A method for online quality monitoring and process evaluation of the stem pressing process.

Abstract

This invention provides a method for online monitoring and process evaluation of the tobacco stem pressing process. The method includes: decoupling the stem thickness, a key indicator that is difficult to detect quickly online, into the stem width, which is easy to measure online, through a physical model, thereby achieving non-contact, rapid, and reliable online evaluation of the stem pressing quality; reconstructing a comprehensive performance index, including extension characteristics, that can isolate the influence of incoming material size and accurately reflect the matching state of "process-material" by linking the tobacco stem diameter and stem width; establishing SPC control charts for the equivalent diameter and extension characteristics of the tobacco stem, respectively, to realize the transformation of stem pressing processing from result monitoring to process root cause diagnosis; and providing scientific process selection decision support for different material characteristics, thereby improving the quality stability, consistency, and controllability of the stem pressing process.

Description

Technical Field

[0001] This invention relates to the field of tobacco processing technology, and in particular to a method for online quality monitoring and process evaluation of the stem pressing process. Background Technology

[0002] In tobacco processing, the stem pressing process is a crucial pretreatment step that compresses tobacco stems into sheets of a specific thickness, providing uniform material for subsequent stem cutting. The quality of stem pressing directly determines the structure and filling properties of the subsequent stems, and even affects the sensory quality of the cigarette product.

[0003] However, in existing technologies, the tobacco industry primarily relies on manual offline sampling for quality evaluation and control of the tobacco stem pressing process. Operators periodically extract small samples of stem pieces from the production line and measure their thickness using calipers or thickness gauges. This method suffers from problems such as poor representativeness of sampling, blind spots, delayed feedback, susceptibility to errors introduced by the measurement method, and a lack of root cause diagnosis capabilities. Summary of the Invention

[0004] To address the problems existing in the prior art, embodiments of the present invention provide a method and system for online quality monitoring and process evaluation of the stem pressing process.

[0005] Firstly, embodiments of this specification provide a method for online quality monitoring and process evaluation of the stem pressing process, the method comprising:

[0006] The tobacco stem raw materials are sampled and pre-treated to generate tobacco stem samples;

[0007] The tobacco stem sample is laid flat, a top view image is captured, the equivalent diameter of the tobacco stem in the top view image is calculated, and based on the equivalent diameter of the tobacco stem, the tobacco stem sample is divided into multiple diameter intervals;

[0008] The tobacco stem sample was subjected to simulated pressing, and the center thickness of the tobacco stem sample after simulated pressing was collected. The tobacco stem sample was also flattened, and the width of the flattened tobacco stem sample was collected.

[0009] Based on the fact that the volume of the tobacco stem sample remains unchanged before and after pressing, a material volume conservation relationship for the tobacco stem sample is established, and its volume calculation formula is as follows:

[0010] ,

[0011] Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness.

[0012] Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined, and the elongation characteristics are:

[0013] Y = W / D,

[0014] Wherein, Y represents the elongation characteristic of the tobacco stem, which is negatively linearly correlated with the center thickness T;

[0015] Based on the equivalent diameter and extension characteristics of the tobacco stem, a control benchmark for tobacco stem detection is generated.

[0016] Secondly, embodiments of this specification provide an online quality monitoring and process evaluation system for the stem pressing process, the system comprising:

[0017] The preprocessing module is used to sample and preprocess tobacco stem raw materials to generate tobacco stem samples;

[0018] The image acquisition module is used to lay the tobacco stem sample flat, acquire a top view image, calculate the equivalent diameter of the tobacco stem in the top view image, and divide the tobacco stem sample into multiple diameter intervals based on the equivalent diameter of the tobacco stem;

[0019] The tobacco stem processing module is used to simulate pressing the tobacco stem sample, collect the center thickness of the tobacco stem sample after simulated pressing, and flatten the tobacco stem sample to collect the width of the flattened tobacco stem sample.

[0020] The data processing module is used to establish a material volume conservation relationship for the tobacco stem samples based on the fact that the volume of the tobacco stem samples remains unchanged before and after pressing. The volume calculation formula is as follows: Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness. Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined. The elongation characteristics are: Y = W / D, where Y is the elongation characteristics of the tobacco stem and is negatively linearly correlated with the center thickness T.

[0021] The control module is used to generate a control benchmark for tobacco stem detection based on the equivalent diameter and extension characteristics of the tobacco stem.

[0022] Thirdly, embodiments of this specification provide an electronic device, including a processor and a memory;

[0023] The processor is connected to the memory;

[0024] The memory is used to store executable program code;

[0025] The processor runs a program corresponding to the executable program code stored in the memory to perform the methods described in one or more embodiments.

[0026] Fourthly, embodiments of this specification provide a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method for online quality monitoring and process evaluation of the pressing process.

[0027] In view of the above, the beneficial effects of the technical solutions provided by some embodiments of this specification include at least the following:

[0028] In one or more embodiments of this specification, the key indicator "stem thickness," which is difficult to detect quickly online, is "decoupled" into stem width, which is easy to measure online, through a physical model. This enables non-contact, rapid, and reliable online evaluation of stem pressing quality. By linking the stem diameter and stem width, a comprehensive performance indicator that can isolate the influence of incoming material size and accurately reflect the matching state of "process-material" characteristics is reconstructed. SPC control charts are established for the equivalent diameter and extension characteristics of the stem, respectively, realizing the transformation of stem pressing processing from "result monitoring" to "process root cause diagnosis." Furthermore, scientific process selection decision support is provided for different material characteristics, improving the quality stability, consistency, and controllability of the stem pressing process. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart of an online quality monitoring and process evaluation method for a stem pressing process provided in one embodiment of this specification.

[0031] Figure 2 This is a distribution diagram of the stem diameter D value of a certain brand of tobacco formula provided in one embodiment of this specification.

[0032] Figure 3 This is a schematic diagram illustrating the relationship between the width W of the tobacco stem, the center thickness T of the tobacco stem, and the diameter D of the tobacco stem in a simulated tobacco stem pressing process, provided in one embodiment of this specification.

[0033] Figure 4 This is a schematic diagram illustrating the relationship between the thickness-to-diameter ratio Y and the tobacco stem diameter D, provided in one embodiment of this specification.

[0034] Figure 5 This is a schematic diagram of an I-MR control chart provided in one embodiment of this specification.

[0035] Figure 6 This is one embodiment provided in this specification. A schematic diagram of the -S control chart.

[0036] Figure 7 This is a schematic diagram of the structure of an online quality monitoring and process evaluation system for the stem pressing process provided in one embodiment of this specification.

[0037] Figure 8 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this specification. Detailed Implementation

[0038] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed merely to enable those skilled in the art to better understand and implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. The function and arrangement of the elements discussed may be changed without departing from the scope of this specification. Various processes or components may be omitted, substituted, or added as needed in the various examples. For example, the described methods may be performed in a different order than described, and steps may be added, omitted, or combined. Furthermore, features described in some examples may be combined in other examples.

[0039] As used herein, the term "comprising" and its variations are open terms meaning "including but not limited to". The term "based on" means "at least partially based on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other definitions, whether explicit or implicit, may be included below. Unless explicitly indicated by the context, the definition of a term shall remain consistent throughout the specification.

[0040] Please see Figure 1 , Figure 1 This document presents an overall flowchart of a method for online quality monitoring and process evaluation of a stem pressing process, as provided in an embodiment of this specification.

[0041] like Figure 1 As shown, the online quality monitoring and process evaluation method for the pressing stem process includes at least the following steps:

[0042] Step S102: Sample and preprocess the tobacco stem raw materials to generate tobacco stem samples.

[0043] Specifically, random sampling is conducted from all batches of tobacco stem raw materials actually used in the production line, and a certain number (e.g., more than 500) of tobacco stems are selected. The tobacco stems selected must be intact, without damage, mold, or clumping, to ensure that the sample covers the full diameter distribution and full grade range of tobacco stems in actual production, and to avoid sampling bias.

[0044] The selected tobacco stems underwent pretreatment, including humidification methods adapted to the production conditions to adjust the moisture content to the production line's standard range. For example, soaking was used: the stems were soaked in hot water at 40-60℃ for 1-2 minutes, and then the surface saturation was removed. A spraying method was also used, where a quantitative amount of hot water was sprayed to humidify the stems and adjust the moisture content to the standard range (26-30%). The humidified stems were then placed in a constant temperature and humidity chamber at 40℃ and 80% relative humidity for 1-2 hours to equilibrate, ensuring all samples reached a uniform and stable processing state. This ensured that the moisture content deviation of the tobacco stem samples was less than a fixed value, achieving a uniform and stable processable state.

[0045] Step S104: Lay the tobacco stem sample flat, capture a top view image, calculate the equivalent diameter of the tobacco stem in the top view image, and divide the tobacco stem sample into multiple diameter intervals based on the equivalent diameter of the tobacco stem.

[0046] Specifically, the tobacco stem samples are laid flat, meaning they are placed on a high-contrast background using a discrete, non-overlapping, and non-bending single-layer tiling method. A high-resolution camera module accurately captures top-view images of the tobacco stem samples perpendicular to the background. Standardized image processing procedures are then performed on the captured images, including filtering and denoising (eliminating environmental noise and grayscale interference), Canny edge detection (accurately extracting the outer contour of individual tobacco stems, removing broken or false edges), contour fitting, and size calculation. The equivalent diameter D of the tobacco stem is calculated using either the least circumscribed rectangle method or the calculation of the equivalent circle diameter.

[0047] Furthermore, the statistical distribution of the equivalent diameter of all tobacco stem samples can be determined by using methods such as equal-frequency binning or process experience to divide all tobacco stem samples into multiple consecutive diameter intervals (e.g., ≤2.0mm, 2.0-3.5mm, 3.5-5.0mm, 5.0-7.0mm, >7.0mm), forming a structured experimental sample set. 20-30 tobacco stems are randomly selected from each interval and labeled with the interval and sequence number.

[0048] Step S106: Simulate pressing the tobacco stem sample, collect the center thickness of the tobacco stem sample after simulated pressing, and flatten the tobacco stem sample, collect the width of the flattened tobacco stem sample.

[0049] Specifically, for tobacco stem samples with pre-defined intervals, a laboratory smooth-surface pressing machine with precisely controllable gaps can be used to simulate production line pressing. The gap between the pressing rollers can be set according to actual process conditions (generally within the range of 0.4~2.0mm). Each marked tobacco stem is pressed individually. This ensures that the pre-pressing diameter D of each tobacco stem uniquely corresponds to the pressed stem sheet, avoiding data pairing failures caused by mixing multiple stems. Immediately after pressing, a high-precision measuring tool is used to measure the thickness T of the center of the stem sheet, i.e., the center thickness of the tobacco stem sample. Next, the pressed stem sheet can be flattened, its top-view image captured, and after image processing, the complete outline of the stem sheet extracted to calculate its maximum width W, i.e., the width of the tobacco stem sample.

[0050] Furthermore, during simulated tablet pressing, single-pass simulated tablet pressing can be performed with different roller gaps (e.g., 0.4mm, 0.8mm, 1.2mm, 1.6mm, 2.0mm), or continuous tablet pressing with multi-level gradient gaps (e.g., 2.0mm+0.8mm, 1.6mm+0.4mm, 0.8mm+0.4mm, etc.). The tablet width (W) under different processing conditions is recorded.

[0051] Step S108: Based on the fact that the volume of the tobacco stem sample remains unchanged before and after pressing, a material volume conservation relationship for the tobacco stem sample is established, and the volume calculation formula is as follows: Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness. Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined. The elongation characteristics are: Y = W / D, where Y is the elongation characteristics of the tobacco stem and is negatively linearly correlated with the center thickness T.

[0052] Specifically, based on the principle of constant volume in the plastic deformation of tobacco stems during compression (the moistened tobacco stems possess excellent plasticity, the elastic rebound after compression is negligible, and the material volume before and after compression is approximately constant), a deformation relationship model is established. Before compression, the tobacco stem is approximately cylindrical; after compression, the stem pieces are approximately cuboids. Therefore:

[0053] ,

[0054] Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness.

[0055] The above equation can be simplified to:

[0056] ,

[0057] Among them, the width-to-diameter ratio Y=W / D can be defined. This index characterizes the radial extension characteristics of the tobacco stem under given process conditions and directly reflects the compaction effect of the stem: under the premise of fixed incoming material diameter D, the Y value has a strict negative linear correlation with the stem thickness T. The larger the Y value, the smaller the stem thickness and the better the compaction effect.

[0058] Step S110: Based on the equivalent diameter and extension characteristics of the tobacco stem, a control benchmark for tobacco stem detection is generated.

[0059] Specifically, the control criteria for tobacco stem detection may include establishing a system based on the equivalent diameter of the tobacco stem. -S control chart, The -S control chart is used to monitor the quality indicators of tobacco stems. It monitors the mean drift and uniformity fluctuation of the incoming stem diameter. The creation process for the two control charts corresponding to the -S control chart includes:

[0060] The mean of the equivalent diameter of tobacco stems in the statistical tobacco stem sample and standard deviation Then, based on the preset subgroup size in the production line (the standard subgroup size can be set to n=3~10), and based on the central limit theorem, combined with the standard deviation... Given a predefined subgroup size for the tobacco stem samples, calculate the standard error of the subgroup mean:

[0061] ,

[0062] Where n is the subgroup size, that is, the number of samples in the subgroup.

[0063] Set a confidence coefficient k (which can be selected within the range of 1.0 to 3.0, for example, k = 3), and combine it with the mean and standard error to determine the upper and lower control limits of the control chart for the D value of the equivalent diameter of the tobacco stem sample, including:

[0064] Control limit D UCL = +k· Control lower limit D LCL = -k· .by The upper and lower control limits of the control chart monitor the mean drift of the incoming material diameter.

[0065] Furthermore, a D-value standard deviation S-control chart can be established simultaneously. By calculating the mean of the standard deviations of all subgroups and combining it with the SPC standard constant of the corresponding subgroup size, the upper and lower control limits of the D-value standard deviation control chart can be calculated. This determines the control limits of the S-control chart, which is used to monitor the uniformity fluctuation of the incoming material diameter. Combining the D-value mean control chart and the D-value standard deviation control chart, the monitoring indicators of tobacco stem quality can be comprehensively monitored.

[0066] Furthermore, the control benchmark for tobacco stem testing may include establishing an I-MR control chart based on the stem's extensibility characteristics, and using the I-MR control chart to monitor stem compression quality indicators. The process for establishing the I control chart and MR control chart in the I-MR control chart includes:

[0067] Based on simulated stem pressing requirements (screening stem slices whose thickness meets production line process requirements). -S control chart ( - The S control chart is in a controlled state, excluding abnormal interference from incoming materials. Valid tobacco stem samples are selected based on the stability of the elongation characteristics (stable fluctuation of the Y value). The mean elongation characteristics of all valid tobacco stem samples are calculated and used as the center line of the I control chart. Then, the moving range of adjacent samples of the valid samples is calculated, and the mean of the moving range is calculated. ;

[0068] Based on the SPC standard constant of the subgroup size, and combined with the mean of the extension characteristic and the mean of the moving range, the upper and lower control limits of the I control chart are calculated, where the lower control limit of the I control chart is the core control item:

[0069] Control upper limit Y UCL = +E2 Control the lower limit Y LCL = -E2 Where E2 is the SPC standard constant.

[0070] Furthermore, based on the SPC standard constant and the mean of the moving range for subgroup size, the upper and lower control limits of the MR control chart are calculated, including:

[0071] Control upper limit MR UCL = D4 Where D4 is the SPC standard constant, and like E2, it is a statistical process control constant determined based on subgroup size. Then, it is matched with... For the same subgroup cycle of the -S control chart, based on the early warning system, and combined with the I control chart and MR control chart, the quality monitoring indicators of the compaction are monitored. Specifically, based on the statistical results of Y values ​​under different compaction processes (such as roller gap and number of compaction cycles), a quantitative evaluation rule for process efficiency is established: under the same incoming material diameter D and the same incoming material moisture content, the larger the mean Y value and the smaller the standard deviation, the better the compaction effect and the better the processing stability of the process. This serves as a quantitative basis for selecting production line process parameters and optimizing process paths, replacing traditional trial-and-error based on experience.

[0072] Furthermore, the I-MR control chart's early warning system is a three-level system, which can: monitor the overall level of the Y value, identify urgent quality anomalies such as excessive stem thickness, and trigger a level one early warning; monitor continuous fluctuations in the Y value, identify trend deterioration and stability anomalies in the stem pressing process, and trigger level two and three early warnings. In addition, the two control charts can be linked for diagnostic execution; that is, when the I-MR control chart triggers an early warning, the incoming material D value is simultaneously linked. The -S control chart status completes the decoupling of abnormal root causes: synchronous abnormalities in the D chart are determined to be due to abnormal incoming material characteristics, while controlled abnormalities in the D chart are determined to be due to abnormal pressing process efficiency. This fundamentally solves the problem that traditional methods cannot trace the root causes of quality abnormalities.

[0073] This invention provides an online monitoring and process evaluation method for the tobacco stem pressing process. The key indicator "stem thickness," which is difficult to detect quickly online, is "decoupled" into the easily measurable stem width through a physical model, enabling non-contact, rapid, and reliable online evaluation of stem pressing quality. By linking the tobacco stem diameter and stem width, a comprehensive performance indicator that can isolate the influence of incoming material size and accurately reflect the matching state of "process-material" characteristics is reconstructed. SPC control charts are established for the equivalent diameter and elongation characteristics of the tobacco stem, respectively, realizing the transformation of stem pressing processing from "result monitoring" to "process root cause diagnosis." Furthermore, scientific process selection decision support is provided for different material characteristics, improving the quality stability, consistency, and controllability of the stem pressing process.

[0074] Furthermore, a Y-value benchmark based on material properties was established through systematic offline experiments, providing a basis for online control. Machine vision was employed to achieve non-contact, rapid measurement with real-time data feedback (within minutes). This solved the problems of large deviations and long feedback lags in traditional manual measurement of sheet thickness. A dual SPC control chart system centered on D and Y was constructed to achieve full-process monitoring from incoming material characteristics to process efficiency. Precise root cause diagnosis was achieved by combining standard SPC anomaly detection rules with specific process logic.

[0075] In another embodiment, the specific process of SPC linkage control and intelligent judgment in an online quality monitoring and process evaluation method for the pressing process may include:

[0076] Data monitoring: Stem diameter (D) monitoring: Single images (a subgroup containing no fewer than 100 stems) are acquired at fixed time intervals (e.g., 20 minutes), and the mean diameter of all detected stems within that time period is calculated. ) and standard deviation (SD). Plotting uses -S control chart to monitor the drift and dispersion of the average size of incoming materials.

[0077] Stalk width (W) detection: Combining material flow lag time (determined by staining marker tracking method, accurate to minutes), images are acquired at the same time intervals, and the mean value of all stalk widths within that time period is calculated. ).

[0078] Quality monitoring (Y): Matching the time window (considering material delivery delays) and Divide the values ​​to obtain the overall performance value Y for that cycle, and use the I-MR (single-value-moving range) control chart to track process stability.

[0079] Linked Diagnosis: When the Y control chart triggers an early warning, the status of the D control chart is analyzed in conjunction with the early warning rules (as shown in Tables 1 and 2 below) to perform a comprehensive diagnosis and locate the root cause of the problem. If the D chart is normal, the problem points to roller wear or material parameters (moisture content); if the D chart is abnormal, the incoming material screening and feeding system should be checked first, as shown in Table 1 (tobacco stem diameter (D)). The rules for using the -S control chart and the rules for using the width-to-diameter ratio (Y) I-MR control chart in Table 2 are as follows:

[0080] D1 1 point exceeds the control limit A single point far exceeds UCL or is lower than LCL 1. Super UCL: Thick steers or steers out of control. 2. Super LCL: Thin steers or broken steers out of control. Emergency Warning: Abnormal incoming material diameter. Immediately check upstream screening equipment to prevent blockage of the stem press or leakage of tobacco stems. D2 Six consecutive points on the same side of the center line The diameter is consistently too large or too small 1. Persistently too large: Coarse stem screen deformed, resulting in larger apertures. 2. Persistently too small: Fine stem screen clogged, or changes in leaf-beating intensity causing an increase in the proportion of fine stems. Trend Warning: The diameter of incoming materials continues to be [large / small]. It is recommended to check the tobacco stem screening equipment and the intensity of leaf threshing to ensure batch consistency of raw materials. D3 Five consecutive points rising or falling The diameter shows a clear unidirectional trend. 1. Continuous increase: Gradual wear and deformation of coarse-grained screens. 2. Continuous decrease: Gradual decrease in fine-grained screen efficiency or gradual change in upstream material structure. Trend Warning: The incoming material diameter shows an [increasing / decreasing] trend, indicating a gradual deterioration of upstream equipment or processes. Preventative maintenance is recommended. D4 Continuous 8 points alternating up and down oscillation The diameter periodically oscillates across the center line. Unstable upstream material supply or feeding system Periodic fluctuation warning: The diameter of the incoming material exhibits periodic oscillations. It is recommended to check the uniformity of tobacco stem collection and blending in the leaf-beating process or the stability of the tobacco stem feeding equipment.

[0081] Table 1

[0082] Y-1 1 point exceeds the control limit The Y value is either extremely high or extremely low at a single point. 1. Extremely high: Measurement error (multiple stem pieces severely overlap or stick together, resulting in an inflated W value). 2. Extremely low: The tobacco stems were not compacted or torn after compaction (resulting in a lower W value). Special Event Warning: Extremely abnormal operating conditions. The materials and images at that moment need to be checked to confirm whether it is a real physical phenomenon or a measurement anomaly. If necessary, optimize and adjust the rehydration and stem-pressing parameters, or strengthen the control of the uniformity of the incoming tobacco stems. Y-2 Six consecutive points below the center line The efficacy of stromal suppression remains low. 1. Insufficient pressure from the pressure rollers, resulting in inadequate calendering of the tobacco stems. 2. Poor material plasticity, insufficient elongation, or leakage during pressing. 3. Continuously small incoming material diameter (judged in conjunction with diagram D). Overall performance warning: The pressing efficiency remains consistently low. First, check and confirm that the gap between the pressing rollers meets the set value. Next, test the material's moisture content and temperature, and evaluate the performance in conjunction with the incoming material diameter data. Y-3 Five consecutive points of decline The efficacy of stromal compression is showing a deteriorating trend. 1. Progressive wear of the pressure rollers leads to a decrease in effective pressure. 2. Malfunction of the rehumidification or heating / humidification system causes a continuous decrease in the material's moisture content / temperature. 3. Changes in the incoming material diameter result in insufficient compaction of coarse material or leakage of pressure in fine material (linkage D-3). Warning of deteriorating trend: Process efficiency continues to decline. It is recommended to confirm the consistency between tobacco stem moisture content and temperature, check the wear and actual clearance of the pressure rollers, and analyze the trend of D. Y-4 MR images out of control The effects of phlegm suppression become more volatile. 1. Extremely uneven mixing of incoming materials (linkage D-4) 2. Drastic fluctuations in moisture content or temperature of materials before pressing 3. Unstable operation of the pressure roller bearings or transmission system 4. Uneven surface of the pressure roller (localized wear, foreign matter adhesion) Stability Warning: Process efficiency fluctuates drastically. Please focus on checking the material morphology and pretreatment consistency, as well as the surface condition of the pressure rollers and the stability of the transmission system.

[0083] Table 2

[0084] In another embodiment, an example of a specific implementation of a method for online quality monitoring and process evaluation of the stem pressing process can be as follows:

[0085] 644 tobacco stems were randomly selected from a certain brand of tobacco from the factory as a sample. After rehydration treatment, the moisture content was controlled at 28% ± 0.5%, and the samples were equilibrated for 2 hours.

[0086] The sample diameter D was measured using a vision system, ranging from 0.78 to 6.42 mm, with an average value of... The value is 3.52 mm, and the overall standard deviation is [missing value]. The value is 1.15. Assuming each subgroup has a sample size of n=100, according to the Central Limit Theorem, the estimated standard deviation of the process subgroup mean is:

[0087] .

[0088] Based on the principle of 3 standard deviations, the lower limit for controlling the diameter D of the incoming tobacco stems is calculated to be DLCL= -3 = 3.52 - 3 × 0.115 = 3.175, control upper limit DUCL = +3 =3.52 + 3 × 0.115 = 3.865. The distribution of the stem diameter D value for a certain brand of tobacco is as follows: Figure 2 As shown.

[0089] Twenty-five random samplings (n=100 each time) were performed on samples collected in the laboratory. The standard deviation S of each sampling was calculated, and the mean of the standard deviations was obtained. The value is 1.175. This is calculated according to the SPC control limits and parameter calculation formula:

[0090] Lower control limit: SLCL = B3 × = =(1- ) × 1.175 = 0.926,

[0091] Control limit: SUCL = B3 × = =(1+ )×1.175=1.424.

[0092] The simulated sampling statistics of the test sample diameter D are shown in Table 3 below, with units of (mm, N=100).

[0093] 1 time 3.413 1.271 14 times 3.628 1.292 2 times 3.509 1.224 15 times 3.380 1.061 3 times 3.509 1.184 16 times 3.581 1.140 4 times 3.480 1.225 17 times 3.402 1.184 5 times 3.465 1.144 18 times 3.610 1.240 6 times 3.519 1.113 19 times 3.540 1.136 7 times 3.374 1.135 20 times 3.507 1.182 8 times 3.552 1.146 21 times 3.512 1.145 9 times 3.485 1.266 22 times 3.465 1.188 10 times 3.581 1.214 23 times 3.505 1.081 11 times 3.665 1.202 24 times 3.372 1.103 12 times 3.624 1.237 25 times 3.589 1.175 13 times 3.609 1.097

[0094] Table 3

[0095] The original D-value distribution was divided into 5 intervals: ≤1.5 mm, 1.5~2.5 mm, 2.5~4.5 mm, 4.5~5.5 mm, and >5.5 mm. Twenty markers were randomly selected from each interval, for a total of 100 markers. A stem pressing experiment was conducted using a laboratory tablet press, with the roller gap set to 0.4 mm (simulating the main process). The actual stem thickness T was measured, and the stem width W was visually measured. The relationship between the stem width W, the stem center thickness T, and the stem diameter D in the simulated pressing process is as follows: Figure 3 As shown.

[0096] Calculate the Y value for each sample, which ranges from 1.176 to 2.515, and the mean value is... The standard deviation is 1.996. The value was 0.318. The Y-values ​​of 65 tobacco stems with diameters ranging from 1.8 to 5.8 mm were relatively stable, ranging from 2.031 to 2.125, with an average value of 0.318. The standard deviation is 2.083. A value of 0.025 effectively reflects the stem pressing characteristics of this tobacco brand, and the stem thickness meets the requirement of ≤1.0mm. The relationship between the thickness-to-diameter ratio Y and the stem diameter D is shown in the graph below. Figure 4 As shown.

[0097] Randomly sample two samples from the Y values ​​in the above interval each time, and calculate the range. Repeat this sampling 30 times to simulate and obtain the moving range mean. The value is 0.0243. Referring to the SPC constant table (when n=2, E2=2.66, D4=3.267), the calculated I-MR chart control limits are:

[0098] YUCL= +E2× =2.083 + 2.66 × 0.0243 = 2.148;

[0099] YLCL= -E2× =2.083-2.66×0.0243=2.018.

[0100] MRUCL = D4× =3.267 × 0.0243 = 0.079. No lower control limit is set.

[0101] The simulated sampling statistics of the Y value of the test samples can be found in Table 4 below.

[0102] 1 time 2.1106 2.0973 0.0133 16 times 2.0879 2.0907 0.0028 2 times 2.1146 2.0936 0.0210 17 times 2.0848 2.0807 0.0041 3 times 2.0779 2.0936 0.0157 18 times 2.0815 2.0971 0.0156 4 times 2.0411 2.0848 0.0436 19 times 2.0936 2.0848 0.0088 5 times 2.0992 2.0722 0.0270 20 times 2.0815 2.0871 0.0056 6 times 2.1221 2.1246 0.0025 21 times 2.0849 2.1066 0.0218 7 times 2.0849 2.0776 0.0073 22 times 2.0378 2.0411 0.0033 8 times 2.1033 2.0971 0.0062 23 times 2.0453 2.0974 0.0521 9 times 2.0741 2.0907 0.0165 24 times 2.0411 2.0453 0.0042 10 times 2.1110 2.1205 0.0095 25 times 2.0685 2.0684 0.0002 11 times 2.1001 2.1114 0.0112 26 times 2.0446 2.0436 0.0010 12 times 2.0314 2.1106 0.0792 27 times 2.1250 2.0890 0.0360 13 times 2.1001 2.0496 0.0506 28 times 2.1039 2.0564 0.0475 14 times 2.1155 2.0406 0.0748 29 times 2.0329 2.0683 0.0354 15 times 2.1246 2.0815 0.0431 30 times 2.0564 2.1250 0.0687

[0103] Table 4

[0104] Additionally, the online system deployment can install a 5-megapixel line scan camera (backlit) above the vibrating conveyor belt in front of the stem pressing machine. Every 20 minutes, it can cut a batch of tobacco stems (one subgroup, containing no less than 100 stems) and output the average diameter of the stems in that subgroup in real time. ) and standard deviation (SD), and plot the D value -S control chart.

[0105] A camera of the same specification is installed above the conveyor belt after the stem pressing machine. Following a 2-minute delay after the material is conveyed by the stem pressing machine, a batch of stem pieces (one subgroup containing no fewer than 100 stem pieces) is captured every 20 minutes, and the average width of the stem pieces is output in real time. The industrial control computer receives data in real time and calculates Y = / And plot the I-MR control chart of the Y value.

[0106] An example of intelligent monitoring and diagnostics can be found where, during a production day, the system detects:

[0107] 1) Control chart representation:

[0108] Y-chart (I-MR): Points 6 to 9 show a continuous downward trend, and point 9 (10:40) is below the lower control limit LCL=2.018. Trigger rule: Y-1 (1 point exceeds the control limit) + Y-3 (5 consecutive points showing a continuous downward trend).

[0109] D diagram ( -S): The value fluctuates between 3.49 and 3.54, all within the range of [3.175, 3.865], and shows no trend. The physical dimensional characteristics of the incoming tobacco stems are normal, ruling out problems such as uneven thickness of the incoming material or abnormal feeding.

[0110] 2) System diagnostic analysis:

[0111] Based on the rules in Table 2, the following warnings and diagnostic suggestions are obtained:

[0112] Warning Level: Level I Warning (Emergency) & Warning of Deteriorating Trend.

[0113] Warning information: The infarction suppression efficacy is extremely abnormal and shows a continuous downward trend.

[0114] Root cause diagnosis recommendations:

[0115] Since the D diagram is stable, the influence of the incoming material diameter is excluded.

[0116] Possible cause 1: Insufficient pressure of the pressure roller (hydraulic system failure).

[0117] Possible cause 2: Poor material plasticity and insufficient elongation (due to moisture regain or heating system failure, resulting in a decrease in moisture content / temperature).

[0118] Possible cause 3: Wear of the pressure roller (usually gradual, which is possible based on the Y-3 trend, but a rapid decrease points to a sudden change in process parameters).

[0119] 3) On-site investigation and handling:

[0120] Operational actions:

[0121] Check the pressure roller gap: The operator checked the mechanical gap setting, which showed 0.4mm, and there was no change.

[0122] Check the pressure roller pressure: The pressure gauge reading of the hydraulic system is normal.

[0123] Check the moisture content of the material (key point): The operator used a rapid moisture meter to measure the moisture content of the tobacco stems before pressing. The reading was 25.7%, which deviated from the process standard requirement of 28% ± 0.5%.

[0124] Fault location identified: Foreign objects were found blocking the valve of the heating and humidifying steam pipeline, resulting in insufficient steam output.

[0125] Adjustment measures:

[0126] Clean immediately: Remove foreign objects from the valve and restore normal steam supply.

[0127] Parameter adjustment: In the system process parameter optimization unit, temporarily increase the temperature set by the heating and humidification PID control to accelerate the recovery of material moisture content.

[0128] Waste removal: Unqualified stem pieces generated between 09:40 and 11:00 are marked and isolated to prevent them from flowing into the next process.

[0129] 4) Restore to normal and verify

[0130] Adjustment effect:

[0131] After a 10-minute adjustment (material flow time), the moisture content of the tobacco stems before pressing rose to 27.8%, and the Yavg value of subgroup 11 (11:20) returned to near the center line (2.09 ∈ [2.008, 2.158]). The MR value increased significantly, but this was caused by active adjustment and not by an abnormality in the processing. The system lifted the warning and indicated that "the process has returned to a stable state".

[0132] Follow-up actions:

[0133] The system automatically records this abnormal event (time, type, cause of low moisture content, and handling solution) to the historical database. Among these, the quality monitoring of the stem pressing process – Y-value (I-MR control chart) – can be viewed as follows: Figure 5 As shown, the D value ( -S control chart) can be like Figure 6 As shown.

[0134] Please refer to the following. Figure 7 , Figure 7 A schematic diagram of a system for online quality monitoring and process evaluation of a stem pressing process, as provided in an embodiment of this specification, is shown. It should be noted that... Figure 7 The online quality monitoring and process evaluation system for the pressing stem process shown is used to execute this manual. Figure 1 The methods shown in the embodiments are illustrated for ease of explanation, showing only the parts related to the embodiments of this specification. For specific technical details not disclosed, please refer to this specification. Figure 1 The example shown.

[0135] like Figure 7 As shown, the online quality monitoring and process evaluation system for the pressing stem process can include at least:

[0136] The preprocessing module S702 is used to perform sampling preprocessing on tobacco stem raw materials to generate tobacco stem samples;

[0137] The image acquisition module S704 is used to lay the tobacco stem sample flat, acquire a top view image, calculate the equivalent diameter of the tobacco stem in the top view image, and divide the tobacco stem sample into multiple diameter intervals based on the equivalent diameter of the tobacco stem;

[0138] The tobacco stem processing module S706 is used to simulate pressing the tobacco stem sample, collect the center thickness of the tobacco stem sample after simulated pressing, and flatten the tobacco stem sample, collect the width of the flattened tobacco stem sample.

[0139] The data processing module S708 is used to establish a material volume conservation relationship for the tobacco stem sample based on the fact that the volume of the tobacco stem sample remains unchanged before and after pressing. The volume calculation formula is as follows: Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness. Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined. The elongation characteristics are: Y = W / D, where Y is the elongation characteristics of the tobacco stem and is negatively linearly correlated with the center thickness T.

[0140] The control module S710 is used to generate a control benchmark for tobacco stem detection based on the equivalent diameter and extension characteristics of the tobacco stem.

[0141] In another embodiment, an online quality monitoring and process evaluation system for the stem pressing process further includes:

[0142] The statistics module is used to calculate the mean and standard deviation of the equivalent diameter of the tobacco stems in the tobacco stem samples.

[0143] The standard error module is used to calculate the standard error of the subgroup mean by combining the standard deviation and the preset subgroup size of the tobacco stem samples.

[0144] The D-value mean control chart module is used to set the confidence coefficient and, in combination with the mean and standard error, determine the upper and lower control limits of the D-value mean control chart for the equivalent diameter of the tobacco stem sample.

[0145] The D-value standard deviation control chart module is used to synchronously establish the D-value standard deviation control chart. By calculating the mean of the standard deviations of all subgroups and combining it with the SPC standard constant of the corresponding subgroup size, the upper and lower control limits of the D-value standard deviation control chart are calculated.

[0146] The monitoring module for tobacco stem quality monitoring indicators is used to monitor tobacco stem quality monitoring indicators by combining the D-value mean control chart and the D-value standard deviation control chart.

[0147] Those skilled in the art will clearly understand that the technical solutions of the embodiments in this specification can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware capable of independently performing or cooperating with other components to perform a specific function. The hardware may be, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0148] Each processing unit and / or module in the embodiments of this specification can be implemented by an analog circuit that implements the functions described in the embodiments of this specification, or by software that executes the functions described in the embodiments of this specification.

[0149] See Figure 8 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this specification, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 8 As shown, the electronic device 800 may include: at least one central processing unit 801, at least one network interface 804, user interface 803, memory 805, and at least one communication bus 802.

[0150] The communication bus 802 is used to enable communication between these components.

[0151] The user interface 803 may include a display screen and a camera. Optionally, the user interface 803 may also include a standard wired interface and a wireless interface.

[0152] The network interface 804 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0153] The processor 801 may include one or more processing cores. The processor 801 connects to various parts within the electronic device 800 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 805, and by calling data stored in the memory 805. Optionally, the processor 801 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 801 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 801 and may be implemented as a separate chip.

[0154] The memory 805 may include random access memory (RAM) or read-only memory. Optionally, the memory 805 may include a non-transitory computer-readable storage medium. The memory 805 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 805 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 805 may also be at least one storage system located remotely from the aforementioned processor 801. Figure 8 As shown, the memory 805, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0155] exist Figure 8In the illustrated electronic device 800, the user interface 803 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 801 can be used to call the image-based interactive application stored in the memory 805 and specifically perform the following operations:

[0156] The tobacco stem raw materials are sampled and pre-treated to generate tobacco stem samples;

[0157] The tobacco stem sample is laid flat, a top view image is captured, the equivalent diameter of the tobacco stem in the top view image is calculated, and based on the equivalent diameter of the tobacco stem, the tobacco stem sample is divided into multiple diameter intervals;

[0158] The tobacco stem sample was subjected to simulated pressing, and the center thickness of the tobacco stem sample after simulated pressing was collected. The tobacco stem sample was also flattened, and the width of the flattened tobacco stem sample was collected.

[0159] Based on the fact that the volume of the tobacco stem sample remains unchanged before and after pressing, a material volume conservation relationship for the tobacco stem sample is established, and its volume calculation formula is as follows:

[0160] ,

[0161] Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness.

[0162] Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined, and the elongation characteristics are:

[0163] Y = W / D,

[0164] Wherein, Y represents the elongation characteristic of the tobacco stem, which is negatively linearly correlated with the center thickness T;

[0165] Based on the equivalent diameter and extension characteristics of the tobacco stem, a control benchmark for tobacco stem detection is generated.

[0166] As an optional embodiment of this specification, the step of generating a control benchmark for tobacco stem detection based on the equivalent diameter and elongation characteristics of the tobacco stem includes:

[0167] Based on the equivalent diameter of the tobacco stem, establish -S control chart, with the aforementioned -S control charts are used to monitor tobacco stem quality indicators. The process of creating a -S control chart includes:

[0168] The mean and standard deviation of the equivalent diameter of the tobacco stems in the tobacco stem samples were statistically analyzed.

[0169] The standard error of the subgroup mean is calculated by combining the standard deviation and the preset subgroup size of the tobacco stem samples;

[0170] By setting confidence coefficients and combining the mean and standard error, the upper and lower control limits of the control chart for the D-value mean of the equivalent diameter of the tobacco stem sample are determined.

[0171] A D-value standard deviation control chart is established simultaneously. By calculating the mean of the standard deviations of all subgroups and combining it with the SPC standard constant of the corresponding subgroup size, the upper and lower control limits of the D-value standard deviation control chart are calculated.

[0172] By combining the aforementioned D-value mean control chart and D-value standard deviation control chart, the quality monitoring indicators of tobacco stems are monitored.

[0173] As an optional embodiment of this specification, the step of generating a control benchmark for tobacco stem detection based on the equivalent diameter and elongation characteristics of the tobacco stem includes:

[0174] Based on the stretching characteristics of the tobacco stems, an I-MR control chart is established. The I-MR control chart is used to monitor stem compression quality indicators. The process for establishing the I-MR control chart includes:

[0175] Based on the simulated stromal pressing requirements, -S control chart, stretching characteristic stability screening of effective tobacco stem samples, and statistical analysis of the mean stretching characteristic of the effective tobacco stem samples as the center line of the I control chart;

[0176] Calculate the moving range of the adjacent samples of the effective sample, and calculate the mean of the moving range;

[0177] Based on the SPC standard constant of the subgroup size, and combined with the mean of the extension characteristics and the mean of the moving range, the upper and lower control limits of the I control chart are calculated, and the lower control limit of the I control chart is the core control item.

[0178] Calculate the upper and lower limits of control for the MR control chart based on the SPC standard constant and the mean of the moving range for the subgroup size.

[0179] Match with the -The same subgroup cycle of the -S control chart, based on the early warning system, combined with the I control chart and MR control chart, is used to monitor the quality monitoring indicators of the strangulation.

[0180] As an optional embodiment of this specification, the early warning system is a three-level early warning system, including:

[0181] Based on the control chart I, monitor the overall level of tobacco stem elongation characteristics and identify abnormal thicknesses, triggering a level one warning.

[0182] Based on the MR control chart, the continuous fluctuations of the tobacco stem extension characteristics are monitored, and trend deterioration and stability anomalies are identified, triggering level two and level three early warnings.

[0183] As an optional embodiment of this specification, the method further includes:

[0184] When the I-MR control chart triggers an early warning, the corresponding mechanism is activated simultaneously. -S control chart state, based on the I-MR control chart state and -S control chart status determination indicates abnormal incoming material characteristics or abnormal pressing process.

[0185] As an optional embodiment of this specification, the method further includes:

[0186] The elongation characteristics of tobacco stems under different pressing processes in the simulated pressing are calculated, and the pressing process with the larger elongation characteristics is selected as the preferred process for the simulated pressing.

[0187] This specification also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0188] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this specification is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this specification. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this specification.

[0189] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0190] In the embodiments provided in this specification, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between systems or units may be electrical or other forms.

[0191] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0193] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this specification, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0194] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0195] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

Claims

1. A method for online quality monitoring and process evaluation of the stem pressing process, the method comprising: The tobacco stem raw materials are sampled and pre-treated to generate tobacco stem samples; The tobacco stem sample is laid flat, a top view image is captured, the equivalent diameter of the tobacco stem in the top view image is calculated, and based on the equivalent diameter of the tobacco stem, the tobacco stem sample is divided into multiple diameter intervals; The tobacco stem sample was subjected to simulated pressing, and the center thickness of the tobacco stem sample after simulated pressing was collected. The tobacco stem sample was also flattened, and the width of the flattened tobacco stem sample was collected. Based on the fact that the volume of the tobacco stem sample remains unchanged before and after pressing, a material volume conservation relationship for the tobacco stem sample is established, and its volume calculation formula is as follows: ， Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness. Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined, and the elongation characteristics are: Y = W / D, Wherein, Y represents the elongation characteristic of the tobacco stem, which is negatively linearly correlated with the center thickness T; Based on the equivalent diameter and extension characteristics of the tobacco stem, a control benchmark for tobacco stem detection is generated.

2. The method according to claim 1, characterized in that, The process of generating control standards for tobacco stem detection based on the equivalent diameter and elongation characteristics of the tobacco stem includes: Based on the equivalent diameter of the tobacco stem, establish -S control chart, with the aforementioned -S control charts are used to monitor tobacco stem quality indicators. The process of creating a -S control chart includes: The mean and standard deviation of the equivalent diameter of the tobacco stems in the tobacco stem samples were statistically analyzed. The standard error of the subgroup mean is calculated by combining the standard deviation and the preset subgroup size of the tobacco stem samples; By setting confidence coefficients and combining the mean and standard error, the upper and lower control limits of the control chart for the D-value mean of the equivalent diameter of the tobacco stem sample are determined. A D-value standard deviation control chart is established simultaneously. By calculating the mean of the standard deviations of all subgroups and combining it with the SPC standard constant of the corresponding subgroup size, the upper and lower control limits of the D-value standard deviation control chart are calculated. By combining the aforementioned D-value mean control chart and D-value standard deviation control chart, the quality monitoring indicators of tobacco stems are monitored.

3. The method according to claim 2, characterized in that, The process of generating control standards for tobacco stem detection based on the equivalent diameter and elongation characteristics of the tobacco stem includes: Based on the stretching characteristics of the tobacco stems, an I-MR control chart is established. The I-MR control chart is used to monitor stem compression quality indicators. The process for establishing the I-MR control chart includes: Based on the simulated stromal pressing requirements, -S control chart, stretching characteristic stability screening of effective tobacco stem samples, and statistical analysis of the mean stretching characteristic of the effective tobacco stem samples as the center line of the I control chart; Calculate the moving range of the adjacent samples of the effective sample, and calculate the mean of the moving range; Based on the SPC standard constant of the subgroup size, and combined with the mean of the extension characteristics and the mean of the moving range, the upper and lower control limits of the I control chart are calculated, and the lower control limit of the I control chart is the core control item. Calculate the upper and lower limits of control for the MR control chart based on the SPC standard constant and the mean of the moving range for the subgroup size. Match with the -The same subgroup cycle of the -S control chart, based on the early warning system, combined with the I control chart and MR control chart, is used to monitor the quality monitoring indicators of the strangulation.

4. The method according to claim 3, characterized in that, The aforementioned early warning system is a three-level early warning system, including: Based on the control chart I, monitor the overall level of tobacco stem elongation characteristics and identify abnormal thicknesses, triggering a level one warning. Based on the MR control chart, the continuous fluctuations of the tobacco stem extension characteristics are monitored, and trend deterioration and stability anomalies are identified, triggering level two and level three early warnings.

5. The method according to claim 3, characterized in that, The method further includes: When the I-MR control chart triggers an early warning, the corresponding mechanism is activated simultaneously. -S control chart state, based on the I-MR control chart state and -S control chart status determination indicates abnormal incoming material characteristics or abnormal pressing process.

6. The method according to claim 1, characterized in that, The method further includes: The elongation characteristics of tobacco stems under different pressing processes in the simulated pressing are calculated, and the pressing process with the larger elongation characteristics is selected as the preferred process for the simulated pressing.

7. A system for online quality monitoring and process evaluation of the pressing stem process, characterized in that, The system includes; The preprocessing module is used to sample and preprocess tobacco stem raw materials to generate tobacco stem samples; The image acquisition module is used to lay the tobacco stem sample flat, acquire a top view image, calculate the equivalent diameter of the tobacco stem in the top view image, and divide the tobacco stem sample into multiple diameter intervals based on the equivalent diameter of the tobacco stem; The tobacco stem processing module is used to simulate pressing the tobacco stem sample, collect the center thickness of the tobacco stem sample after simulated pressing, and flatten the tobacco stem sample to collect the width of the flattened tobacco stem sample. The data processing module is used to establish a material volume conservation relationship for the tobacco stem samples based on the fact that the volume of the tobacco stem samples remains unchanged before and after pressing. The volume calculation formula is as follows: Where D is the equivalent diameter of the tobacco stem, L is the length of the tobacco stem, W is the width of the flattened tobacco stem, and T is the center thickness. Based on the volume calculation formula, the elongation characteristics of the tobacco stem are determined. The elongation characteristics are: Y = W / D, where Y is the elongation characteristics of the tobacco stem and is negatively linearly correlated with the center thickness T. The control module is used to generate a control benchmark for tobacco stem detection based on the equivalent diameter and extension characteristics of the tobacco stem.

8. The method according to claim 7, characterized in that, The system also includes: The statistics module is used to calculate the mean and standard deviation of the equivalent diameter of the tobacco stems in the tobacco stem samples. The standard error module is used to calculate the standard error of the subgroup mean by combining the standard deviation and the preset subgroup size of the tobacco stem samples. The D-value mean control chart module is used to set the confidence coefficient and, in combination with the mean and standard error, determine the upper and lower control limits of the D-value mean control chart for the equivalent diameter of the tobacco stem sample. The D-value standard deviation control chart module is used to synchronously establish the D-value standard deviation control chart. By calculating the mean of the standard deviations of all subgroups and combining it with the SPC standard constant of the corresponding subgroup size, the upper and lower control limits of the D-value standard deviation control chart are calculated. The monitoring module for tobacco stem quality monitoring indicators is used to monitor tobacco stem quality monitoring indicators by combining the D-value mean control chart and the D-value standard deviation control chart.

9. An electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the method as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of claims 1-6.

Images