send production speed control signals and packaging frequency adjustment instructions according to the carton production quota adjustment scheme. Calculate the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, trigger parameter correction and generate the carton production management execution status result.

[0016] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: By synchronously marking and processing the operating parameters of the cutting process and the characteristics of the cardboard, the production status is presented in the form of continuous data. Based on the parameter changes, a mapping relationship between output and consumption is constructed, making production efficiency calculable and comparable. Combined with time window analysis, a status judgment basis linked to inventory demand is formed, allowing production quotas to be dynamically corrected according to status changes. During the execution process, output deviation detection and feedback correction are introduced to ensure that control commands are consistent with actual operation. Production adjustment shifts from experience-based judgment to data-driven, reducing inventory fluctuations and improving resource utilization and production stability. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the accompanying drawings without creative effort.

[0018] Figure 1 This is a system schematic diagram of the present invention; Figure 2 This is a schematic diagram of the system framework of the present invention; Figure 3 This is a flowchart of the production line parameter acquisition module in this invention; Figure 4 This is a flowchart of the capacity prediction calculation module in this invention; Figure 5 This is a flowchart of the inventory demand analysis module in this invention; Figure 6 This is a flowchart of the quota dynamic adjustment module in this invention; Figure 7 This is a flowchart of the control feedback module in this invention; Figure 8 This is a flowchart of the method of the present invention. Detailed Implementation

[0019] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0020] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0021] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0022] In this embodiment of the invention, sometimes the subscript such as W1 is written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0023] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0024] This invention provides an intelligent production management system for cardboard boxes, such as... Figure 1-2 The diagram shown illustrates an intelligent production management system for cardboard boxes. This system includes: The production line parameter acquisition module monitors the changes in the cutting machine's blade speed to obtain instantaneous blade speed values, detects cardboard thickness parameters, timestamps and synchronizes the blade speed and thickness values, performs filtering processing on the blade speed and thickness values, and constructs a carton production status dataset. The capacity prediction and calculation module calls the carton production status dataset, extracts the knife speed change rate and board thickness change rate as feature vectors, uses a support vector machine regression model to train the nonlinear mapping relationship, calculates the ratio of the predicted output of finished carton to the consumption of raw paper, and generates the carton production efficiency coefficient. The inventory demand analysis module calls the cardboard box production efficiency coefficient, uses the sliding window algorithm to perform weighted average calculation, marks the production status according to the preset efficiency threshold, and establishes an index of inventory adjustment strategies corresponding to the current production status. The quota dynamic adjustment module calls the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compares and analyzes it with the current finished carton inventory, and obtains an increase production instruction when the inventory is lower than the strategy requirement and a decrease production instruction when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan. The execution control feedback module sends production speed control signals and packaging frequency adjustment instructions according to the carton production quota adjustment plan. It calculates the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, it triggers parameter correction and generates the carton production management execution status result. The carton production status dataset includes equipment operation stability indicators, production cycle consistency indicators, abnormal working condition classification identifiers, and production time period characteristic information. The carton production efficiency coefficient includes unit paper output rate, capacity utilization rate, and efficiency change trend value. The inventory adjustment strategy index corresponding to the current production status includes inventory safety level, production adjustment response type, and adjustment decision weight coefficient. The carton production quota adjustment scheme includes target output setting value, capacity allocation ratio coefficient, and output adjustment range level. The carton production management execution status results include execution achievement rate indicators, output deviation classification results, and system operation effectiveness evaluation identifiers.

[0025] Specifically, such as Figure 2 , 3 As shown, the production line parameter acquisition module includes: The speed acquisition submodule monitors the changes in the cutting machine tool speed to obtain instantaneous sampled values ​​of the tool speed, acquires the pulse time sequence output by the speed sensor, records the corresponding time of the sampling clock, performs first-order difference operation based on the time difference of adjacent pulses and performs pulse timing alignment processing to generate the instantaneous speed value of the tool. An incremental rotary encoder, model E6B2-CWZ6C, was selected as the core component for speed acquisition. This encoder was rigidly connected to the non-drive end of the cutting machine's cutter shaft, and the encoder's resolution parameters were set. Configure the high-frequency pulse capture channel of the data acquisition card to achieve 2500 pulses per revolution, and set the sampling clock frequency. The frequency is 50 MHz. When the cutting machine starts running and drives the cutter shaft to rotate, the encoder outputs quadrature pulse signals of phase A and phase B. The acquisition card triggers an interrupt when it detects the rising edge of the phase A pulse, reads the count value in the current hardware timer register, and stores the count value in the high-speed cache queue to construct a pulse time sequence. For example, the clock count values ​​corresponding to three consecutively captured pulses are as follows: , , ,in The value read is 1000500. The value read is 1005500. The read value is 1010500. Record the time corresponding to the sampling clock. Convert the count value into a physical timestamp using the clock frequency. The calculation formula is as follows: The corresponding timestamp For 0.02001 seconds, For 0.02011 seconds, The pulse period is 0.02021 seconds. First-order difference operations are performed based on the time difference between adjacent pulses, and pulse timing alignment is then applied. The timestamps of adjacent terms in the sequence are extracted, and subtraction is performed to obtain the pulse period. The calculations were based on the example data. Second, The calculated time difference is then reverted to the center of the pulse interval, i.e., the time label of the velocity calculation point is set to [value missing]. Call the speed conversion logic and use the formula Calculate the rotational speed and substitute the values ​​to obtain the result. For each revolution per minute, a sliding average filter is applied to the continuously calculated rotational speed values. The sliding window size is set to 5 to remove instantaneous noise caused by mechanical vibration and generate the instantaneous rotational speed value of the tool.

[0026] The thickness acquisition submodule detects the paperboard thickness parameters, acquires the displacement electrical signal sequence output by the thickness detection device, converts it into a thickness value according to the calibration relationship, organizes it in sequence according to the acquisition time information, filters abnormal jump data according to the thickness change range, and generates the paperboard thickness measurement value. A laser triangular reflective displacement sensor is installed above the cardboard conveying path, and the effective measurement range of the sensor is set. The sensor's analog output range is 0 mm to 30 mm, calibrated to a current signal range of 4 mA to 20 mA. The sensor output is connected to the input channel of an analog-to-digital converter (ADC). The displacement electrical signal sequence output by the thickness detection device is acquired. The ADC resolution is set to 16 bits, and the sampling frequency to 1000 Hz. The instantaneous current value transmitted by the sensor is continuously read. Based on the calibration relationship, the current is converted into a thickness value, and a linear mapping equation between current and thickness is established. , here This represents the calculated thickness value. If the collected current value is 12 mA, then substituting it into the calculation yields... The specific current signal and thickness conversion data are shown in Table 1, which is organized sequentially according to the acquisition time information, and is used for each calculated thickness data. Add millisecond-level timestamps This generates a time-series thickness data stream, filters out abrupt changes in data based on thickness variation ranges, and sets a threshold for the thickness change rate. The threshold was set with reference to the maximum allowable roughness and corrugation characteristics of the cardboard surface. Standard cardboard samples were selected for testing, and the maximum normal thickness difference between adjacent sampling points was measured to be 0.5 mm. Considering sensor noise, [the threshold was set to - the original text is incomplete]. Set to 0.8 mm, traverse the thickness data stream, and calculate the absolute value of the difference between adjacent data points. ,like If the value is in millimeters, then the current data is determined. For abnormal transition points, the normal value from the previous time step is used. Replace the outlier value. For example, if the sequence contains 15.0 mm, 15.1 mm, 25.0 mm, and 15.2 mm, where 25.0 mm differs from the previous value by 9.9 mm, exceeding the threshold of 0.8 mm, perform a replacement operation to correct it to 15.1 mm, and generate the paperboard thickness measurement value.

[0027] Table 1: Thickness Sensor Signal Calibration Data Table Table 1 shows the linear correspondence between the sensor output current, ADC sampling value and final physical thickness in the thickness acquisition submodule, serving as a reference for data conversion.

[0028] The time-series fusion submodule, based on the paperboard thickness measurement value and the instantaneous speed value of the cutter, calculates the time offset according to the acquisition time information of the two types of data, performs item-by-item alignment on the speed sequence and thickness sequence, performs filtering processing and combines them in time order to establish a carton production status dataset; Read the physical distance between the thickness detection point and the center point of the cutting tool in the configuration parameters. The distance was measured to be 2.5 meters, and the average linear velocity fed back by the conveyor belt's main shaft encoder was also obtained. Assuming the current production line speed is constant at 1.25 meters per second, the time offset is calculated based on the acquisition time information of the two types of data, and then the formula is used. Calculate the lag time and substitute it into the numerical calculation. The second indicates that the position of the cardboard being cut by the tool at the current moment corresponds to the part that passed the thickness sensor 2.0 seconds ago. The speed sequence and thickness sequence are aligned item by item, with the tool speed sampling time as the reference. Based on this, the closest timestamp is retrieved from the thickness data sequence. For data items in seconds, if the timestamps of the thickness sequence are respectively Second, The tool rotation speed sampling time is 12.05 seconds, and the corresponding traceback time is 10.05 seconds, which is in the range of seconds. and Between these points, the thickness value at that moment was calculated using linear interpolation. The data is filtered and combined in chronological order. Kalman filtering is then applied to the aligned rotational speed and thickness data pairs. The state observation noise covariance matrix is ​​then set. for Smooth out data fluctuations and process the data at the same time. The following speed value Thickness value and the corresponding linear velocity according to The data is written to the database line by line in a specific format, for example, a single record is generated as follows: Establish a dataset of cardboard box production status.

[0029] Specifically, such as Figure 2 , 4 As shown, the capacity forecasting calculation module includes: The production status acquisition submodule acquires the carton production status dataset, performs sequential verification on the instantaneous speed value of the cutter and the measured value of the cardboard thickness based on the recorded time identifier information, determines the continuous status based on the time interval between adjacent records, rearranges the order, and generates a production status time series data sequence. Retrieve stored data including timestamps using the database query interface Rotation speed ,thickness and linear velocity The data records are set to the current production shift within the query time window. The acquired dataset is loaded into a memory buffer. Based on the recorded timestamp information, the instantaneous speed of the cutting tool and the measured thickness of the cardboard are checked for order. A quicksort algorithm is used based on the timestamp. Sort the key-value pairs of data rows in ascending order, traverse the sorted sequence, and check the timestamps of adjacent rows. and If found In cases of reverse order, the data rows are swapped to ensure strict temporal increment. Continuity is determined based on the time interval between adjacent records, and a continuity threshold is set. The threshold is selected based on the system sampling frequency. Hertz setting, calculation formula is as follows Substituting the numerical values, we get This setting is designed to allow for a jitter tolerance of up to 2.5 sampling periods, for reordering, to calculate the actual time interval. ,like Seconds, determined at to If there is a data interruption or shutdown state, insert a status flag bit in this interval. Conversely, mark For example, the previous moment Seconds, current moment If the interval is less than 0.02 seconds, it is marked as a continuous production state, and a production state time series data sequence is generated.

[0030] The feature vector construction submodule performs differential analysis on the instantaneous speed values ​​of the cutter corresponding to adjacent time markers based on the production status time sequence and calculates the cutter speed change rate by combining the time interval. It also calculates the board thickness change rate based on the paperboard thickness measurement value and combines them according to a unified time index to generate a capacity prediction feature vector. Extract continuous state flag bits For the valid data segment, perform differential calculation on the instantaneous tool rotation speed values ​​corresponding to adjacent time markers and calculate the tool speed change rate by combining the time interval, and define the tool speed change rate. The calculation formula is ,in and These are the tool rotation speeds at the current and previous moments, respectively, in revolutions per minute (rpm). and For the corresponding sampling time, this formula quantifies the acceleration characteristics of the tool by calculating the rotational speed increment per unit time. The advantage of this formula lies in its ability to sensitively capture instantaneous acceleration and deceleration oscillations during the cutting process by introducing a time derivative term, reflecting the smoothness of the mechanical transmission. Substituting the numerical values ​​into the example, let... Second, Turn every minute, Second, Every minute, then Rotating every minute and second, the board thickness change rate is calculated based on the measured board thickness value, and the board thickness change rate is defined. The calculation formula is ,in This represents the thickness of the cardboard. The absolute value is used here to reflect the magnitude, not the direction, of thickness fluctuations. Substitute the data... millimeters, assuming the current measurement value Millimeters, calculated The result, measured in millimeters per second, indicates a minute abrupt change in the thickness of the cardboard at the current instant, caused by the corrugated board's rebound under pressure. By combining the calculated feature parameters with the original state data according to a unified time index, a multidimensional feature row vector is constructed. As shown in Table 2, the specific feature data calculated and generated at this moment are listed, and the production capacity prediction feature vector is generated.

[0031] Table 2: Production Status Feature Vector Data Table Table 2 shows the sequence of production state feature vectors obtained after differential operation based on the original collected data. The tool speed change rate and plate thickness change rate reflect the dynamic stability of the production process and serve as the input basis for subsequent efficiency regression analysis.

[0032] The efficiency coefficient generation submodule calls the capacity prediction feature vector, maps the feature vector to the feature space and constructs a regression constraint relationship, determines the support vector set based on the sample distance and solves the regression function, obtains the predicted value sequence and calculates the ratio of each item with the raw paper consumption to generate the carton production efficiency coefficient. From the feature vector Extract as input vector The feature vectors are mapped to the feature space and regression constraints are constructed. A support vector regression model is built using the radial basis function (RBF) as the kernel function. The set of support vectors is determined based on sample distances, and the regression function is solved. The regression prediction formula is defined as follows: ,in This represents the predicted standard paper consumption per unit time (i.e., material consumption under theoretical maximum capacity). To pre-train selected support vectors, For the corresponding weighting coefficients, For kernel parameters, As a bias term, this formula utilizes a nonlinear mapping in high-dimensional space to accurately derive the theoretical production capacity limit under the current operating condition by weighted summation of the similarity between the original optimal production state (support vectors) and the current state, and sets the model parameters. , Select the nearest support vector The corresponding weight Substitute the current input vector First, calculate the squared Euclidean distance. Next, calculate the kernel function output. Because the single vector distance is too large, resulting in extremely small values, the support vectors are corrected to demonstrate the calculation process. Then the squared distance is The kernel function value is Calculate the predicted value Kilograms per minute were used to obtain a predicted value sequence and compare it with the raw paper consumption item by item to collect the actual raw paper consumption measurement value on the production line. The value read is kilograms per minute, using the formula Calculate the efficiency coefficient, in the formula This characterizes the degree to which actual material consumption is converted into theoretical effective production capacity under the current combination of process parameters. Substituting these values ​​into numerical calculations yields... The results show that the material utilization efficiency or capacity conversion rate under the current production state is 94.5%, with about 5.5% of non-theoretical loss or efficiency overflow (depending on the specific definition, here it means that the actual consumption is higher than the theoretical prediction standard value), generating the carton production efficiency coefficient.

[0033] Specifically, such as Figure 2 , 5 As shown, the inventory demand analysis module includes: The efficiency data processing submodule obtains the time series of carton production efficiency coefficients, verifies the continuity of data based on the time index, removes missing items, divides the data into segments according to the window length, performs weighted and normalized processing, updates the data step by step with the window, and generates a weighted production efficiency value. The efficiency coefficient set generated by the calculation is read from the time series database through the data interface. The time span for reading is set to the most recent complete production shift. For example, the efficiency coefficient value of a set of consecutive time points read is... , , , , The continuity of data is verified based on the time index, checking whether the timestamp of each data point conforms to the fixed sampling step size. Minutes, if detected If data is missing or marked as a non-numeric type (NaN), remove the missing item, remove the invalid data from the sequence, and shift the index of subsequent data forward. The reconstructed sequence is as follows: Divide the data into segments according to the window length and set the sliding window length. Construct a first-in-first-out (FIFO) data buffer and capture the current moment. and the previous The calculation window vector consists of 1 valid data point. For example, the current window data is Weighted and normalized processing is performed, and a time decay weighted algorithm is introduced to define a weight vector. The weight generation function is set as follows: ; Here Substitute the time-order index of the data within the corresponding window (1 for oldest, N for newest) into the input. Calculated , , Using the formula: ; Calculate the weighted efficiency value, where This represents the weighted production efficiency value. For the first in the window The efficiency coefficient, the advantage of this formula lies in its linearly increasing weighting, which assigns greater importance to the most recent measurement value while preserving the smoothing effect of the original data. It accurately reflects the recent trend of production efficiency and suppresses random fluctuations. Substituting the values ​​into the calculation... Step-by-step calculation yields The results indicate that the current overall production efficiency after weighted smoothing is 0.95166, slightly higher than the window mean, reflecting a slight increase or maintenance of high efficiency. As the window is updated, the window is moved one step backward along the time axis to introduce the next data point. Update the window vector to The weighting operation is repeated to generate a weighted production efficiency value.

[0034] The status determination and labeling submodule, based on the weighted production efficiency value, calls the preset efficiency threshold interval set, compares the efficiency value with the interval boundary item by item, determines the interval label according to the result, maps the label to the status code and binds the time index, and generates the production status identifier value. The system retrieves a preset efficiency threshold interval set, which is determined based on the statistical results of the time series of cardboard box production efficiency coefficients. It then retrieves a weighted efficiency value sample set of the past 30 production cycles from the original database, with a total sample size of 10,000 data points, and calculates the arithmetic mean of this sample set. with standard deviation , measured , The upper and lower boundaries of the efficiency threshold range are obtained by dividing the weighted production efficiency values ​​into quantiles, defining three state intervals: the lower limit of the high-efficiency zone is... The upper limit of the inefficient zone boundary is Substituting the values ​​into the numerical calculation yields an efficient threshold. Inefficient threshold Construct a set of intervals: efficient intervals Normal range Inefficient range The efficiency values ​​are compared with the interval boundaries item by item, and the weighted production efficiency values ​​obtained from the steps are calculated. Compare with the above threshold and execute the judgment logic: If If it is, then it is judged as efficient; if If it is normal, then it is considered normal; if If it is inefficient, the label of the interval to which it belongs is determined based on the result. Determine which state the current state belongs to. The range is labeled "High_Efficiency". The label is mapped to a status code and bound to a time index. Referring to the status code mapping table (as shown in Table 3), the hexadecimal code corresponding to "High_Efficiency" is... Record the current timestamp Generate combined data packets Generate production status identifier values.

[0035] Table 3: Production Status Threshold Classification and Inventory Strategy Mapping Table As shown in Table 3, the numerical ranges of the three production state intervals determined based on statistical distribution, the corresponding machine identification codes, and the associated inventory adjustment coefficients are listed in detail, serving as a direct reference for subsequent strategy mapping.

[0036] The inventory strategy mapping submodule calls the production status identifier value, performs key-value matching in the inventory adjustment rule table according to the status code, extracts the inventory adjustment parameters, performs consistency verification, combines and associates them, and establishes an inventory adjustment strategy index corresponding to the current production status; Parse the received data packets to obtain the status code Based on the status code, key-value matching is performed in the inventory adjustment rule table, and the mapping relationship data shown in Table 3 is loaded into the in-memory hash table. Searching using the key, the entry for "high-efficiency production" was found. Inventory adjustment parameters were extracted, and the corresponding inventory adjustment coefficients were obtained. and basic safety stock Set a standard safety stock of raw paper for this model of cardboard box. Meters are used for consistency checks and grouped together using formulas. Calculate the target value for dynamic safety stock, where The recommended inventory level represents the current production status. To reflect the correction factor for production consumption rate, this formula directly converts efficiency fluctuations at the production end into inventory level requirements at the warehousing end through multiplication. Substituting the values, the result is... Meters, further combined with the current actual remaining inventory in the warehouse. Meters, calculate replenishment trigger difference Rice, if If the target inventory level is met, a replenishment order is generated; otherwise, the system remains on hold and observes. An index of inventory adjustment strategies corresponding to the current production status is established, and the calculation results are structured and stored as a strategy record: [Status: 0x01, Adjustment coefficient: 1.15, Target inventory: 550m, Replenishment suggestion: +550m]. This result indicates that under the current efficient production status, a potential risk of accelerated raw paper consumption has been identified, and the safety stock benchmark has been automatically increased by 15%. Based on this, a replenishment suggestion of 550m has been issued to prevent material shortages.

[0037] Specifically, such as Figure 2 , 6 As shown, the quota dynamic adjustment module includes: The strategy matching submodule calls the inventory adjustment strategy index corresponding to the current production status, collects the current production status identifier and receives the strategy table index field, performs comparison and verification based on the status identifier and index field, decomposes and verifies the target inventory and fluctuation range parameters, and generates the inventory control benchmark quantity. Access the policy mapping hash table stored in memory via the background data bus, collect the current production status identifier, receive the policy table index field, and extract the generated production status code. It serves as the primary key and also receives the material index field of the current production batch. The system performs a comparison and verification based on the status identifier and the index field, and retrieves the match from the hash table. and The strategy entries are double-matched to verify the validity of the strategy version and the consistency of the timestamp, preventing the misuse of expired strategies. The target inventory and fluctuation range parameters are broken down and verified, and the dynamic safety stock target value is parsed from the matched strategy records. Meters, and obtain the allowable inventory fluctuation tolerance coefficient under this condition. ,set up (i.e., a 5% tolerance level), using the formula An inventory control baseline range is constructed. This formula creates a flexible buffer by setting upper and lower boundaries to avoid frequent adjustment commands triggered by minor normal production fluctuations. Substituting values ​​into the calculation, the lower limit is... meters, with an upper limit of Meters, while defining the inventory central baseline. meters, the interval calculated above The central value is encapsulated into a core parameter package for inventory control, generating the baseline quantity for inventory control.

[0038] The inventory deviation calculation submodule obtains the current inventory of finished cartons based on the inventory control benchmark and performs inventory measurement verification. It calculates the difference between the measured inventory value and the inventory control benchmark and identifies the deviation direction. Based on the fluctuation range parameter, it determines the range of the difference and obtains the inventory deviation value. Read the generated value including the lower limit. Upper limit and target value The parameter package retrieves the current inventory of finished cartons and performs inventory measurement verification. It then instructs the RFID reader terminal of the warehouse management subsystem to perform a real-time inventory check of the M-2025-A model cartons in the finished goods warehouse area, reading the physical inventory data as follows: Meters are used to calculate the difference between the measured inventory value and the inventory control benchmark quantity, and to indicate the direction of the deviation, using a formula. Calculate the absolute deviation, substitute it into the numerical values, and you will get... A negative result indicates a current inventory deficit. The difference is then assigned to a specific range based on the fluctuation range parameter. and control range A comparison was performed because The current inventory level has been determined to have fallen below the safe lower limit, falling into an "abnormal low level" state. Further calculation of the relative deviation rate is then performed. Calculated The result indicates that the inventory shortfall is close to 10%, necessitating remedial measures to reduce the deviation. The inventory deviation value is obtained by combining the deviation direction "Negative" and the deviation level "Level_2_Alert".

[0039] The quota adjustment generation submodule calls the corresponding quota correction rule parameters in the inventory adjustment strategy based on the inventory deviation value, performs proportional mapping and numerical conversion for the current production quota, performs boundary condition verification and discretization processing on the conversion result, and generates a carton production quota adjustment plan. Parse the input deviation data packet The corresponding quota adjustment rule parameters in the inventory adjustment strategy are called. The quota adjustment strategy parameter table shown in Table 4 is consulted, and the corresponding adjustment coefficient is matched according to the deviation level "Level_2_Alert". and the maximum single adjustment limit For each meter, a proportional mapping and numerical conversion is performed based on the current production quota to obtain the original planned production quota for the next cycle of the current production line. Meters, using formula Calculate the adjusted quota, where This is the inventory deviation value (the absolute value is used in the magnitude calculation, and the sign is determined by the inventory status; it is added for shortages and subtracted for overstocks, due to the preceding sequence). A negative value represents a deficit, so logically, an increase in the quota is needed. This is reflected in the formula. The adjustment to the compensation logic (i.e., increasing when there is a deficit) is beneficial because the formula introduces a correction coefficient. To accelerate production catch-up or slowdown caused by inventory discrepancies, while also... The function sets a hard threshold. To prevent drastic fluctuations in production plans due to sensor misreading or extreme deviations, and to protect the stable operation of the production line, the required compensation amount, based on numerical calculations, is... The value is less than the limit of 1000 meters, therefore the effective adjustment is 660 meters. Calculate the new quota. The conversion results were checked for boundary conditions and discretized. Considering that the minimum winding step length of the production equipment is 50 meters, the rounding formula was used. Discretize and calculate The plan involves adjusting the production quota for cardboard boxes.

[0040] Table 4: Inventory Quota Adjustment Strategy Parameter Table Table 4 lists the quota adjustment parameters under different inventory deviation levels, based on the calculated deviation rate. The correction factor and limit are determined by referring to a table, which serves as the key input parameters for the quota calculation formula.

[0041] Specifically, such as Figure 2, 7 As shown, the execution control feedback module includes: The production speed control submodule obtains production quota data and receives equipment status parameters according to the carton production quota adjustment plan. Based on the data, it performs production cycle alignment calculation, compares the deviation between output capacity and operating rhythm, and generates production speed control signals. Read the determined total production quota adjustment from the shared memory area. The system acquires production quota data and receives equipment status parameters. It then polls multiple servo drive nodes on the corrugated cardboard production line in real time via an industrial Ethernet interface (EtherCAT) to collect current equipment operating status data, including the current instantaneous production speed. meters per minute, remaining scheduled production time Minutes and overall equipment utilization rate coefficient Based on the data, production cycle alignment calculations are performed using the formula. Calculate the theoretical average linear velocity required to meet the quota target, where Represents the target linear velocity. For the remaining available time window, This formula, used to correct efficiency losses caused by equipment downtime or minor interruptions, establishes a baseline pace for production progress by distributing the total workload across the effective production time. Substituting the numerical values, the result is... The speed is measured in meters per minute. The deviation between output capacity and operating rhythm is compared, and the rated maximum linear speed of the production line is obtained by calling the equipment's inherent parameter library. meters per minute, verification Establishment is made to ensure the target speed is within the safe operating zone, and then the speed deviation is calculated. meters per minute, a proportional-integral-derivative (PID) control algorithm is introduced to generate the adjustment increment, and the proportional coefficient is set. Calculate the initial adjustment amount meters per minute, the adjusted target command value Converting meters per minute to the corresponding analog voltage signal, assuming the driver receives... Volt voltage corresponding Speed ​​in meters per minute, calculate control voltage Volts generate production speed control signals.

[0042] The packaging frequency adjustment submodule obtains the packaging line operation status and output data according to the carton production quota adjustment plan, calculates the packaging frequency based on the data, performs consistency verification and mapping instructions on the frequency results and operation status, and generates packaging frequency adjustment instructions. Analyze the specifications of this batch of cartons in the analysis plan and extract the cardboard cutting length. Rice and the number of bags stacked together The system acquires data on the packaging line's operating status and output, reads real-time encoder feedback values ​​from the backend automatic stacker and packing machine, and obtains the current conveyor belt speed of the packaging line. meters per minute and the cycle time of the packing machine Seconds, based on the data, calculate the packaging frequency using the formula. Calculate the back-end packaging frequency required to adapt the front-end production speed, where The unit is packets per minute. meters per minute This formula represents the total length of cardboard consumed per package. It establishes a flow balance between continuous corrugated cardboard production and subsequent discrete packaging operations. Substituting the values, we can calculate... Packets / minute. Perform consistency checks and mapping instructions on the frequency results and operating status. Refer to the packaging line operating parameter configuration table shown in Table 5, and calculate accordingly. Packets per minute, falling into the "medium speed mode" range, matching the corresponding conveyor belt set speed. meters per minute and packing machine compression waiting time Seconds to verify the current maximum processing capacity of the packing machine. Packets / minute, confirm To meet equipment performance constraints, the target frequency is... The instruction to convert packets / minute to the pulse frequency of the PLC controller is used, and the pulse equivalent is set to... Pulse / packet, calculate transmission frequency Hertz, generates packaging frequency adjustment instructions.

[0043] Table 5: Packaging Line Operating Parameter Configuration Table As shown in Table 5, the packaging line operation is divided into three discrete intervals based on the demand frequency calculated at the front end. Specific parameters for conveyor belt speed, equipment action delay, and underlying servo control frequency are provided to ensure dynamic matching between back-end packaging capacity and front-end output rate. The deviation detection and calculation submodule, based on the packaging frequency adjustment command and production speed control signal, obtains actual and expected output data, performs difference calculation and identifies the direction of the difference, compares it with the preset deviation threshold item by item, triggers production parameter correction for differences exceeding the threshold, and generates the carton production management execution status result. The actual and expected output data are acquired through the feedback bus of the photoelectric counting sensor and servo driver installed at the end of the production line, and the sampling period is set. Minutes, at the end of the current cycle, read the actual number of carton lengths produced. meters, while based on the previously set target speed Calculate the expected theoretical output per meter per minute within this cycle. Meters, perform difference calculation and identify the direction of the difference, using the formula Calculate the cycle production deviation, substitute the values ​​to obtain The meter, marked as "overproduction," is compared item by item with a preset deviation threshold. This threshold is based on the original production quota data recorded in the carton production quota adjustment plan and the actual output data within the corresponding period. The system database is then retrieved from the original records of the last 50 similar production scheduling periods to calculate the standard deviation of the original deviation values. Meters, according to a unified statistical period, undergo deviation interval statistical processing, and are applied... The rule sets a normal fluctuation range and obtains the maximum permissible deviation value of the stable operating range. Meters, and using the maximum permissible deviation value as the preset deviation threshold, the current absolute value of the deviation. meters, and threshold The meters were compared to determine the result. This falls within the allowable range of system random error and does not require triggering correction logic. If we assume the actual output... Meters, then the deviation Meters, absolute value At this point, if the difference exceeds the threshold, production parameter correction will be triggered, and a negative feedback coefficient will be automatically generated. Revise the speed command for the next cycle and generate the execution status results for carton production management.

[0044] Please see Figure 8 The intelligent production management method for cardboard boxes is implemented based on the aforementioned intelligent production management system for cardboard boxes, and includes the following steps: S1: Monitor the change in the cutting machine's blade speed to obtain the instantaneous value of the blade speed, detect the cardboard thickness parameter, and timestamp and synchronize the blade speed value and thickness value. Eliminate noise in the collected data through filtering and construct a carton production status dataset. S2: Call the carton production status dataset, extract the knife speed change rate and board thickness change rate as feature vectors, use the support vector machine regression model to train the nonlinear mapping relationship, calculate the ratio of the predicted output of finished carton to the consumption of raw paper, and generate the carton production efficiency coefficient. S3: Call the carton production efficiency coefficient, use the sliding window algorithm to perform weighted average calculation, mark the production status according to the preset efficiency threshold, and establish an inventory adjustment strategy index corresponding to the current production status. S4: Call the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compare and analyze it with the current finished carton inventory, increase production when the inventory is lower than the strategy requirement, and reduce production when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan. S5: Based on the carton production quota adjustment plan, send production speed control signals and packaging frequency adjustment instructions. Calculate the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, trigger parameter correction and generate the carton production management execution status result.

[0045] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent production management system for cardboard boxes, characterized in that, The system includes: The production line parameter acquisition module monitors the changes in the cutting machine's blade speed to obtain instantaneous blade speed values, detects cardboard thickness parameters, timestamps and synchronizes the blade speed and thickness values, performs filtering processing on the blade speed and thickness values, and constructs a carton production status dataset. The capacity prediction and calculation module calls the carton production status dataset, extracts the knife speed change rate and board thickness change rate as feature vectors, uses a support vector machine regression model to train the nonlinear mapping relationship, calculates the ratio of the predicted output of finished carton to the consumption of raw paper, and generates the carton production efficiency coefficient. The inventory demand analysis module calls the carton production efficiency coefficient, uses a sliding window algorithm to perform weighted average calculation, marks the production status according to the preset efficiency threshold, and generates an inventory adjustment strategy index corresponding to the current production status. The quota dynamic adjustment module calls the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compares and analyzes it with the current finished carton inventory, and obtains an increase production instruction when the inventory is lower than the strategy requirement and a decrease production instruction when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan.

2. The intelligent production management system for cardboard boxes according to claim 1, characterized in that, The carton production status dataset includes equipment operation stability indicators, production cycle consistency indicators, abnormal working condition classification identifiers, and production time period characteristic information. The carton production efficiency coefficient includes unit paper output rate, capacity utilization rate, and efficiency change trend value. The inventory adjustment strategy index corresponding to the current production status includes inventory safety level, production adjustment response type, and adjustment decision weight coefficient. The carton production quota adjustment scheme includes target output setting value, capacity allocation ratio coefficient, and output adjustment range level.

3. The intelligent production management system for cardboard boxes according to claim 1, characterized in that, The production line parameter acquisition module includes: The speed acquisition submodule monitors the changes in the cutting machine tool speed to obtain instantaneous sampled values ​​of the tool speed, acquires the pulse time sequence output by the speed sensor, records the corresponding time of the sampling clock, performs first-order difference operation based on the time difference of adjacent pulses and performs pulse timing alignment processing to generate the instantaneous speed value of the tool. The thickness acquisition submodule detects the paperboard thickness parameters, acquires the displacement electrical signal sequence output by the thickness detection device, converts it into a thickness value according to the calibration relationship, organizes it in sequence according to the acquisition time information, filters abnormal jump data according to the thickness change range, and generates the paperboard thickness measurement value. The time-series fusion submodule, based on the paperboard thickness measurement value and the instantaneous speed value of the cutter, calculates the time offset according to the acquisition time information of the two types of data, performs item-by-item alignment on the speed sequence and thickness sequence, performs filtering processing, and combines them in time order to establish a carton production status dataset.

4. The intelligent production management system for cardboard boxes according to claim 3, characterized in that, The capacity forecasting calculation module includes: The production status acquisition submodule acquires the carton production status dataset, performs sequential verification on the instantaneous speed value of the cutter and the measured value of the cardboard thickness based on the recorded time identifier information, determines the continuous status based on the time interval between adjacent records, rearranges the order, and generates a production status time series data sequence. The feature vector construction submodule performs differential calculation on the instantaneous speed values ​​of the cutter corresponding to adjacent time markers based on the production state time sequence and calculates the cutter speed change rate by combining the time interval. It also calculates the board thickness change rate based on the paperboard thickness measurement value and combines them according to a unified time index to generate a capacity prediction feature vector. The efficiency coefficient generation submodule calls the capacity prediction feature vector, maps the feature vector to the feature space and constructs a regression constraint relationship, determines the support vector set based on the sample distance and solves the regression function, obtains the predicted value sequence and calculates the ratio with the raw paper consumption item by item to generate the carton production efficiency coefficient. The amount of raw paper consumed is determined by the production volume of cardboard boxes, the thickness and size of the paper used in each cardboard box.

5. The intelligent production management system for cardboard boxes according to claim 4, characterized in that, The inventory demand analysis module includes: The efficiency data processing submodule obtains the time series of the carton production efficiency coefficient, verifies the data continuity based on the time index, removes missing items, divides the data into segments according to the window length, performs weighted and normalized processing, updates the data step by step with the window, and generates a weighted production efficiency value. The status determination and labeling submodule, based on the weighted production efficiency value, calls a preset set of efficiency threshold intervals, compares the efficiency values ​​with the interval boundaries one by one, determines the interval label according to the result, maps the label to a status code and binds it to a time index, and generates a production status identifier value. The inventory strategy mapping submodule calls the production status identifier value, performs key-value matching in the inventory adjustment rule table according to the status code, extracts the inventory adjustment parameters, performs consistency verification and combines them for association, and establishes the inventory adjustment strategy index corresponding to the current production status.

6. The intelligent production management system for cardboard boxes according to claim 5, characterized in that, The quota dynamic adjustment module includes: The strategy matching submodule calls the inventory adjustment strategy index corresponding to the current production status, collects the current production status identifier and receives the strategy table index field, performs comparison and verification based on the status identifier and index field, decomposes and verifies the target inventory and fluctuation range parameters, and generates the inventory control benchmark quantity. The inventory deviation calculation submodule obtains the current inventory of finished cartons based on the inventory control benchmark quantity and performs inventory measurement verification. It calculates the difference between the measured inventory value and the inventory control benchmark quantity and identifies the deviation direction. Based on the fluctuation range parameter, it determines the range of the difference and obtains the inventory deviation value. The quota adjustment generation submodule, based on the inventory deviation value, calls the corresponding quota correction rule parameters in the inventory adjustment strategy, performs proportional mapping and numerical conversion for the current production quota, performs boundary condition verification and discretization processing on the conversion result, and generates a carton production quota adjustment scheme.

7. The intelligent production management system for cardboard boxes according to claim 1, characterized in that, The system also includes: The execution control feedback module sends production speed control signals and packaging frequency adjustment instructions according to the carton production quota adjustment scheme. It calculates the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, it triggers parameter correction and generates the carton production management execution status result. The execution status results of the carton production management include the execution achievement rate index, the output deviation classification results, and the system operation effectiveness evaluation indicator.

8. The intelligent production management system for cardboard boxes according to claim 7, characterized in that, The execution control feedback module includes: The production speed control submodule obtains production quota data and receives equipment status parameters according to the carton production quota adjustment scheme, performs production cycle alignment calculation based on the data, compares the deviation between output capacity and operating rhythm, and generates a production speed control signal. The packaging frequency adjustment submodule obtains the packaging line operation status and output data according to the carton production quota adjustment plan, calculates the packaging frequency based on the data, performs consistency verification and mapping instructions on the frequency results and operation status, and generates packaging frequency adjustment instructions. The deviation detection and calculation submodule, based on the packaging frequency adjustment command and production speed control signal, obtains actual and expected output data, performs difference calculation and identifies the direction of the difference, compares it item by item with the preset deviation threshold, triggers production parameter correction for differences exceeding the threshold, and generates the carton production management execution status result.

9. The intelligent production management system for cardboard boxes according to claim 8, characterized in that, The preset deviation threshold is based on the original production quota data recorded in the carton production quota adjustment scheme and the actual output data in the corresponding period. The deviation interval is statistically processed according to a unified statistical period to obtain the maximum allowable deviation value of the stable operating interval, and the maximum allowable deviation value is used as the preset deviation threshold.

10. A method for intelligent production management of cardboard boxes, characterized in that, The intelligent production management system for cardboard boxes according to any one of claims 1-9 includes the following steps: S1: Monitor the change in the cutting machine's blade speed to obtain the instantaneous value of the blade speed, detect the paperboard thickness parameter, timestamp and synchronize the blade speed value and thickness value, perform filtering processing on the blade speed value and thickness value, and construct a carton production status dataset. S2: Call the carton production status dataset, extract the knife speed change rate and board thickness change rate as feature vectors, use a support vector machine regression model to train the nonlinear mapping relationship, calculate the ratio of the predicted output of finished carton to the consumption of raw paper, and generate the carton production efficiency coefficient. S3: Call the carton production efficiency coefficient, use the sliding window algorithm to perform weighted average calculation, mark the production status according to the preset efficiency threshold, and generate the inventory adjustment strategy index corresponding to the current production status; S4: Call the inventory adjustment strategy in the inventory adjustment strategy index corresponding to the current production status, compare and analyze it with the current finished carton inventory, and obtain an increase production instruction when the inventory is lower than the strategy requirement, and obtain a decrease production instruction when it is higher than the strategy requirement, thus forming a carton production quota adjustment plan. S5: Send production speed control signals and packaging frequency adjustment instructions according to the carton production quota adjustment scheme. Calculate the difference between the actual output and the expected output of cartons through deviation detection. When the difference exceeds the preset deviation threshold, trigger parameter correction and generate the carton production management execution status result.

Images