Intelligent production scheduling data analysis method for platen paper production line

Abstract

The invention provides an intelligent production scheduling data analysis method for a platen paper production line, and the method comprises the steps: obtaining the fiber length distribution and the current screen mesh aperture size from a slurry pool, obtaining the real-time capacity level and the production speed of each workshop section from a storage bin monitoring device, and carrying out the data fusion, thereby obtaining an initial dynamic relation matrix; if the agglomeration density is higher than a preset risk threshold value, relevant subsets about the fiber flowing speed and the screen resistance are extracted from the dynamic relation matrix, the size of the screen hole diameter is adjusted through the fiber agglomeration density, meanwhile, the production speed is integrated, and the adjusted material passing rate is obtained; the material passing rate is compared with the current storage bin capacity level to obtain the capacity matching degree, whether the buffer storage space needs to be expanded or not is judged according to the capacity matching degree, and if the material passing rate exceeds the capacity level preset threshold value, the buffer space distribution proportion is increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and particularly relates to a method for intelligent production scheduling data analysis of a board paper production line. BACKGROUND

[0002] In the field of pulp and papermaking, the stability of paper quality is crucial for production efficiency and product competitiveness, especially in board paper production lines, the processing of fiber raw materials directly determines the thickness uniformity of finished paper and production continuity. However, the existing methods have obvious shortcomings in dealing with fiber agglomeration and production speed fluctuations. Many solutions rely too much on single equipment adjustment or fixed parameters, ignoring the dynamic relationship between fiber characteristics, equipment parameters and production rhythm, resulting in the inability to flexibly adapt to changes in different batches of raw materials or the material flow demand between multiple sections in the production line. This limitation makes it difficult for the production line to maintain stable material supply and uniform paper quality when facing complex working conditions. Specifically, fiber agglomeration is a core technical challenge that affects production stability. Agglomerates formed by fibers with different lengths in the pulp pool will be redistributed due to the adjustment of the screen mesh aperture of the screening equipment, thereby affecting the production speed of the subsequent sections. Although adjusting the screen mesh aperture can change the distribution of agglomerates, it introduces a new problem: the difficulty in matching the storage bin capacity and production speed. For example, when the operator adjusts the screen mesh aperture to reduce agglomerate blockage, too many short fibers may pass through, causing speed fluctuations in subsequent sections due to changes in material characteristics, and even causing storage bin overflow or empty bin phenomena. Such fluctuations not only disrupt the production rhythm, but also can cause unevenness in paper thickness. Therefore, how to analyze the dynamic relationship between the storage bin capacity, fiber length distribution, screen mesh aperture adjustment value and production speed of each section in real time, optimize the configuration of buffer storage space between sections, ensure continuous and stable material flow and maintain uniform thickness of finished paper, becomes a key problem. SUMMARY

[0003] The present application provides a method for intelligent production scheduling data analysis of a board paper production line, mainly including:

[0004] The fiber length distribution and screen mesh aperture data are obtained from the slurry pool, the capacity level and production speed of each section are obtained from the storage bin monitoring device, the data are fused to construct an initial dynamic relationship matrix; the fiber length is identified according to the initial dynamic relationship matrix, the fibers are classified into long fibers, medium fibers and short fibers, the proportion of long fibers is calculated, the ratio of fiber length to screen mesh aperture is obtained through weighted average processing, and the agglomeration density is determined; according to the agglomeration density, a subset of fiber flow speed and screen mesh resistance is extracted from the initial dynamic relationship matrix, the screen mesh aperture is adjusted, and the material passing rate is calculated in combination with the production speed; the material passing rate is compared with the storage bin capacity level, the capacity matching degree is calculated, and the buffer space allocation proportion is adjusted according to the capacity matching degree; the fiber passing speed fluctuation of each section after adjustment is extracted, the fiber length distribution is fused, and the moving average filtering algorithm is used for processing to obtain a smooth production speed; the flow stability is calculated by comparing the smooth production speed with the initial dynamic relationship matrix, the storage bin capacity requirement is adjusted according to the flow stability, and a target material flow parameter set is determined; the target material flow parameter set is used for paper thickness uniformity prediction, the adjusted screen mesh aperture and buffer space allocation proportion are fused, the thickness standard deviation and coefficient of variation are calculated, and production scheduling parameters are determined.

[0005] Further, the initial dynamic relationship matrix is constructed by fusing the data obtained from the slurry pool and the storage bin monitoring device, including:

[0006] Samples are collected from different positions of the slurry pool, fiber length is scanned, the proportions of long fibers, medium fibers and short fibers are counted, and screen mesh aperture values are read; capacity level data are obtained from the storage bin, a time stamp is marked, and a capacity change sequence is generated; production speeds are collected from the beating, screening and forming sections, and material transfer rates of adjacent sections are calculated; according to the fiber length distribution and screen mesh aperture values, a fiber passing rate vector is calculated, and the long fiber corresponding value in the fiber passing rate vector is adjusted; the initial dynamic relationship matrix is constructed by arranging the fiber passing rate vector, the material transfer rate and the capacity change sequence in time sequence as columns.

[0007] Further, the initial dynamic relationship matrix is constructed by fusing the data obtained from the slurry pool and the storage bin monitoring device, including:

[0008] extracting a fiber passing rate vector from the initial dynamic relationship matrix, identifying long fibers, medium fibers and short fibers; counting a proportion of the number of the long fibers, collecting long fiber concentrations at different positions of a pulp pool, performing weighted summation by depth to obtain a comprehensive long fiber proportion; calculating a ratio by dividing the comprehensive long fiber proportion by a screen mesh aperture value; extracting fiber passing rates at continuous time points, calculating a sum of absolute values of passing rate differences to determine an agglomeration fluctuation index; and calculating an agglomeration density according to the agglomeration fluctuation index, the ratio and a fiber suspension concentration.

[0009] Further, the fiber flow speed and the screen mesh resistance subset are extracted from the initial dynamic relationship matrix according to the agglomeration density, the screen mesh aperture is adjusted, the material passing rate is calculated in combination with the production speed, and the method comprises the following steps.

[0010] The material passing rate is calculated by multiplying the fiber mass flow rate by the screening section speed and dividing the fiber suspension concentration.

[0011] Further, the material passing rate is compared with the storage bin capacity level to calculate a capacity matching degree, and the buffer space allocation proportion is adjusted according to the capacity matching degree, and the method comprises the following steps.

[0012] The material inflow amount is calculated by multiplying the material passing rate by the screening section speed; the storage bin capacity occupancy rate is obtained; the ratio of the material inflow amount to the remaining capacity is calculated as the capacity matching degree; the difference value is calculated by comparing the capacity matching degree with a threshold value to determine a buffer space expansion demand coefficient; the additional buffer space demand amount is calculated by the buffer space expansion demand coefficient to determine the buffer space allocation proportion increment to adjust the allocation proportion.

[0013] Further, the fiber passing speed fluctuation of each section after adjustment is extracted, the fiber length distribution is fused, and a moving average filtering algorithm is used to process to obtain a smoothed production speed, and the method comprises the following steps.

[0014] The fiber passing speed difference value of each section is extracted to form a fluctuation sequence; the moving average filtering is used on the fluctuation sequence to calculate the average value in the window to obtain a smoothed fluctuation sequence; the comprehensive fluctuation index is calculated according to the weighted fusion of the smoothed fluctuation sequence and the fiber length distribution; the material flow trend is determined by the difference value of the comprehensive fluctuation index; the filter window size is adjusted to process the original production speed to obtain the smoothed production speed.

[0015] Further, the flow stability is calculated by comparing the smooth production speed with the initial dynamic relationship matrix, the storage bin capacity demand is adjusted according to the flow stability, and the target material flow parameter set is determined, including:

[0016] By point-by-point comparison of the smooth production speed and the material transfer rate, the speed difference standard deviation is calculated, the flow stability index is determined in combination with the capacity change sequence, the stability deviation is calculated by the difference between the flow stability index and the reference value, and the capacity adjustment coefficient is calculated according to the stability deviation and the fiber passing rate fluctuation amplitude; the storage bin capacity is adjusted by the capacity adjustment coefficient, the target production speed and the screen mesh size are determined, and the target material flow parameter set is constructed.

[0017] Further, the paper thickness uniformity prediction is performed on the target material flow parameter set, the adjusted screen mesh size and the buffer space allocation ratio are fused, the thickness standard deviation and the coefficient of variation are calculated, and the production scheduling parameter is determined, including:

[0018] The thickness mapping relationship is established by the target material flow parameter set, the paper thickness distribution is calculated, the thickness standard deviation and the coefficient of variation are calculated according to the paper thickness distribution, the production coordination coefficient is determined by fusing the buffer space ratio through the ratio of the thickness standard deviation and the adjusted screen mesh size, and the optimal production speed combination and the section coordination timing are determined by adjusting the speed of each section and calculating the material transfer time interval.

[0019] Further, the paper thickness uniformity prediction is performed on the target material flow parameter set, the adjusted screen mesh size and the buffer space allocation ratio are fused, the thickness standard deviation and the coefficient of variation are calculated, and the production scheduling parameter is determined, including:

[0020] The beating section and the forming section speed matching coefficient is calculated by the screen mesh size and the storage bin capacity in the target material flow parameter set in combination with the thickness coefficient of variation, the section coordination timing is determined by adjusting the material transfer time interval according to the speed matching coefficient, the buffer time is calculated by dividing the storage bin capacity by the material consumption rate, the screen adjustment frequency and the speed change period are determined by comparing the buffer time with the screen adjustment time, the section start sequence and the speed switching opportunity are set, and the production scheduling scheme is constructed.

[0021] The technical scheme provided by the embodiment of the application can include the following beneficial effects:

[0022] This invention discloses an intelligent scheduling data analysis method for a sheet metal production line. Addressing the problems of fiber agglomeration, unstable material flow, and low production efficiency during pulp preparation and paper forming, it constructs an initial dynamic relationship matrix through data fusion, identifies and classifies fiber lengths, calculates the ratio of long fibers to screen aperture, and determines agglomeration density. When the agglomeration density exceeds the standard, the screen aperture is dynamically adjusted and the production speed is optimized to improve material throughput. Further, through capacity matching analysis, the buffer storage space is expanded, and moving average filtering is used to smooth production speed fluctuations, predict material flow trends, and assess flow stability. If the stability deviation exceeds a threshold, the storage silo capacity requirement is recalculated, a target material flow parameter set is generated, paper thickness uniformity is predicted, and the coordination sequence and speed matching of work sections are optimized. Finally, an intelligent scheduling scheme including start-stop sequence and speed switching timing is formed. This invention achieves full-process optimization from fiber separation to paper forming by dynamically controlling screen aperture and production parameters, improving paper thickness uniformity and production efficiency, and reducing material waste and equipment wear. Attached Figure Description

[0023] Fig. 1 This is a flowchart of an intelligent scheduling data analysis method for a board paper production line according to the present invention.

[0024] Fig. 2 This is a schematic diagram of an intelligent scheduling data analysis method for a board paper production line according to the present invention. Detailed Implementation

[0025] To further understand the content of this invention, a detailed description of the invention is provided in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0026] like Figs. 1-2 This embodiment of an intelligent scheduling data analysis method for a board paper production line may specifically include:

[0027] S101. Obtain the fiber length distribution and current screen aperture size from the slurry tank, and simultaneously obtain the real-time capacity level and production speed of each section from the storage silo monitoring equipment. Perform data fusion to obtain the initial dynamic relationship matrix.

[0028] The pulp sample is collected from the sampling port at the bottom and middle of the pulp pool, the length value of each fiber in the sample is scanned by the image recognition function of the fiber analyzer, and the distribution data of the long fiber ratio, the medium fiber ratio and the short fiber ratio are obtained by statistics. At the same time, the current screen aperture value is read from the control panel of the screening equipment. The real-time capacity level data is obtained by the ultrasonic liquid level sensor built-in the storage bin, the current production speed value of each section is collected from the PLC controller of the beating section, the screening section and the forming section, the capacity level is time-stamped according to the collection time, and the capacity change sequence is obtained. According to the ratio relationship between the fiber length distribution and the screen aperture value, the probability value of the fiber of different length passing through the screen is calculated, the fiber passing rate vector is constructed, if the long fiber ratio exceeds the preset threshold value, the value of the corresponding position in the passing rate vector is adjusted according to the difference between the long fiber ratio and the threshold value, and the material transfer rate between adjacent sections is calculated by the difference between the production speeds of each section. The fiber passing rate vector is used as the first column of the matrix, the material transfer rate is used as the second column, and the capacity change sequence is used as the third column. The row vector is arranged in time sequence to form an initial dynamic relationship matrix containing fiber characteristics, equipment parameters and production rhythm.

[0029] In an embodiment, the fiber analyzer adopts a linear array CCD camera combined with an LED backlight source to constitute an image acquisition system, and the pulp sample is fixed on the detection area by a glass slide. The image recognition function identifies the outline of a single fiber through an edge detection algorithm, and measures the straight-line distance between the two endpoints of the fiber as the fiber length value. Fibers longer than 5 mm are classified as long fibers, fibers between 3 and 5 mm are classified as medium fibers, and fibers shorter than 3 mm are classified as short fibers. The distribution data is obtained by counting the percentage of the number of each type of fiber in the total number of fibers.

[0030] It should be noted that the ultrasonic liquid level sensor is installed at the top of the storage bin, and the liquid level is calculated according to the time difference by emitting a 40 kHz ultrasonic pulse and receiving the reflected signal. The capacity change sequence refers to a data pair composed of the capacity level value at each collection time and the corresponding time stamp, arranged in chronological order to form a sequence.

[0031] Specifically, the construction process of the fiber passing rate vector is to calculate the ratio of fiber length to screen aperture. When the fiber length is less than 0.8 times the screen aperture, the passing probability is set to 0.95; when the fiber length is between 0.8 and 1.2 times the screen aperture, the passing probability decreases linearly from 0.95 to 0.1; when the fiber length is greater than 1.2 times the screen aperture, the passing probability is set to 0.1. The preset threshold value of the long fiber ratio is usually set to 35%, and when the actual ratio exceeds this value, the passing rate value at the corresponding position is reduced by 0.02 for every 1 percentage point.

[0032] In a possible implementation, the material transfer rate is calculated by the product of the production speed difference between adjacent sections and the pipe cross-sectional area. The transfer rate between the beating section and the screening section reflects the conveying capacity of the pulp, and the transfer rate between the screening section and the forming section reflects the supply speed of the qualified pulp.

[0033] Preferably, the initial dynamic relationship matrix is constructed in a time-aligned manner, and each row represents a snapshot of the system state at the same time. The columns of the matrix are arranged in the order of the fiber passing rate vector, the material transfer rate, and the capacity change sequence, forming a multi-dimensional data structure reflecting the running state of the system. This matrix structure can intuitively show the influence law of the change of fiber characteristics on the production process.

[0034] S102, identifying the fiber length according to the initial dynamic relationship matrix, classifying the fibers in the pulp pool according to the fiber length, the fiber classification including long fibers, medium fibers and short fibers, identifying the proportion of long fibers, and performing weighted average processing on the proportion of long fibers to obtain the ratio of fiber length to screen mesh aperture and determine the agglomeration density.

[0035] The numerical distribution of the fiber passing rate vector is extracted from the initial dynamic relationship matrix, the K-means clustering method is used to group the passing rate values, the number of clusters is set to three, and according to the center value of each group of passing rate values, long fibers correspond to the low passing rate group, medium fibers correspond to the medium passing rate group, and short fibers correspond to the high passing rate group. The number distribution of each type of fiber is obtained by counting the number of data points in each group. According to the number distribution, the percentage of the number of long fibers to the total number of fibers is calculated, the long fiber concentration data at the bottom, middle and upper parts of the pulp pool are collected, and the long fiber proportions at each position are weighted and summed according to the preset depth weight coefficient. The bottom weight is the largest, and the upper weight is the smallest, to obtain a comprehensive long fiber proportion value. The ratio of fiber length to screen mesh aperture is obtained by dividing the comprehensive long fiber proportion value by the current screen mesh aperture value. If the ratio exceeds the preset agglomeration risk threshold, the fiber passing rate values at five consecutive time points in the matrix are extracted, and the sum of the absolute values of the passing rate difference between adjacent time points is calculated as an agglomeration fluctuation index. According to the agglomeration fluctuation index multiplied by the ratio of fiber length to screen mesh aperture, and then multiplied by the fiber suspension concentration in the pulp pool, the agglomeration degree value of the fiber in unit volume is obtained. The agglomeration degree value is compared with the preset critical density threshold value, and if the agglomeration degree is higher than the critical density threshold value, the agglomeration degree value is defined as the agglomeration density, and the agglomeration density value is determined.

[0036] In one embodiment, the implementation process of the K-means clustering method starts from the fiber passing rate vector of the initial dynamic relationship matrix. The passing rate value corresponding to each time point in the matrix reflects the probability of different length fibers passing through the screen mesh, and the passing rate is distributed between 0.1 and 0.95. The clustering algorithm first randomly selects three initial clustering centers, respectively corresponding to the passing rate values of 0.15, 0.5 and 0.85. In the iteration process, the algorithm calculates the Euclidean distance of each passing rate value to the three clustering centers, and assigns the value to the nearest clustering group. The average value of each group is recalculated as the new clustering center after each iteration, until the change of the clustering center is less than 0.01 or the number of iterations reaches 100. Among the three clustering groups formed, the group with the smallest center value corresponds to long fibers, because long fibers are difficult to pass through the screen mesh; the group with the middle center value corresponds to medium fibers; and the group with the largest center value corresponds to short fibers, which are easy to pass through the screen mesh. The number of data points contained in each clustering group is counted, and the proportion of each type of fiber is obtained by dividing the total number of data points.

[0037] It should be noted that the multi-position sampling of the slurry pool reflects the distribution characteristics of the fibers in the vertical direction. Because long fibers have a larger density and are prone to sedimentation, the concentration of long fibers at the bottom of the pool is usually higher than that at the upper part. The sampling positions are set at a height of 0.5 meters, 2 meters and 3.5 meters from the bottom of the pool, representing the bottom, middle and upper parts respectively.

[0038] Specifically, the setting of the depth weight coefficient is based on the fiber sedimentation theory and actual production experience. The bottom weight is set to 0.5 because the fiber concentration in this area best reflects the composition of the fibers actually entering the screening device; the middle weight is 0.3, reflecting the fiber state in the transition area; and the upper weight is 0.2, representing the distribution of fibers in the suspended state. The calculation process of weighted summation is to multiply the long fiber proportion at each of the three positions by the corresponding weight, and then add them to obtain the comprehensive value.

[0039] In one possible implementation, the calculation of the ratio of fiber length to screen mesh aperture involves the determination of the average length of the fibers. According to the clustering results, the average length of long fibers is taken as 6 millimeters, that of medium fibers as 4 millimeters, and that of short fibers as 2 millimeters. The weighted average fiber length is obtained by multiplying the long fiber proportion value by 6 millimeters, the medium fiber proportion value by 4 millimeters, and the short fiber proportion value by 2 millimeters, and then adding them together. The length is divided by the screen mesh aperture value to obtain the ratio.

[0040] Preferably, the agglomeration risk threshold is set to 1.5, and when the ratio exceeds this value, it indicates that the fiber length is too large relative to the screen mesh aperture, and agglomeration is likely to occur. The calculation of the agglomeration fluctuation index selects five consecutive time points with a time interval of 30 seconds. The difference between the passing rates of adjacent time points reflects the instability of fiber passing, and the larger the absolute value of the difference, the more serious the agglomeration phenomenon. The absolute values of the four differences obtained from the five time points are added to obtain the agglomeration fluctuation index.

[0041] Exemplarily, the calculation of the aggregation degree value integrates three key parameters. The agglomeration fluctuation index reflects the instability in time dimension, the ratio of fiber length to screen mesh aperture reflects the blocking tendency in space dimension, and the fiber suspension concentration reflects the material density. The product of the three values represents the degree of fiber entanglement and aggregation in unit volume. When the fiber suspension concentration is 15 grams per liter, the agglomeration fluctuation index is 0.8, and the ratio is 1.8, the aggregation degree value is 21.6.

[0042] It can be understood that the setting of the critical density threshold needs to consider the processing capacity of the production line and the quality requirements of the product. If the threshold is too low, it will cause frequent alarms and unnecessary adjustments, and if the threshold is too high, it may miss the early warning of the agglomeration risk. Through statistical analysis of historical production data, when the aggregation degree value exceeds 20, the probability of blockage in the subsequent section significantly increases.

[0043] In an embodiment, the final determination of the agglomeration density also takes into account the influence of temperature factor. The increase of pulp temperature will reduce the friction coefficient between fibers and reduce the agglomeration tendency. When the pulp temperature is higher than 40 degrees Celsius, the aggregation degree value is multiplied by a temperature correction coefficient of 0.9; when it is lower than 30 degrees Celsius, it is multiplied by a correction coefficient of 1.1; and when it is between the two, a linear interpolation is used. The corrected value is used as the final agglomeration density, providing a quantitative basis for subsequent screen adjustment and production speed control. Further, the application of the agglomeration density value can guide the optimization adjustment of the production process. When the agglomeration density exceeds the critical value, the screening equipment automatically increases the screen vibration frequency or adjusts the screen inclination angle to break the fiber agglomerates that have been formed. At the same time, a dispersing agent is injected into the pulp pool to reduce the adhesion between fibers, fundamentally reducing the probability of agglomeration.

[0044] S103, if the agglomeration density is higher than the preset risk threshold, extract the relevant subset about the fiber flow speed and the screen resistance from the dynamic relationship matrix, and adjust the screen aperture size through the fiber agglomeration density, while integrating the production speed to obtain the adjusted material passing rate.

[0045] If the agglomeration density is higher than the preset risk threshold, the row index of the fiber passing rate vector less than the preset passing rate threshold is located from the dynamic relationship matrix, the material transfer rate data corresponding to the row index is extracted as the fiber flow speed, the reciprocal of the passing rate change amount of adjacent time points is calculated as the screen resistance coefficient, and a relevant subset containing the flow speed and the resistance coefficient is constructed. According to the mean value of the screen resistance coefficient in the relevant subset, the difference between the agglomeration density and the preset risk threshold is calculated, the difference is multiplied by a preset aperture adjustment coefficient to obtain a screen aperture adjustment amount, and the original screen aperture is added to the adjustment amount to obtain a target screen aperture value. The ratio of the target screen aperture value to the original aperture value is used to adjust the production speed of each section, the beating section speed is divided by the ratio to obtain a new beating speed, the screening section speed is multiplied by the ratio to obtain a new screening speed, and the forming section speed is adjusted according to the material balance principle to obtain an adjusted production speed combination. The product of the screening section speed in the adjusted production speed combination and the target screen aperture value is divided by the fiber suspension concentration in the slurry pool to calculate the fiber mass flow rate passing through the screen per unit time, and the ratio of the fiber mass flow rate to the total mass flow rate of the input slurry is determined as the adjusted material passing rate. Whether the adjusted material passing rate is lower than the preset minimum passing rate threshold is judged, and if it is lower, the screen vibration frequency is increased, and the increase amount of the vibration frequency is proportional to the deviation of the material passing rate. The material passing rate is recalculated under the new vibration condition.

[0046] In an embodiment, the construction process of the relevant subset starts from data screening of the dynamic relationship matrix. When the agglomeration density exceeds the risk threshold, the fiber passing rate values of all time points in the matrix are automatically scanned. The preset passing rate threshold is usually set to 0.3, and a value lower than this indicates that the fiber passing is severely blocked. All rows with a passing rate lower than 0.3 are identified, and the material transfer rate data corresponding to these rows is extracted. The material transfer rate reflects the actual flow speed of the fiber in the pipeline, with a unit of meters per second. The calculation of the screen resistance coefficient is based on the change characteristics of the passing rate of adjacent time points. When the passing rate decreases from 0.4 to 0.2, the change amount is 0.2, and its reciprocal 5 is taken as the resistance coefficient. The larger the resistance coefficient, the stronger the hindering effect of the screen on the fiber flow.

[0047] It should be noted that the calculation of the mean value of the screen resistance coefficient uses a sliding window method, and the window size is 10 consecutive time points. This method can smooth short-term fluctuations and reflect the overall trend of screen resistance. The difference between the agglomeration density and the risk threshold directly reflects the urgency of the current production state, and the larger the difference, the more serious the agglomeration problem, which requires a larger adjustment.

[0048] Specifically, the aperture adjustment coefficient is an empirical value based on historical production data. When the agglomeration density exceeds the risk threshold by 1 unit, the screen aperture needs to be increased by 0.1 mm; when it exceeds 2 units, it needs to be increased by 0.25 mm; when it exceeds 3 units or more, the increase is increased in a logarithmic relationship to avoid excessive adjustment causing a large amount of short fibers to be lost. The determination of the target screen aperture value also needs to consider the physical limitations of the equipment. The screen aperture cannot exceed the maximum value allowed by the equipment, which is usually 8 mm.

[0049] Preferably, the adjustment of the production speed combination follows the principle of mass conservation. The beating section as the source section, its speed adjustment directly affects the subsequent material supply. When the screen aperture is increased, the fiber passing resistance is reduced, and the screening section processing capacity is improved, so the screening speed is proportional to the aperture ratio. The beating section speed needs to be reduced accordingly to avoid a large amount of material accumulation before the screening section. The speed adjustment of the forming section is more complex and needs to be dynamically adjusted according to the actual amount of qualified pulp received to maintain the storage tank liquid level within a safe range.

[0050] In one possible implementation, the specific implementation of the material balance principle is realized through the mass flow conservation equation. The total mass flow of the input pulp is equal to the beating section speed multiplied by the pulp density and the pipe cross-sectional area. The fiber mass flow passing through the screen is determined by the screening section speed, the target screen aperture, and the fiber suspension concentration. The fiber suspension concentration usually fluctuates between 10 to 20 grams per liter. The higher the concentration, the more fiber content in the unit volume of pulp, and the greater the fiber mass flow passing through the same aperture screen. The adjusted material passing rate is defined as the ratio of the actual passing fiber mass flow to the total input mass flow, which directly reflects the screening efficiency.

[0051] Illustratively, when the material passing rate is lower than the preset minimum passing rate threshold of 0.4, it indicates that even if the screen aperture is adjusted, the fiber passing is still difficult. At this time, the vibration frequency adjustment mechanism is started, and vibration can break the entanglement between fibers and improve the passing efficiency. The increase amount of vibration frequency is calculated by multiplying the deviation of material passing rate from the minimum threshold by the frequency adjustment coefficient, which is usually 100 hertz per unit deviation.

[0052] It can be understood that the vibration frequency cannot be increased unlimitedly, and too high vibration frequency will cause the screen fatigue damage. The upper limit of the vibration frequency of the industrial screening equipment is usually 50 Hz. When the frequency upper limit is reached, the system further improves the vibration effect by increasing the amplitude. The amplitude is increased from the standard 2 mm to 4 mm, which can increase the material passing rate by 15% to 20%. Further, the recalculation of the material passing rate under the new vibration condition considers the promotion of vibration to the fiber dispersion. Vibration makes the fiber agglomerates loose, reduces the actual fiber aggregation size, and increases the effective passing area of the screen. The vibration effect coefficient is introduced in the calculation formula, which is proportional to the product of the vibration frequency and the amplitude, and the typical value is between 1.2 and 1.5.

[0053] For example, in actual production, when it is detected that the agglomeration density rises from 20 to 25, exceeding the risk threshold 22, the system automatically performs the adjustment program. First, the average resistance coefficient is extracted as 4.5, and the screen aperture needs to be increased by 0.3 mm. The original aperture is 5 mm, which is adjusted to 5.3 mm, and the aperture ratio is 1.06. The beating section speed is reduced from 100 liters per minute to 94 liters per minute, and the screening section speed is increased from 80 liters per minute to 85 liters per minute. After adjustment, the material passing rate is increased from 0.35 to 0.45, meeting the normal production requirements.

[0054] S104, compare the material passing rate with the current storage capacity level to obtain a capacity matching degree, and determine whether the buffer storage space needs to be expanded according to the capacity matching degree. If the material passing rate exceeds the preset threshold of the capacity level, the buffer space allocation ratio is increased.

[0055] The adjusted material passing rate value and the current capacity level percentage of the storage bin are obtained, the material passing rate is multiplied by the previously adjusted screening section production speed to obtain the material inflow amount per unit time, the real-time capacity occupancy rate is read from the storage bin liquid level sensor, and the ratio of the material inflow amount to the remaining capacity of the storage bin is calculated as the capacity matching degree. According to the comparison between the capacity matching degree and the preset capacity matching degree threshold, the capacity matching degree threshold is set as the critical value for safe operation of the storage bin. If the capacity matching degree is greater than the threshold, the buffer space expansion requirement coefficient is determined by subtracting the difference between the capacity matching degree and the threshold. The additional buffer space requirement amount is obtained by multiplying the buffer space expansion requirement coefficient by the current storage capacity. If the material passing rate exceeds the preset threshold of the capacity level, the additional buffer space requirement amount is increased by a preset percentage as the emergency buffer amount. The buffer space allocation ratio increment is obtained by dividing the sum of the additional buffer space requirement amount and the emergency buffer amount by the current storage capacity. The increased buffer space allocation ratio is determined by adding the increment to the original buffer space allocation ratio.

[0056] In one embodiment, the calculation of the capacity matching degree is based on real-time monitoring data and dynamic flow analysis. The material inflow is measured by a flow meter at the outlet of the screening section, which uses electromagnetic induction principle to accurately measure the volume flow of fiber-containing slurry. When the material passing rate is 0.5 and the production speed of the screening section is 85 liters per minute, the material inflow is 42.5 liters per minute. The remaining capacity of the storage bin is obtained by subtracting the current capacity occupancy from the total capacity. If the total capacity of the storage bin is 5000 liters and the current capacity occupancy is 70%, the remaining capacity is 1500 liters. The capacity matching degree is 42.5 liters per minute divided by 1500 liters, which is about 0.028 per minute.

[0057] It should be noted that the setting of the capacity matching degree threshold takes into account the production continuity and safety margin. The threshold is usually set to 0.02 per minute, which means that the remaining capacity can support at least 50 minutes of continuous production. When the capacity matching degree exceeds this threshold, it indicates that the storage bin will reach full capacity in a short time.

[0058] Specifically, the buffer space expansion demand coefficient reflects the deviation of actual demand from the safety standard. When the capacity matching degree is 0.028 and the threshold is 0.02, the difference 0.008 represents a 0.8% increase in capacity pressure per minute. This coefficient multiplied by the current storage bin capacity of 5000 liters gives an additional buffer space demand of 400 liters. This means that an additional buffer capacity of 400 liters needs to be added to maintain safe operation.

[0059] Preferably, the setting of the emergency buffer amount adopts a hierarchical response mechanism. When the material passing rate exceeds the capacity level preset threshold of 0.6, the system determines that it is in a high flow state and additional emergency buffer is needed. The preset percentage is usually 20%, so the additional demand of 400 liters increases by 20% to 480 liters.

[0060] In one possible implementation, the adjustment of the buffer space allocation ratio is realized by gradual increments. The original buffer space allocation ratio is assumed to be 30%, and the additional 480 liters divided by 5000 liters gives an increment of 9.6%, and the final buffer space allocation ratio is adjusted to 39.6%. This gradual adjustment avoids sharp fluctuations in the system and ensures smooth transition of production. In practical applications, the example is delivered to the storage bin control system, which automatically adjusts the feed valve opening and discharge speed to realize dynamic management of the buffer space.

[0061] S105, extract the fiber passing speed fluctuation of each section after increasing the buffer space allocation ratio, filter and smooth the fiber passing speed fluctuation of each section, and fuse the fiber length distribution to predict the material flow trend, and obtain the smoothed production speed by moving average filtering algorithm.

[0062] The absolute value of the speed difference value of each section at adjacent time points is calculated as the speed fluctuation value, and the speed fluctuation values are arranged in time sequence to form a fluctuation sequence, and the fiber passing speed fluctuation data set of each section is obtained. For each fluctuation sequence in the fiber passing speed fluctuation data set, a moving average filtering algorithm with a preset time window is used to calculate the arithmetic mean value of the fluctuation values in the window to replace the center point value, and the sliding window is moved point by point to complete the filtering processing, and the smoothed fluctuation sequence is obtained. According to the smoothed fluctuation sequence and the fiber length distribution, the long fiber proportion is multiplied by the beating section fluctuation value, the medium fiber proportion is multiplied by the screening section fluctuation value, and the short fiber proportion is multiplied by the forming section fluctuation value, and the weighted fluctuation values are summed to obtain a comprehensive fluctuation index. By calculating the difference value of the comprehensive fluctuation index at consecutive time points, the time sequence change rate is obtained. If the change rate is positive, the material flow shows an accelerating trend, and if it is negative, it shows a decelerating trend. According to the absolute value of the change rate, the material flow trend value of the next time period is predicted. The moving average filtering window size is adjusted using the material flow trend value. When the trend is accelerating, the window is reduced to the original window multiplied by a preset reduction factor. When the trend is decelerating, the window is expanded to the original window multiplied by a preset expansion factor. The adjusted window is used for moving average filtering of the original production speed data of each section to obtain the smoothed production speed of each section.

[0063] In one embodiment, the extraction process of fiber passing speed fluctuation starts from the system state after buffer space adjustment. When the buffer space allocation ratio increases from 30% to 39.6%, the operating characteristics of each section will change. The fiber passing speed of the beating section fluctuates from 94 liters per minute to 96 liters per minute, the screening section fluctuates from 85 liters per minute to 88 liters per minute, and the forming section fluctuates from 78 liters per minute to 82 liters per minute. The calculation of the speed fluctuation value uses the difference method of adjacent sampling points, and the sampling interval is set to 10 seconds. If the speed of the beating section at the first time point is 94 liters per minute and the speed at the second time point is 95.5 liters per minute, then the speed fluctuation value is 1.5 liters per minute. These fluctuation values are arranged in time sequence to form a fluctuation sequence that reflects the dynamic characteristics of each section.

[0064] It should be noted that the window size of the moving average filtering algorithm directly affects the smoothing effect. The initial window size is usually set to 5 data points, corresponding to a time span of 50 seconds. In the filtering process, the average value of the 5 fluctuation values in the window is obtained by adding them together and dividing by 5, which replaces the original value of the center point. The window slides one data point at a time, and the entire sequence is traversed.

[0065] Specifically, the weighted fusion of fiber length distribution and fluctuation sequence reflects the influence of different fiber types on each section. Long fibers mainly affect the beating section, because long fibers need more mechanical action to disperse during the beating process; medium fibers mainly affect the screening section, and the matching relationship between their length and screen mesh aperture determines the screening efficiency; short fibers mainly affect the forming section, and the uniform distribution of short fibers is directly related to the consistency of paper thickness. Assuming that the proportion of long fibers is 40%, the proportion of medium fibers is 35%, and the proportion of short fibers is 25%, the smooth fluctuation value of the beating section is 1.2, the screening section is 0.8, and the forming section is 0.5, then the comprehensive fluctuation index is 0.4 x 1.2 + 0.35 x 0.8 + 0.25 x 0.5 = 0.885.

[0066] Preferably, the prediction of material flow trend is based on the time evolution characteristics of the comprehensive fluctuation index. The comprehensive fluctuation index is continuously calculated at 10 time points, and if the index value gradually increases from 0.885 to 1.05, it indicates that the system fluctuation is increasing. The change rate of time series is calculated by the index difference of adjacent two time points, and the positive change rate indicates that the fluctuation is intensified, and the material flow presents an accelerating trend; the negative change rate indicates that the fluctuation is weakened, and the material flow tends to be stable. The absolute value of the change rate reflects the degree of change in the trend, and the larger the absolute value, the faster the system state changes.

[0067] In one possible implementation, the dynamic adjustment mechanism of the moving average filter window automatically responds to the predicted flow trend. When an accelerating trend is detected, the system determines that a faster response speed is needed, and therefore the filter window is reduced. The preset reduction coefficient is usually 0.6, and the original window of 5 data points is reduced to 3 data points. A smaller window can track speed changes faster, but the smoothing effect will be reduced. Conversely, when a decelerating trend is detected, the system determines that a larger delay can be accepted to obtain a better smoothing effect, and the preset expansion coefficient is 1.5, and the window is expanded to 7 or 8 data points.

[0068] Illustratively, the adjusted filter processing is applied to the original production speed data of each section. The original production speed refers to the real-time collected data without any processing, which contains all the noise and disturbances. Using the adjusted window to filter these original data can effectively suppress noise while maintaining system responsiveness. The beating section uses a 3-point window to obtain a fast-response smoothed speed, the screening section uses a 5-point standard window, and the forming section uses a 7-point large window to obtain a highly smoothed speed curve.

[0069] It can be understood that the smoothed production speed of each section constitutes a set of coordinated control parameters. This set of parameters reflects the stable running speed that each section should maintain under the current fiber distribution and agglomeration state. The smoothed speed of the beating section is stabilized at 95 liters per minute, the screening section is stabilized at 86 liters per minute, and the forming section is stabilized at 80 liters per minute. Further, the smoothed production speed also needs to consider the material balance relationship between sections. The output of the beating section must match the processing capacity of the screening section, and the qualified pulp output of the screening section must meet the demand of the forming section. The smoothed speed obtained by moving average filtering eliminates the interference of short-term fluctuations, enables each section to run coordinately at a stable speed, and avoids the phenomenon of material backlog or flow interruption caused by speed fluctuations.

[0070] S106, by comparing the smoothed production speed with the dynamic relationship matrix, the flow stability is evaluated, if the material flow stability deviation is not less than the preset deviation threshold, the storage bin capacity demand is recalculated according to the stability deviation value, and the target material flow parameter set is obtained.

[0071] By comparing the smoothed production speed of each section with the material transfer rate at the corresponding time point in the dynamic relationship matrix point by point, the speed difference value at each time point is calculated, the standard deviation of the speed difference value sequence is calculated, and the standard deviation is multiplied by the ratio of the difference between the maximum value and the minimum value of the capacity change sequence in the matrix to obtain the flow stability index. According to the difference between the flow stability index and the preset stability reference value, the stability deviation value is obtained, if the stability deviation value is not less than the preset deviation threshold, it is determined that the material flow is unstable, and the difference between the maximum value and the minimum value of the fiber passing rate in the time period corresponding to the deviation value in the dynamic relationship matrix is extracted as the fluctuation amplitude. The product of the fluctuation amplitude and the stability deviation value is divided by the current storage bin capacity occupancy rate to obtain the capacity adjustment coefficient, and the original storage bin capacity is multiplied by the capacity adjustment coefficient and then multiplied by the preset expansion coefficient to obtain the target storage bin capacity demand. According to the target storage bin capacity demand divided by the material consumption per unit time, the target production speed is obtained, and the calculation formula can be:

[0072]

[0073] , V t represents the target production speed, C s represents the target storage bin capacity demand, R c represents the material consumption per unit time; the target production speed is divided by the weighted sum value of the fiber length corresponding to the long fiber proportion, the medium fiber proportion and the short fiber proportion respectively to determine the adjusted screen aperture, wherein

[0074] L w =P l ·L l +Pm • L m + P s • L s

[0075] , L w represents the fiber length weighted sum value, P l represents the long fiber proportion, L l represents the fiber length corresponding to the long fiber, P m represents the medium fiber proportion, L m represents the fiber length corresponding to the medium fiber, P s represents the short fiber proportion, L s represents the fiber length corresponding to the short fiber; the adjusted screen aperture Da = Vt / Lw. By integrating the adjusted screen aperture, the target production speed and the target storage bin capacity requirement, a target material flow parameter set is constructed, the adjusted screen aperture as the screening control parameter, the target production speed as the section coordination parameter, and the target storage bin capacity requirement as the buffer configuration parameter.

[0076] In an embodiment, the flow stability evaluation process is based on the accurate comparison between the smoothed production speed and the dynamic relationship matrix. The smoothed production speed represents the stable running state after filtering processing, and the material transfer rate in the dynamic relationship matrix reflects the actual material flow situation. The point-by-point comparison implementation is to compare the two sets of data at the same time stamp, and calculate the speed difference value at each time point. Assuming that the smoothed beating section speed at a certain time point is 95 liters per minute, and the corresponding material transfer rate in the matrix is 92 liters per minute, the difference is 3 liters per minute. Collecting the difference value data of 100 time points in succession, a difference value sequence is formed. The standard deviation is calculated by statistical method, first calculating the average value of the difference value sequence, then calculating the sum of squares of the deviation of each difference value from the average value, dividing by the number of data points and taking the square root to get the standard deviation. The difference between the maximum value and the minimum value of the capacity change sequence reflects the fluctuation range of the storage bin capacity, when the storage bin capacity fluctuates from 3500 liters to 4200 liters, the difference is 700 liters. Multiply the ratio of the standard deviation to 700 liters, and the flow stability index obtained comprehensively reflects the coupling effect of speed deviation and capacity fluctuation.

[0077] It should be noted that the setting of the stability benchmark value is based on the statistical analysis of historical production data. By analyzing the distribution of the flow stability index under normal production conditions, the upper limit of the 95% confidence interval is taken as the benchmark value. When the actual index exceeds the benchmark value, it means that the system deviates from the normal running state.

[0078] Specifically, the extraction of the fluctuation amplitude of the fiber passing rate requires accurate positioning of the time period corresponding to the deviation. When the stability deviation value is 0.15, the system automatically searches for a data segment of 30 seconds before and after the appearance of the deviation value in the dynamic relationship matrix. Within this time period, the fiber passing rate may fluctuate from 0.45 to 0.65, and the fluctuation amplitude is 0.2. This fluctuation amplitude directly reflects the degree of influence of fiber agglomeration on the passing efficiency.

[0079] Preferably, the calculation of the capacity adjustment coefficient takes into account the interaction of multiple factors. The product of the fluctuation amplitude 0.2 and the stability deviation value 0.15 is 0.03, which represents the degree of instability of the system. If the current storage bin capacity utilization rate is 70%, the capacity adjustment coefficient is 0.03 divided by 0.7, which is approximately 0.043. The original storage bin capacity of 5000 liters multiplied by 1.043 gives 5215 liters, and then multiplied by the preset expansion coefficient of 1.1, the final target storage bin capacity requirement is 5736 liters. The introduction of the preset expansion coefficient is to provide additional safety margin to avoid capacity shortage under extreme working conditions.

[0080] In one possible implementation, the reverse calculation process of the target production speed involves material balance calculation. The material consumption per unit time is determined by the paper output rate of the forming section, assuming that 80 kg of board paper is produced per minute, the corresponding pulp consumption is 100 liters per minute. The target storage bin capacity of 5736 liters divided by 100 liters per minute gives a buffer time of 57.36 minutes. In order to maintain this buffer time, the target production speed needs to be adjusted to a function value of the capacity requirement and the buffer time.

[0081] Illustratively, the determination of the adjusted screen mesh size uses a weighted average method. The long fiber proportion of 40% corresponds to a fiber length of 6 mm, the medium fiber proportion of 35% corresponds to 4 mm, and the short fiber proportion of 25% corresponds to 2 mm. The weighted sum gives an average fiber length of 4.3 mm. The target production speed of 100 liters per minute divided by 4.3 mm gives a speed-length ratio of about 23.3. According to the empirical formula, the screen mesh size should be set to 0.22 times the speed-length ratio, i.e. 5.1 mm. This aperture value can ensure the passing efficiency while avoiding excessive loss of short fibers.

[0082] It can be understood that the construction of the target material flow parameter set realizes the coordinated optimization of multiple parameters. The adjusted screen mesh size of 5.1 mm as a screening control parameter directly affects the screening efficiency of the fibers; the target production speed of 100 liters per minute as a coordination parameter between sections ensures the balanced flow of the material between sections; and the target storage bin capacity of 5736 liters as a buffer configuration parameter provides sufficient buffer space to cope with production fluctuations. Further, there is a mutual restraint relationship between the parameters in the parameter set. The increase of the screen mesh size will increase the material passing rate, but may reduce the paper quality; the increase of the production speed will increase the output, but will increase the pressure of the storage bin; and the expansion of the storage bin capacity provides more buffer space, but increases the equipment investment. By integrating the three parameters into a unified parameter set, the system can find a balance point between quality, efficiency and cost.

[0083] For example, in actual application, when the flow stability index is detected to rise from 0.8 to 1.2, the system automatically starts the parameter adjustment program. Through the above calculation process, the parameter combination of the adjusted screen mesh size of 5.1 mm, the target production speed of 100 liters per minute and the target storage bin capacity of 5736 liters is obtained. This set of parameters can effectively cope with the production fluctuations caused by fiber agglomeration and maintain the stable operation of the table paper production line.

[0084] S107, paper forming quality prediction processing is performed on the target material flow parameter set, the adjusted screen mesh size and the buffer storage space are fused to obtain a uniform paper thickness distribution index, and the production scheduling parameter related to the intelligent production scheduling of the paper production line is obtained by combining the material flow parameter set.

[0085] The linear regression processing is performed on the adjusted screen mesh size, the target production speed, and the target storage bin capacity in the target material flow parameter set to establish a mapping relationship between the parameters and the paper thickness. The mapping relationship is used to calculate the predicted thickness values of the paper at different positions to obtain paper thickness distribution data. According to the paper thickness distribution data, the sum of squares of the thickness values of each sampling point and the average thickness is calculated, and the standard deviation of the thickness is obtained by taking the square root of the sum of squares divided by the number of sampling points. The thickness coefficient of variation is obtained by dividing the standard deviation of the thickness by the average thickness. The standard deviation of the thickness and the thickness coefficient of variation are used as uniform paper thickness distribution indexes. The production coordination coefficient is obtained by using the ratio of the standard deviation of the thickness to the adjusted screen mesh size and combining the proportion of the buffer storage space in the total capacity. The speed adjustment proportion of each section is determined according to the production coordination coefficient. The adjusted speed values of each section are obtained by multiplying the speed adjustment proportion by the target speed of the beating section, the screening section, and the forming section, respectively. The optimal production speed combination is formed by combining the adjusted speed values of the three sections. The material transfer time interval is calculated according to the speed difference between adjacent sections. The delay start time of the screening section after the beating section starts and the delay start time of the forming section after the screening section starts are determined according to the material transfer time interval. The optimal production speed combination and the delay start time of each section are integrated to construct a production scheduling parameter set.

[0086] In an embodiment, the implementation process of the linear regression processing is based on historical production data to establish a correlation model between the parameters and the thickness. The target material flow parameter set contains three key variables: the adjusted screen mesh size of 5.1 mm, the target production speed of 100 liters per minute, and the target storage bin capacity of 5736 liters. These parameters are input into the regression model as independent variables, and the paper thickness is used as the dependent variable. The regression coefficients are determined by the least squares method. The regression coefficient of the screen mesh size reflects the influence of the mesh size on the fiber distribution, the coefficient of the production speed represents the effect of the speed on the fiber deposition, and the coefficient of the storage bin capacity represents the contribution of the buffer time to the uniformity of the fibers. The established mapping relationship is expressed as: the predicted thickness is equal to the base thickness plus the product of the mesh size coefficient and the mesh size value, plus the product of the speed coefficient and the speed value, plus the product of the capacity coefficient and the capacity value. Through this mapping relationship, the thickness values at different positions in the transverse and longitudinal directions of the paper can be predicted to form a complete thickness distribution data matrix.

[0087] It should be noted that the standard deviation of the thickness and the coefficient of variation are core indexes for evaluating the quality of the paper. The standard deviation reflects the absolute fluctuation degree of the thickness, and the coefficient of variation reflects the relative fluctuation by eliminating the influence of the average thickness. The sampling points are usually set at nine positions of the paper: the four corners, the four midpoints of the edges, and the center point to ensure covering the entire surface of the paper.

[0088] Specifically, the calculation of the production coordination coefficient combines the two dimensions of quality control and capacity balance. The ratio of the thickness standard deviation 0.05 mm to the screen aperture 5.1 mm is about 0.0098, which reflects the impact of screening accuracy on thickness control. The proportion of the buffer storage space 2000 L to the total capacity 5736 L is 0.35, which represents the buffer capacity of the system. The way to combine the two is to multiply the ratio and the proportion and then take the square root, obtaining a production coordination coefficient of about 0.059. This coefficient is used to determine the speed adjustment ratio of each section. The larger the coefficient, the greater the speed adjustment required.

[0089] Preferably, each section speed adjustment adopts a differentiated strategy. The beating section as the source section, its speed adjustment ratio is set to 1.2 times the production coordination coefficient, i.e. 0.071; the screening section as the intermediate section, the adjustment ratio is equal to the production coordination coefficient 0.059; the forming section as the terminal section, the adjustment ratio is 0.8 times the coefficient, i.e. 0.047. The original target speed 100 L / min multiplied by the respective adjustment ratio, the beating section adjusted speed is 107.1 L / min, the screening section is 105.9 L / min, and the forming section is 104.7 L / min. This decreasing speed configuration avoids the accumulation of materials between sections.

[0090] In one possible implementation, the calculation of the material transfer time interval is based on the speed difference and the pipe volume of adjacent sections. The pipe volume from the beating section to the screening section is 500 L, the speed difference is 1.2 L / min, and the transfer time interval is 500 divided by 1.2, about 417 seconds. The pipe volume from the screening section to the forming section is 400 L, the speed difference is 1.2 L / min, and the transfer time interval is 333 seconds. These time intervals determine the timing arrangement of section start.

[0091] Illustratively, the design of the section coordination timing follows the principle of continuous material flow. When the beating section starts at zero time, it needs to wait for the first batch of pulp to fill the pipe and reach the screening section inlet, so the delayed start time of the screening section is set to 420 seconds. Similarly, the forming section starts 335 seconds after the screening section starts. This staggered start-up method ensures that each section starts working only after receiving a stable material flow, avoiding idling or flow interruption.

[0092] It can be understood that the construction of the production scheduling parameter set realizes the balance between quality control and production efficiency. The optimal production speed combination contains the adjusted speed values of the three sections, which are optimized in coordination to ensure the uniformity of paper thickness and maintain high production efficiency. The section coordination timing contains the start-up delay time and shutdown sequence of each section, which ensures the continuous flow of materials and the coordinated operation of equipment. Further, this set of production scheduling parameters can be connected with the intelligent scheduling system of the board paper production line. The scheduling system calls the corresponding parameter set according to the order requirements and equipment status, and automatically sets the operating parameters of each section. When producing different specifications of board paper, the system will recalculate and adjust the parameter set to realize flexible production.

[0093] For example, in actual production, when receiving an order for board paper with a thickness requirement of 2.5 mm and a uniformity requirement of a coefficient of variation less than 5%, the system first runs the quality prediction model to confirm that the current parameter set can meet the requirements. Then, according to the section coordination timing, each section is started in turn, with the beating section running at a speed of 107.1 liters per minute, the screening section starting at 105.9 liters per minute after 7 minutes, and the forming section starting at 104.7 liters per minute after another 5.5 minutes. This precise timing control and speed matching ensure that the uniformity of the board paper thickness meets the quality standards while maintaining the efficient operation of the production line.

[0094] Based on the screen aperture and storage bin capacity configuration in the target material flow parameter set, combined with the predicted paper thickness uniformity, the speed matching relationship between the pulp preparation section and the forming section is determined, the material transfer beat between sections is adjusted according to the uniformity requirement of the thickness distribution, the section coordination timing from fiber separation to paper forming is obtained, the buffer time of each section is determined through the storage bin capacity configuration, the screen adjustment frequency and production speed change cycle are integrated, and the scheduling and scheduling scheme including the section start-stop sequence and speed switching timing is formed.

[0095] Based on the screen mesh aperture value in the target material flow parameter set and the storage bin capacity configuration data, combined with the predicted paper thickness uniformity, the ratio of the output flow of the beating section to the receiving flow of the forming section is calculated, and when the thickness variation coefficient is less than the preset threshold, the ratio is determined as the speed matching coefficient to obtain the speed matching relationship of the beating section and the forming section. According to the speed matching relationship and the thickness distribution uniformity requirement, the time interval of material transfer between sections is calculated, and the transfer time from the beating section to the screening section is proportionally adjusted with the transfer time from the screening section to the forming section to obtain a material transfer beat sequence. The material transfer beat sequence is used to determine the time difference of the beating section start time, the screening section start time and the forming section start time to form a section coordination time sequence, and the buffer time of each section is calculated according to the storage bin capacity configuration divided by the material consumption rate of each section. Through the comparison of the buffer time and the adjustment time required by the screen mesh aperture, when the buffer time is greater than the preset multiple of the adjustment time, the screen mesh adjustment frequency is determined as the integer part of the buffer time divided by the adjustment time, and the time interval corresponding to the screen mesh adjustment frequency is taken as the larger value with the production speed change interval to obtain a speed change period. According to the section coordination time sequence and the speed change period, the section start sequence is set as beating, screening and forming in turn, and the speed switching time is set at the starting point of each speed change period, and the start-stop sequence and the speed switching time are integrated to form a production scheduling scheme.

[0096] In an embodiment, the determination process of the speed matching coefficient is based on the dual constraints of flow balance principle and quality control requirement. The output flow of the beating section is measured by the flow meter of the outlet pipe, and the typical value is 107 liters per minute. The receiving flow of the forming section needs to consider fiber loss and water evaporation, and the actual receiving amount is about 102 liters per minute. The ratio of the two is 1.049, which reflects the material transfer efficiency of the system. When the paper thickness variation coefficient is lower than the preset threshold of 5%, it means that the current flow ratio can guarantee the thickness uniformity, and at this time 1.049 is determined as the speed matching coefficient. The physical meaning of this coefficient is that for every 1.049 units of pulp output by the beating section, the forming section can process exactly 1 unit, and the remaining 0.049 units are discharged through the screening residue of the screening section and absorbed by the buffer of the storage bin. The establishment of the speed matching relationship enables each section to maintain material balance at different speeds, avoiding that a certain section becomes a production bottleneck.

[0097] It should be noted that the formation of the material transfer beat sequence needs to consider the pipe length, pulp flow rate and equipment response time comprehensively. The pipe length from the beating section to the screening section is 50 meters, the average flow rate of the pulp is 2 meters per second, and the theoretical transfer time is 25 seconds. However, in fact, the start-up preparation time of the screening equipment needs to be added, which is 15 seconds, so the actual transfer time is 40 seconds.

[0098] Specifically, the core of the beat ratio adjustment is to maintain the continuous operation of each section. When the uniformity requirement of thickness distribution is improved, the processing time of the screening section needs to be extended to ensure that the fibers are fully separated. The transfer time from beating to screening is 40 seconds and the transfer time from screening to forming is 30 seconds. If the uniformity requirement is improved from a coefficient of variation of 5% to 3%, the ratio needs to be adjusted from 4:3 to 5:3, and the processing cycle of the screening section is correspondingly extended. The adjusted material transfer beat sequence is 50 seconds, 30 seconds, which determines the operation rhythm of each section.

[0099] Preferably, the design of the section coordination timing adopts the feedforward control idea. The first batch of pulp needs 50 seconds to reach the screening section inlet after the beating section starts at zero time. The screening section starts at the 50th second and processes the first batch of pulp for 20 seconds, plus the transfer time of 30 seconds to the forming section, the forming section should start at the 100th second. This cascade starting method forms a section coordination timing of 0 seconds, 50 seconds, and 100 seconds. The calculation of the buffer time of each section is based on the storage bin capacity and the material consumption rate. The storage bin capacity is 5736 liters, the beating section consumption rate is 107 liters per minute, and the buffer time is 53.6 minutes; the screening section storage bin is 4000 liters, the consumption rate is 105 liters per minute, and the buffer time is 38.1 minutes; the forming section storage bin is 3000 liters, the consumption rate is 102 liters per minute, and the buffer time is 29.4 minutes.

[0100] In one possible implementation, the determination of the screen adjustment frequency needs to balance production efficiency and quality control. Adjusting the screen aperture from 5.0 mm to 5.2 mm takes 3 minutes, including 1 minute of shutdown, 1.5 minutes of adjustment, and 0.5 minutes of restart. When the beating section buffer time 53.6 minutes is greater than 15 times the adjustment time 3 minutes, the screen adjustment can be carried out without affecting the continuity of production. The screen adjustment frequency is determined to be the integer part of 53.6 divided by 3, i.e. 17 times. This means that a maximum of 17 screen adjustments can be made in one production cycle.

[0101] Exemplarily, the determination of the speed change period takes into account both screen adjustment and production rhythm. The time interval corresponding to the screen adjustment frequency of 17 times is 3.15 minutes, and the production speed may change every 5 minutes according to order requirements. Taking the larger value of 5 minutes as the speed change period ensures that the system has enough time to complete the adjustment and reach a stable state.

[0102] It can be understood that the core of the production scheduling scheme is to coordinate the start-stop and speed switching of each section. The start sequence of the section is strictly according to the order of beating, screening and forming, and is started at 0 seconds, 50 seconds and 100 seconds respectively. At the beginning of each 5-minute speed change cycle, the system first adjusts the speed of the beating section, and after a 50-second delay, adjusts the speed of the screening section, and then adjusts the speed of the forming section after another 50-second delay. This wave-like speed adjustment avoids system shock. Further, the setting of the speed switching time needs to consider the buffering effect of the storage bin. At the 0th minute of each cycle, the beating section switches from 107 liters per minute to 110 liters per minute; at the 0.83rd minute, the screening section switches from 105 liters per minute to 108 liters per minute; and at the 1.67th minute, the forming section switches from 102 liters per minute to 105 liters per minute. This time difference setting takes advantage of the buffering capacity of the storage bin to smooth the impact of speed switching on the system.

[0103] For example, in actual production scheduling, the morning shift starts production at 8 o'clock, the beating section is started first, the screening section is started at 8:00:50, and the forming section is started at 8:01:40. The first speed adjustment is made at 8:05, and the production capacity is increased by 5% according to the order requirements. The beating section speed is increased at 8:05, the screening section follows at 8:05:50, and the forming section completes the adjustment at 8:06:40. During the adjustment process, the liquid level of each storage bin is always maintained within the safe range of 30% to 70%, achieving smooth speed switching. This production scheduling scheme realizes the efficient and stable operation of the board paper production line through precise timing control and speed coordination.

[0104] The above disclosure is only the preferred embodiment of the present application, and of course cannot limit the scope of the rights of the present application. Those skilled in the art can understand that the above-mentioned embodiments can be implemented in whole or in part, and equivalent changes made in accordance with the claims of the present application still fall within the scope of the present application.

Claims

1. A method for analyzing intelligent scheduling data of a platform paper production line, characterized in that, The method comprises the following steps: Obtaining fiber length distribution and screen mesh size data from the pulp pool, obtaining capacity level and production speed of each section from the storage bin monitoring device, and fusing the data to construct an initial dynamic relationship matrix; According to the initial dynamic relationship matrix, the fiber length is identified, the fibers are classified into long fibers, medium fibers and short fibers, the proportion of long fibers is calculated, the ratio of fiber length to screen mesh size is obtained by weighted average processing, and the agglomeration density is determined; according to the agglomeration density, a subset of fiber flow speed and screen mesh resistance is extracted from the initial dynamic relationship matrix, the screen mesh size is adjusted, and the material passing rate is calculated in combination with the production speed; the material passing rate is compared with the storage bin capacity level, the capacity matching degree is calculated, and the buffer space allocation proportion is adjusted according to the capacity matching degree; Extracting the fiber passing speed fluctuation of each section after adjustment, fusing the fiber length distribution, and adopting a moving average filtering algorithm to process to obtain a smooth production speed; comparing the smooth production speed with the initial dynamic relationship matrix to calculate the flow stability, adjusting the storage bin capacity requirement according to the flow stability, and determining the target material flow parameter set; predicting the paper thickness uniformity of the target material flow parameter set, fusing the adjusted screen mesh size and buffer space allocation proportion, calculating the thickness standard deviation and coefficient of variation, and determining the production scheduling parameter.

2. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The method comprises the following steps: Collecting samples from different positions of the pulp pool, scanning fiber length, counting the proportions of long fibers, medium fibers and short fibers, and reading screen mesh size values; obtaining capacity level data from the storage bin, marking a time stamp, and generating a capacity change sequence; collecting production speeds from the beating, screening and forming sections, and calculating material transfer rates of adjacent sections; according to the fiber length distribution and screen mesh size values, a fiber passing rate vector is calculated, and the values corresponding to long fibers in the fiber passing rate vector are adjusted; the fiber passing rate vector, the material transfer rate and the capacity change sequence are arranged in time sequence as columns to construct an initial dynamic relationship matrix.

3. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The method comprises the following steps: Extracting a fiber passing rate vector from the initial dynamic relationship matrix to identify long fibers, medium fibers and short fibers; counting the proportion of long fibers, collecting long fiber concentrations at different positions of the pulp pool, and summing up the long fiber concentrations by depth weighting to obtain a comprehensive long fiber proportion; calculating a ratio by dividing the comprehensive long fiber proportion by the screen mesh size value; extracting fiber passing rates at consecutive time points, calculating the sum of the absolute values of the passing rate difference, and determining an agglomeration fluctuation index; calculating the agglomeration density according to the agglomeration fluctuation index, the ratio and the fiber suspension concentration.

4. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The method comprises the following steps: Extracting the material passing rate corresponding to the low-pass rate row from the initial dynamic relationship matrix as the fiber flow speed; calculating the reciprocal of the passing rate change amount to determine the screen mesh resistance coefficient, and constructing a subset; calculating the screen mesh aperture adjustment amount according to the mean value of the screen mesh resistance coefficient and the difference value of the agglomeration density, and determining the target screen mesh aperture; adjusting the production speed of each section according to the target screen mesh aperture; calculating the fiber mass flow by multiplying the screen section speed by the target screen mesh aperture and dividing by the fiber suspension concentration, and determining the material passing rate.

5. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The material passing rate is compared with the storage bin capacity level, the capacity matching degree is calculated, and the buffer space allocation ratio is adjusted according to the capacity matching degree, including: The material inflow amount is calculated by multiplying the material passing rate by the screening section speed; the storage bin capacity occupancy rate is obtained, and the ratio of the material inflow amount to the remaining capacity is calculated as the capacity matching degree; the difference value is calculated by comparing the capacity matching degree with the threshold value, and the buffer space expansion demand coefficient is determined; the additional buffer space demand amount is calculated by the buffer space expansion demand coefficient, the buffer space allocation ratio increment is determined, and the allocation ratio is adjusted.

6. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The fiber passing speed fluctuation of each section after adjustment is extracted, and the fiber length distribution is fused to obtain a smooth production speed by using a moving average filtering algorithm, including: The fiber passing speed difference value of each section is extracted to form a fluctuation sequence; the moving average filtering is used on the fluctuation sequence to calculate the average value in the window to obtain a smooth fluctuation sequence; the comprehensive fluctuation index is calculated according to the weighted fusion of the smooth fluctuation sequence and the fiber length distribution; the material flow trend is determined by the difference value of the comprehensive fluctuation index; the filter window size is adjusted to process the original production speed to obtain a smooth production speed.

7. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The flow stability is calculated by comparing the smooth production speed with the initial dynamic relationship matrix, the storage bin capacity demand is adjusted according to the flow stability, and the target material flow parameter set is determined, including: The speed difference standard deviation is calculated by point-by-point comparison of the smooth production speed and the material passing rate, and the flow stability index is determined in combination with the capacity change sequence; the stability deviation is calculated by the difference value of the flow stability index and the reference value; the capacity adjustment coefficient is calculated according to the stability deviation and the fiber passing rate fluctuation amplitude; the target production speed and the screen mesh aperture are determined by adjusting the storage bin capacity by the capacity adjustment coefficient, and the target material flow parameter set is constructed.

8. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The paper thickness uniformity prediction is performed on the target material flow parameter set, the adjusted screen mesh aperture and the buffer space allocation ratio are fused, the thickness standard deviation and the coefficient of variation are calculated, and the production scheduling parameters are determined, including: The thickness mapping relationship is established by the target material flow parameter set to calculate the paper thickness distribution; the thickness standard deviation and the coefficient of variation are calculated according to the paper thickness distribution; the production coordination coefficient is determined by fusing the buffer space ratio through the ratio of the thickness standard deviation to the adjusted screen mesh aperture; the optimal production speed combination and the section coordination timing are determined by adjusting the speed of each section, calculating the material transfer time interval, and adjusting the speed of each section.

9. The intelligent scheduling data analysis method for a platform paper production line according to claim 1, characterized in that, The paper thickness uniformity prediction of the target material flow parameter set is fused with the adjusted screen mesh aperture and the buffer space allocation ratio, the thickness standard deviation and the variation coefficient are calculated, and the production scheduling parameters are determined, including: Through the screen mesh aperture and the storage bin capacity in the target material flow parameter set, combined with the thickness variation coefficient, the speed matching coefficient of the beating section and the forming section is calculated; according to the speed matching coefficient, the material transfer time interval is adjusted, the section coordination timing is determined; through the storage bin capacity divided by the material consumption rate, the buffer time is calculated; through the comparison between the buffer time and the screen adjustment time, the screen adjustment frequency and the speed change period are determined, the section start sequence and the speed switching opportunity are set, and the production scheduling scheme is constructed.

Images