Cut stem thickness prediction method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a cut stem thickness prediction method, electronic equipment, a storage medium and a program product, and relates to the technical field of cigarette production.The method comprises the steps that the actually-measured thickness and the actually-measured moisture content of a sample cut stem are input into a first density prediction model, and the predicted density of the sample cut stem is obtained; the first density prediction model is used for representing a function relationship among the stem density, the stem thickness and the stem moisture content; according to the difference between the predicted density and the actually measured density of the sample cut stems, correcting the first density prediction model to obtain a second density prediction model; constructing a cut stem thickness prediction model based on the second density prediction model, wherein the cut stem thickness prediction model is used for representing a function relationship among the cut stem thickness, the cut stem density and the cut stem moisture content; and inputting the actually measured density and the actually measured moisture content of the target cut stem into the cut stem thickness prediction model to obtain the predicted thickness of the target cut stem. According to the invention, the accuracy and stability of cut stem thickness prediction can be improved.

Description

Technical Field

[0001] The present invention relates to the field of cigarette production technology, and in particular to a method for predicting stem thickness, electronic equipment, storage medium and program product. Background Technology

[0002] In cigarette production, stems are an important component of tobacco, and their processing quality directly affects the sensory quality of cigarettes and the stability of subsequent processes. Stem thickness is one of the key control parameters in the stem-cutting process, typically requiring control within a certain range. Therefore, accurate detection and evaluation of stem thickness is of great significance for production process control.

[0003] In the current production process, the acquisition of stem thickness often relies on manual inspection or experience-based judgment, which has low inspection efficiency and insufficient stability. It is difficult to obtain more accurate stem thickness information quickly and stably during the production process, which is not conducive to timely and effective control of stem thickness. Summary of the Invention

[0004] This invention provides a method for predicting stem thickness, an electronic device, a storage medium, and a program product, which can improve the accuracy and stability of stem thickness prediction.

[0005] In a first aspect, the stem thickness prediction method provided in the embodiments of the present invention includes: The measured thickness and measured moisture content of the sample stem are input into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density and stem thickness and stem moisture content. Based on the difference between the predicted density and the measured density of the sample filaments, the first density prediction model is modified to obtain the second density prediction model. A stem thickness prediction model is constructed based on the second density prediction model. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density and stem moisture content. The measured density and measured moisture content of the target stem are input into the stem thickness prediction model to obtain the predicted thickness of the target stem.

[0006] Secondly, the filament thickness prediction device provided in the embodiments of the present invention includes: The density prediction module is used to input the measured thickness and measured moisture content of the sample stem into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density and stem thickness and stem moisture content. The density model correction module is used to correct the first density prediction model based on the difference between the predicted density and the measured density of the sample filaments, so as to obtain the second density prediction model. The thickness model construction module is used to construct a stem thickness prediction model based on the second density prediction model. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density and stem moisture content. The thickness prediction module is used to input the measured density and measured moisture content of the target filament into the filament thickness prediction model to obtain the predicted thickness of the target filament.

[0007] Thirdly, the electronic device provided in the embodiments of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the filament thickness prediction method as described in any embodiment of the present invention.

[0008] Fourthly, the computer-readable storage medium provided in the embodiments of the present invention stores a computer program thereon, which, when executed by a processor, implements the filament thickness prediction method as described in any embodiment of the present invention.

[0009] Fifthly, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the filament thickness prediction method as described in any embodiment of the present invention.

[0010] In this embodiment of the invention, the predicted density of the sample filaments is obtained by inputting the measured thickness and moisture content of the sample filaments into a first density prediction model. The first density prediction model is used to characterize the functional relationship between filament density, filament thickness, and filament moisture content, providing basic data for subsequent model correction and thickness prediction. Based on the difference between the predicted density and the measured density of the sample filaments, the first density prediction model is corrected to obtain a second density prediction model, which can effectively reduce the impact of measurement fluctuations on model accuracy and improve the stability and accuracy of the model. Based on the second density prediction model, a filament thickness prediction model is constructed. The filament thickness prediction model is used to characterize the functional relationship between filament thickness, filament density, and filament moisture content, enabling the conversion from a density model to a thickness prediction model while maintaining the model's conformity to the actual process causal relationship, thus improving the reliability and prediction accuracy of the thickness prediction model. By inputting the measured density and moisture content of the target filament into the filament thickness prediction model, the predicted thickness of the target filament is obtained. This allows for the rapid acquisition of filament thickness results during production using readily available detection data, reducing the time required for traditional manual inspection, improving the efficiency of filament thickness detection, and facilitating real-time monitoring and process control during production. Furthermore, the filament thickness prediction method proposed in this invention does not directly establish a filament thickness prediction model based on filament density and moisture content. Instead, it first constructs a density prediction model that conforms to the physical laws of filament processing, and then corrects the model by analyzing the difference between the predicted and measured densities. Based on this, a filament thickness prediction model is then constructed. This invention fully considers the physical causal relationships between various parameters during filament processing. Since filament density is the result of the combined effects of filament thickness and moisture content, prioritizing the establishment of a density prediction model more accurately reflects the actual changes during production. After obtaining a stable and reliable second density prediction model, a filament thickness prediction model is constructed through model transformation, ensuring that the final filament thickness prediction relationship conforms to the actual process mechanism and has good prediction accuracy. Compared to conventional methods that directly establish a model for predicting stem thickness, this invention achieves more accurate prediction of stem thickness by establishing a density model, correcting the model, and then back-calculating the thickness. This allows for rapid acquisition of stem thickness information during production, improving the accuracy of stem thickness control and the stability of the production process. Attached Figure Description

[0011] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1This is a schematic flowchart of the stem thickness prediction method provided in an embodiment of the present invention; Figure 2 This is another flowchart illustrating the method for predicting stem thickness provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the structure of the filament thickness prediction device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Figure 1 This is a schematic flowchart of a stem thickness prediction method provided in an embodiment of the present invention. The stem thickness prediction method provided in this embodiment is applicable to scenarios requiring stem thickness prediction in cigarette production. This stem thickness prediction method can be executed by a stem thickness prediction device provided in this embodiment, which can be implemented using software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, such as a computer or server. The following embodiment illustrates the integration of the stem thickness prediction device into an electronic device. See reference... Figure 1 The method for predicting the thickness of the filament in this embodiment may include the following steps: Step 101: Input the measured thickness and measured moisture content of the sample stem into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density and stem thickness and stem moisture content.

[0016] The term "sample stem filament" refers to the stem filament sample used to establish or modify the prediction model; that is, multiple batches of stem filament data collected during the production process and tested for thickness, moisture content, and density. "Measured thickness" refers to the stem filament thickness value obtained through actual testing methods. "Measured moisture content" refers to the actual proportion of water contained in the stem filament as measured by moisture detection methods. The first density prediction model is a regression model established based on the measured thickness, measured moisture content, and measured density of the sample stem filaments to predict stem filament density, characterizing the functional relationship between stem filament density, thickness, and moisture content. "Predicted density" refers to the stem filament density value calculated by inputting the measured thickness and measured moisture content of the sample stem filaments into the first density prediction model. "Functional relationship" refers to the correspondence established between different variables through mathematical expressions.

[0017] Specifically, the thickness and moisture content of the sample stems are measured and then substituted into the pre-established first density prediction model to calculate the corresponding predicted stem density value.

[0018] For example, suppose the first density prediction model is There are 30 batches of sample stems, using K i The thickness of the i-th batch of stems is represented by X. i Let represent the moisture content of the i-th batch of stems. Then, input the measured thickness and measured moisture content of the stems from 30 batches of samples into the first density prediction model. The predicted density of stem fibers from 30 batches of samples can be obtained. .

[0019] Step 102: Based on the difference between the predicted density and the measured density of the sample filaments, the first density prediction model is corrected to obtain the second density prediction model.

[0020] The second density prediction model is a regression model established based on the measured thickness and moisture content of the sample stems and the corrected predicted density. Its prediction results are closer to the actual detection results than those of the first density prediction model.

[0021] Specifically, in the actual testing process, the measured density of the stem fibers... The measured density is not only related to the actual physical density of the stems, but also affected by environmental factors such as filling error, weighing error, and moisture evaporation error, leading to fluctuations in the measured density data. For example, it exhibits a systematic deviation from the true value in a regular manner. To reduce the impact of this fluctuation on the model's accuracy, the predicted density is uniformly corrected by calculating the error values ​​between the predicted and measured densities, such as the residual sum of squares, root mean square error, and mean absolute error. This effectively eliminates this systematic deviation, allowing the corrected density result to more accurately reflect the actual density of the stems. Furthermore, a second density prediction model with better fitting performance is reconstructed using the corrected predicted density and the measured thickness and moisture content of the sample stems, thereby improving the accuracy of subsequent stem thickness predictions.

[0022] Step 103: Construct a stem thickness prediction model based on the second density prediction model. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density, and stem moisture content.

[0023] The stem thickness prediction model is a mathematical model built on the second density prediction model. It is used to convert the density and moisture content information of stems into predicted values ​​of stem thickness, so as to achieve rapid and accurate prediction of stem thickness.

[0024] Specifically, based on the measured thickness, measured moisture content, and corrected predicted density of the sample stems, a stem thickness prediction model is directly established, with stem thickness as the dependent variable and stem moisture content and stem density as independent variables. This type of modeling is considered anti-causal, violating the inherent causal relationship of the physical processing of stem fibers. Furthermore, when there is a strong interdependence between the dependent variable (stem fiber thickness) and the independent variables (stem fiber moisture content and density), the directly fitted model may suffer from poor stability and low prediction accuracy. To overcome these shortcomings, this embodiment utilizes a pre-established second density prediction model that conforms to physical causal relationships. Construct a model for predicting stem thickness. .

[0025] Step 104: Input the measured density and measured moisture content of the target filament into the filament thickness prediction model to obtain the predicted thickness of the target filament.

[0026] The target stem wire refers to the specific stem wire whose thickness needs to be predicted during the production process; it can be a batch or a single stem wire. Predicted thickness refers to the stem wire thickness value calculated by inputting the measured density and moisture content of the target stem wire into the stem wire thickness prediction model.

[0027] Specifically, by inputting the measured density and measured moisture content of the target filament into the filament thickness prediction model, the model calculates and outputs the predicted thickness of the target filament based on the established functional relationship.

[0028] In this embodiment, the measured thickness and moisture content of the sample stem are input into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density, stem thickness, and stem moisture content, providing basic data for subsequent model correction and thickness prediction. Based on the difference between the predicted density and the measured density of the sample stem, the first density prediction model is corrected to obtain the second density prediction model, which can effectively reduce the impact of measurement fluctuations on model accuracy and improve the stability and accuracy of the model. Based on the second density prediction model, a stem thickness prediction model is constructed. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density, and stem moisture content, enabling the conversion from a density model to a thickness prediction model while maintaining the model's conformity to the actual process causal relationship, thus improving the reliability and prediction accuracy of the thickness prediction model. By inputting the measured density and moisture content of the target filament into the filament thickness prediction model, the predicted thickness of the target filament is obtained. This allows for the rapid acquisition of filament thickness results during production using readily available detection data, reducing the time required for traditional manual inspection, improving the efficiency of filament thickness detection, and facilitating real-time monitoring and process control during production. Furthermore, the filament thickness prediction method proposed in this invention does not directly establish a filament thickness prediction model based on filament density and moisture content. Instead, it first constructs a density prediction model that conforms to the physical laws of filament processing, and then corrects the model by analyzing the difference between the predicted and measured densities. Based on this, a filament thickness prediction model is then constructed. This invention fully considers the physical causal relationships between various parameters during filament processing. Since filament density is the result of the combined effects of filament thickness and moisture content, prioritizing the establishment of a density prediction model more accurately reflects the actual changes during production. After obtaining a stable and reliable second density prediction model, a filament thickness prediction model is constructed through model transformation, ensuring that the final filament thickness prediction relationship conforms to the actual process mechanism and has good prediction accuracy. Compared to conventional methods that directly establish a model for predicting stem thickness, this invention achieves more accurate prediction of stem thickness by establishing a density model, correcting the model, and then back-calculating the thickness. This allows for rapid acquisition of stem thickness information during production, improving the accuracy of stem thickness control and the stability of the production process.

[0029] Figure 2 This is another flowchart illustrating the filament thickness prediction method provided in this embodiment of the invention, as shown below. Figure 2 As shown, the filament thickness prediction method in this embodiment may include: Step 201: Input the measured thickness and measured moisture content of the sample stem into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between the stem density, stem thickness and stem moisture content.

[0030] Optionally, the first density prediction model is obtained as follows: based on the measured thickness, measured moisture content and measured density of the sample stems, a regression model is constructed with stem thickness and stem moisture content as independent variables and stem density as dependent variable, thus obtaining the first density prediction model.

[0031] Specifically, using the measured thickness, moisture content, and density of stems from multiple samples as modeling samples, a functional relationship model between stem density and stem thickness and moisture content is established through regression analysis, thus forming the first density prediction model, which can be expressed as follows: More specifically, it can be expressed as .

[0032] Optionally, the measured thickness of the sample stem filaments is obtained by the following method: feeding the silicone rod and the tobacco stem together into a filament cutter for cutting, collecting the silicone sheets obtained after cutting; measuring the thickness of multiple silicone sheets and calculating the average thickness, and using the average thickness as the measured thickness of the sample stem filaments of the corresponding batch.

[0033] A silicone rod is a rod-shaped object made of a flexible and easily cut silicone material. It is used in the shredding process, fed into a shredder along with the tobacco stems to record the cutting thickness. A shredder is a device used to cut tobacco stems into shreds; its cutting parameters determine the thickness characteristics of the shreds. A silicone sheet is a thin sheet structure formed after the silicone rod is cut by the shredder; its thickness reflects the actual cutting thickness at a given moment. The average thickness is the result obtained by statistically calculating the thickness values ​​of multiple silicone sheets, used to reduce the impact of single measurement errors on the final result.

[0034] Specifically, during the shredding process, silicone rods and tobacco stems are simultaneously fed into the shredder for cutting. Because silicone material can accurately record the actual cutting gap of the blade during the cutting process, the thickness of the resulting silicone sheet reflects the cutting thickness at that specific moment. Subsequently, the thickness of multiple silicone sheets is measured, and the measured thickness data are averaged to reduce the impact of accidental measurement errors or fluctuations in a single cut. Finally, the calculated average thickness is used as the measured thickness of the tobacco stems in the corresponding batch, thus obtaining more stable and representative thickness data for subsequent model construction and analysis.

[0035] For example, assuming there are 30 batches of stem shreds, during the production of these 30 batches, silica gel slices are collected from each batch under ideal conditions (continuous and stable production, moisture content fluctuation within ±0.5% of the set value after cutting, and no wet clumps). The preparation method for the slices is as follows: First, randomly set the stem shred thickness value on the equipment, selecting a value within the range of 0.08-0.14 mm. Second, place a 3-5 cm long silica gel rod into the stem shredder's feed chute. Then, use a micrometer to measure the thickness of 50 cut silica gel slices that meet the requirements (avoiding the ends of the silica gel rod). The average thickness h of these samples is then taken as the measured thickness value of that batch of stem shreds. h is the average thickness, S i Where n is the thickness of each silicone sheet and n is the number of samples.

[0036] Optionally, the measured moisture content of the sample stem filaments is obtained as follows: a stem filament sample is collected at the outlet of the filament cutter; the collected stem filament sample is placed in a dry container of known mass and weighed to obtain the wet weight of the sample; the container containing the stem filament sample is placed in an oven and dried to constant weight at a preset temperature; the container is removed and placed in a desiccator to cool to room temperature and weighed again to obtain the dry weight of the sample; based on the wet weight and dry weight of the sample, the measured moisture content of the sample stem filaments is calculated.

[0037] The shredder outlet refers to the position where the shredder outputs shredded stems after cutting, allowing for the acquisition of a shredded stem sample in its current production state. A drying container is a container used to hold, weigh, and dry samples; its own mass has been pre-determined. Sample wet weight refers to the mass of the collected shredded stem sample measured after being placed in the drying container, before drying. An oven is a device used to heat and dry samples, controlling the temperature to evaporate moisture. Constant weight refers to a state where the sample remains essentially unchanged after multiple weighings during continuous drying, indicating that the moisture in the sample has been largely removed. A desiccator is a device used to cool samples in a low-humidity environment to prevent the sample from reabsorbing moisture from the air during cooling. Sample dry weight refers to the mass of the sample obtained after drying and cooling to room temperature, primarily reflecting the mass of the solid matter in the sample.

[0038] Specifically, a sample of stem shreds is collected at the discharge port of the shredder to ensure that the obtained sample reflects the moisture content of the stem shreds under the current production conditions. The collected stem shred sample is then placed in a pre-weighed drying container and weighed to obtain the sample's mass in its moisture-containing state, i.e., the sample's wet weight. Next, the container containing the stem shred sample is placed in an oven and dried at a preset temperature to allow the moisture in the sample to gradually evaporate, continuing drying until the mass is essentially stable, i.e., at constant weight. Afterward, the container is removed and placed in a desiccator to cool to room temperature to prevent the sample from absorbing moisture from the environment during cooling, and the sample is weighed again to obtain the sample's dry weight. The proportion of moisture in the sample is calculated based on the difference between the sample's wet weight and dry weight, thus obtaining the measured moisture content of the stem shreds for subsequent model construction and data analysis. Furthermore, the measured moisture content of the target stem shreds can also be obtained using this method.

[0039] For example, a sample of stem shreds is collected at the discharge port of the shredder and placed in a dry container of known mass for weighing. Assuming the dry container weighs 50.000g, the total mass of the container and the stem sample is measured to be 58.500g, indicating a wet weight of 8.500g. The dry container containing the stem sample is then placed in an oven and dried at a preset temperature (e.g., 105°C) until a constant weight is reached. After drying, the container is removed and cooled to room temperature in a desiccator, and weighed again. Assuming the total mass of the container and the stem sample is now 57.000g, the dry weight of the stem sample is 7.000g. Based on the sample's wet and dry weights, the measured moisture content of the stem sample can be calculated, for example, using the following formula: Sample moisture content = (Sample wet weight - Sample dry weight) ÷ Sample wet weight × 100%. Substituting the above data into the calculation, we get: Sample moisture content = (8.500 - 7.000) ÷ 8.500 × 100% ≈ 17.65%. That is, the measured moisture content of this batch of stem samples is approximately 17.65%.

[0040] Optionally, the measured density of the sample stem filaments is obtained as follows: a container with a standard volume is filled with the stem filament sample at the outlet of the filament cutter and weighed to obtain the weight of the stem filament sample; the measured density of the sample stem filaments is determined based on the ratio of the weight to the standard volume.

[0041] A standard volume container refers to a measuring container with a known and fixed internal volume, used to hold stem samples so that stem density can be calculated through the correspondence between volume and mass. The weight of the stem sample refers to the actual mass of the stem obtained by weighing the container filled with the sample and subtracting the container's own mass. Standard volume refers to the known volume parameter inside the container, such as a fixed volume determined during container design, used in density calculations. A ratio refers to the numerical relationship between two quantities, specifically the ratio between the weight of the stem sample and the standard volume of the container.

[0042] Specifically, a container with a known standard volume is filled with the fibrous stem sample, ensuring the container is completely filled. The container is then weighed, and the actual weight of the fibrous stem sample is calculated based on the weighing result. After obtaining the weight of the fibrous stem sample and the standard volume of the container, the measured density of the fibrous stem sample can be calculated using the density calculation formula (density equals the ratio of mass to volume). In this way, a measured density reflecting the fibrous stem can be quickly obtained using simple mass measurement and known volume parameters, thus providing fundamental data for the establishment of subsequent fibrous stem density prediction models or fibrous stem thickness prediction models. Furthermore, the measured density of a target fibrous stem can also be obtained using this method.

[0043] For example, samples are extracted from the discharge trough of a shredder using a specially designed cylindrical tube (e.g., 5 cm inner diameter, 10 cm height, and 196.3 cm³ volume). 3 The density of a cylindrical tube was tested by filling it with stems (the tube was gently shaken while filling to ensure full filling, and the filling position was such that the stems were flush with the edge of the tube's inlet). After all the stems were poured out, they were weighed with an accuracy of 0.001g to obtain the mass (m) of each stem sample. i (i=1,…, n), obtained through the density formula The measured density of each stem sample was calculated. (i=1,…, n), to prevent moisture loss from the stem samples, the total time for sampling and weighing each sample must be within a certain range, for example, no more than 20 seconds.

[0044] Step 202: Calculate the sum of squared residuals based on the difference between the predicted density and the measured density of the sample filaments.

[0045] The difference refers to the numerical deviation between the predicted density and the measured density, reflecting the degree of deviation between the model's prediction and the actual measurement. The residual sum of squares is a statistic obtained by summing the squares of the residuals for each sample, used to comprehensively characterize the overall error between the model's prediction and the actual measurement.

[0046] Specifically, for each sample of filament, the predicted density obtained by the density prediction model is compared with the corresponding measured density to obtain the residual value of each sample. Then, the residuals corresponding to all samples are squared and summed to obtain the residual sum of squares, which is used to reflect the magnitude of the overall prediction error of the current density prediction model and to provide a basis for subsequent model correction.

[0047] For example, suppose we use To represent the predicted density, use Let represent the measured density. Then, the difference between the predicted density and the measured density of the sample filaments is: The sum of squared residuals is .

[0048] Step 203: Correct the predicted density of the sample filaments based on the sum of squared residuals to obtain the corrected density.

[0049] Corrected density refers to the density value obtained by adjusting the predicted density based on the predicted density and taking into account the overall error reflected by the sum of squared residuals.

[0050] Specifically, the model error information represented by the residual sum of squares is used to uniformly adjust or compensate the predicted density corresponding to each sample filament, thereby obtaining the corrected density. This corrected density can reduce the impact of measurement fluctuations to a certain extent and is closer to the overall density distribution characteristics of the sample filament, providing basic data for the subsequent construction of a more accurate second density prediction model or thickness prediction model.

[0051] Optionally, the predicted density of the sample filaments is corrected based on the residual sum of squares to obtain the corrected density, including: when the predicted density of the sample filaments is greater than the measured density, the predicted density of the sample filaments is subtracted from the residual sum of squares to obtain the corrected density; when the predicted density of the sample filaments is less than the measured density, the predicted density of the sample filaments is added to the residual sum of squares to obtain the corrected density.

[0052] Specifically, the predicted density is adjusted directionally based on the relationship between the predicted and measured densities. When the predicted density of the sample stalk is greater than the measured density, it indicates that the model prediction is generally too high; therefore, it is adjusted downwards by subtracting the sum of squared residuals from the predicted density. Conversely, when the predicted density is less than the measured density, it indicates that the model prediction is generally too low; therefore, it is adjusted upwards by adding the sum of squared residuals to the predicted density. The corrected density obtained in this way can compensate for the model prediction error to a certain extent, making the obtained density result closer to the actual density distribution of the sample stalk, thus providing a more stable data foundation for the subsequent construction of the second density prediction model and the stalk thickness prediction model.

[0053] For example, assume the predicted density is The measured density is The sum of squared residuals is ,use To indicate the corrected density, when hour, ,when hour, .

[0054] Step 204: Based on the measured thickness, measured moisture content and corrected density of the sample stems, construct a regression model with stem thickness and moisture content as independent variables and stem density as dependent variable to obtain the second density prediction model.

[0055] The independent variable is the variable that serves as an input factor in the regression model, used to explain or influence changes in the outcome. In this step, it includes stem thickness and stem moisture content. The dependent variable is the variable that serves as the predictor in the regression model, whose value changes with the independent variable. In this step, it is stem density. A regression model is a mathematical model that establishes a functional relationship between variables through statistical analysis of sample data, used to describe the correspondence between the independent and dependent variables.

[0056] Specifically, using the measured thickness, measured moisture content, and corrected density of multiple sample stems as modeling samples, a functional relationship model between stem density and stem thickness and moisture content is established through regression analysis, thus forming a new density prediction model, namely the second density prediction model, which can be expressed as follows: More specifically, it can be expressed as At this point, the stem thickness prediction model can be expressed as: .

[0057] Step 205: Construct a stem thickness prediction model based on the second density prediction model. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density, and stem moisture content.

[0058] Step 206: Input the measured density and measured moisture content of the target filament into the filament thickness prediction model to obtain the predicted thickness of the target filament.

[0059] For example, during the production process of the stem shredder in the factory, the moisture content and stem density of 11 batches of stem shreds were tested. Meanwhile, the thickness K of the stem wires in each batch was measured using a silicone rod. i The thickness of the stem fibers must be controlled within ±0.02 mm of the standard center value. The calculated stem fiber density results are shown in Table 1. The predicted results of the stem thickness are shown in Table 2: when , , , Based on the calculation results of the stem thickness deviation, the predicted value of the stem thickness deviates from the measured value by ±0.001mm. The fitting result of the stem thickness is relatively ideal and can meet the control requirements of the stem thickness standard.

[0060] In this embodiment, the measured thickness and moisture content of the sample stem are input into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density, stem thickness, and stem moisture content, providing basic data for subsequent model correction and thickness prediction. The sum of squared residuals is calculated based on the difference between the predicted and measured densities of the sample stem. The predicted density is then corrected based on the sum of squared residuals to obtain the corrected density. A regression model is constructed based on the measured thickness, measured moisture content, and corrected density of the sample stem, with stem thickness and moisture content as independent variables and stem density as the dependent variable, resulting in the second density prediction model. This effectively reduces the impact of measurement fluctuations on model accuracy, improving model stability and accuracy. A stem thickness prediction model is then constructed based on the second density prediction model. This model characterizes the functional relationship between stem thickness, stem density, and stem moisture content, enabling the conversion from a density model to a thickness prediction model while maintaining the model's conformity to actual process causal relationships, thus improving the reliability and prediction accuracy of the thickness prediction model. By inputting the measured density and moisture content of the target filament into the filament thickness prediction model, the predicted thickness of the target filament is obtained. This allows for the rapid acquisition of filament thickness results during production using readily available detection data, reducing the time required for traditional manual inspection, improving the efficiency of filament thickness detection, and facilitating real-time monitoring and process control during production. Furthermore, the filament thickness prediction method proposed in this invention does not directly establish a filament thickness prediction model based on filament density and moisture content. Instead, it first constructs a density prediction model that conforms to the physical laws of filament processing, and then corrects the predicted density by the difference between the predicted density and the measured density to construct a second density prediction model. Based on this, the filament thickness prediction model is then derived. This invention fully considers the physical causal relationships between various parameters during filament processing. Since filament density is the result of the combined effect of filament thickness and moisture content, prioritizing the establishment of a density prediction model more accurately reflects the actual changes during production. After obtaining a stable and reliable second density prediction model, a filament thickness prediction model is constructed through model transformation, ensuring that the final filament thickness prediction relationship conforms to the actual process mechanism and has good prediction accuracy. Compared to conventional methods that directly establish a model for predicting stem thickness, this invention achieves more accurate prediction of stem thickness by establishing a density model, correcting the model, and then back-calculating the thickness. This allows for rapid acquisition of stem thickness information during production, improving the accuracy of stem thickness control and the stability of the production process.

[0061] Figure 3 This is a schematic diagram of a filament thickness prediction device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: The density prediction module 301 is used to input the measured thickness and measured moisture content of the sample stem into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between the stem density and the stem thickness and moisture content. The density model correction module 302 is used to correct the first density prediction model based on the difference between the predicted density and the measured density of the sample filaments, so as to obtain the second density prediction model. Thickness model construction module 303 is used to construct a stem thickness prediction model based on the second density prediction model. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density and stem moisture content. The thickness prediction module 304 is used to input the measured density and measured moisture content of the target filament into the filament thickness prediction model to obtain the predicted thickness of the target filament.

[0062] In one embodiment, the density model correction module 302 specifically includes: The difference calculation module is used to calculate the sum of squared residuals based on the difference between the predicted density and the measured density of the sample filaments. The corrected density acquisition module is used to correct the predicted density of the sample filaments based on the sum of squared residuals to obtain the corrected density. The density model acquisition module is used to construct a regression model with the thickness and moisture content of the sample stems as independent variables and the density of the stems as dependent variable, based on the measured thickness, measured moisture content and corrected density of the stems, to obtain the second density prediction model.

[0063] In one embodiment, the corrected density acquisition module is specifically used for: When the predicted density of the sample filaments is greater than the measured density, the predicted density of the sample filaments is subtracted from the sum of squared residuals to obtain the corrected density. When the predicted density of the sample filaments is less than the measured density, the predicted density of the sample filaments is added to the sum of squared residuals to obtain the corrected density.

[0064] In one embodiment, the first density prediction model is obtained as follows: Based on the measured thickness, moisture content, and density of the sample stems, a regression model was constructed with stem thickness and moisture content as independent variables and stem density as the dependent variable, thus obtaining the first density prediction model.

[0065] In one embodiment, the measured thickness of the sample filament was obtained as follows: The silicone rod and the tobacco stem are fed into a shredder for cutting, and the resulting silicone sheets are collected. The thickness of multiple silicone sheets was measured and the average thickness was calculated. The average thickness was then used as the measured thickness of the sample strands in the corresponding batch.

[0066] In one embodiment, the measured moisture content of the sample stem filaments was obtained as follows: Collect shredded strands at the discharge port of the shredder; The collected stem samples were placed in a dry container of known mass and weighed to obtain the wet weight of the sample; Place the container containing the stem sample into an oven and dry it to constant weight at a preset temperature; Remove the container and place it in a desiccator to cool to room temperature. Weigh it again to obtain the dry weight of the sample. The measured moisture content of the sample stems was calculated based on the sample wet weight and sample dry weight.

[0067] In one embodiment, the measured density of the sample filaments was obtained as follows: A container with a standard volume was filled with the stem sample at the discharge port of the shredder and weighed to obtain the weight of the stem sample. The measured density of the sample filaments was determined based on the ratio of weight to standard volume.

[0068] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0069] The apparatus of this invention obtains the predicted density of the sample filaments by inputting the measured thickness and moisture content of the sample filaments into a first density prediction model. The first density prediction model characterizes the functional relationship between filament density, filament thickness, and filament moisture content, providing basic data for subsequent model correction and thickness prediction. Based on the difference between the predicted and measured densities of the sample filaments, the first density prediction model is corrected to obtain a second density prediction model, which effectively reduces the impact of measurement fluctuations on model accuracy and improves model stability and accuracy. Based on the second density prediction model, a filament thickness prediction model is constructed. The filament thickness prediction model characterizes the functional relationship between filament thickness, filament density, and filament moisture content, enabling the conversion from a density model to a thickness prediction model while maintaining the model's conformity to the actual process causal relationship, thus improving the reliability and prediction accuracy of the thickness prediction model. By inputting the measured density and moisture content of the target filament into the filament thickness prediction model, the predicted thickness of the target filament is obtained. This allows for the rapid acquisition of filament thickness results during production using readily available detection data, reducing the time required for traditional manual inspection, improving the efficiency of filament thickness detection, and facilitating real-time monitoring and process control during production. Furthermore, the filament thickness prediction method proposed in this invention does not directly establish a filament thickness prediction model based on filament density and moisture content. Instead, it first constructs a density prediction model that conforms to the physical laws of filament processing, and then corrects the model by analyzing the difference between the predicted and measured densities. Based on this, a filament thickness prediction model is then constructed. This invention fully considers the physical causal relationships between various parameters during filament processing. Since filament density is the result of the combined effects of filament thickness and moisture content, prioritizing the establishment of a density prediction model more accurately reflects the actual changes during production. After obtaining a stable and reliable second density prediction model, a filament thickness prediction model is constructed through model transformation, ensuring that the final filament thickness prediction relationship conforms to the actual process mechanism and has good prediction accuracy. Compared to conventional methods that directly establish a model for predicting stem thickness, this invention achieves more accurate prediction of stem thickness by establishing a density model, correcting the model, and then back-calculating the thickness. This allows for rapid acquisition of stem thickness information during production, improving the accuracy of stem thickness control and the stability of the production process.

[0070] The following is for reference. Figure 4 It shows a schematic diagram of the structure of a computer system 400 suitable for implementing an electronic device according to embodiments of the present invention. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0071] like Figure 4As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage section 508 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the computer system 400. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0072] The following components are connected to I / O interface 405: input section 406 including keyboard, mouse, etc.; output section 407 including cathode ray tube, liquid crystal display, etc., and speakers, etc.; storage section 408 including hard disk, etc.; and communication section 409 including network interface card, such as modem, etc. Communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0073] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the functions defined above in the system of this invention.

[0074] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, etc., or any suitable combination thereof.

[0075] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0076] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including a density prediction module, a density model correction module, a thickness model construction module, and a thickness prediction module. The names of these modules do not necessarily limit the module itself.

[0077] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: The measured thickness and moisture content of the sample stem are input into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density, stem thickness, and stem moisture content. Based on the difference between the predicted density and the measured density of the sample stem, the first density prediction model is corrected to obtain the second density prediction model. Based on the second density prediction model, a stem thickness prediction model is constructed. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density, and stem moisture content. The measured density and measured moisture content of the target stem are input into the stem thickness prediction model to obtain the predicted thickness of the target stem.

[0078] The technical solution of this invention involves inputting the measured thickness and moisture content of the sample stem into a first density prediction model to obtain the predicted density of the sample stem. The first density prediction model characterizes the functional relationship between stem density, stem thickness, and stem moisture content, providing basic data for subsequent model correction and thickness prediction. Based on the difference between the predicted and measured densities of the sample stem, the first density prediction model is corrected to obtain a second density prediction model, which effectively reduces the impact of measurement fluctuations on model accuracy and improves model stability and accuracy. A stem thickness prediction model is then constructed based on the second density prediction model. This model characterizes the functional relationship between stem thickness, stem density, and stem moisture content, enabling the conversion from a density model to a thickness prediction model while maintaining the model's conformity to actual process causal relationships, thus improving the reliability and prediction accuracy of the thickness prediction model. By inputting the measured density and moisture content of the target filament into the filament thickness prediction model, the predicted thickness of the target filament is obtained. This allows for the rapid acquisition of filament thickness results during production using readily available detection data, reducing the time required for traditional manual inspection, improving the efficiency of filament thickness detection, and facilitating real-time monitoring and process control during production. Furthermore, the filament thickness prediction method proposed in this invention does not directly establish a filament thickness prediction model based on filament density and moisture content. Instead, it first constructs a density prediction model that conforms to the physical laws of filament processing, and then corrects the model by analyzing the difference between the predicted and measured densities. Based on this, a filament thickness prediction model is then constructed. This invention fully considers the physical causal relationships between various parameters during filament processing. Since filament density is the result of the combined effects of filament thickness and moisture content, prioritizing the establishment of a density prediction model more accurately reflects the actual changes during production. After obtaining a stable and reliable second density prediction model, a filament thickness prediction model is constructed through model transformation, ensuring that the final filament thickness prediction relationship conforms to the actual process mechanism and has good prediction accuracy. Compared to conventional methods that directly establish a model for predicting stem thickness, this invention achieves more accurate prediction of stem thickness by establishing a density model, correcting the model, and then back-calculating the thickness. This allows for rapid acquisition of stem thickness information during production, improving the accuracy of stem thickness control and the stability of the production process.

[0079] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the filament thickness prediction method as provided in any embodiment of this invention.

[0080] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0081] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0082] It should be noted that the collection, use, storage, sharing, and transfer of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations, and require notification to the user and obtaining the user's consent or authorization. Where applicable, user personal information has undergone de-identification and / or anonymization and / or encryption technical processing. In addition, a corresponding operation entry is provided for the user to choose to agree to or reject the automated decision result; if the user chooses to reject, the process proceeds to the expert decision-making process.

[0083] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting stem thickness, characterized in that, include: The measured thickness and measured moisture content of the sample stem are input into the first density prediction model to obtain the predicted density of the sample stem. The first density prediction model is used to characterize the functional relationship between stem density and stem thickness and stem moisture content. Based on the difference between the predicted density and the measured density of the sample filaments, the first density prediction model is corrected to obtain the second density prediction model. Based on the second density prediction model, a stem thickness prediction model is constructed. The stem thickness prediction model is used to characterize the functional relationship between stem thickness, stem density, and stem moisture content. The measured density and measured moisture content of the target stem are input into the stem thickness prediction model to obtain the predicted thickness of the target stem.

2. The method according to claim 1, characterized in that, The step of correcting the first density prediction model based on the difference between the predicted density and the measured density of the sample filaments to obtain a second density prediction model includes: The sum of squared residuals is calculated based on the difference between the predicted density and the measured density of the sample filaments. The predicted density of the sample filaments is corrected based on the sum of squared residuals to obtain the corrected density; Based on the measured thickness, measured moisture content, and corrected density of the sample stems, a regression model is constructed with stem thickness and stem moisture content as independent variables and stem density as the dependent variable, thus obtaining the second density prediction model.

3. The method according to claim 2, characterized in that, The predicted density of the sample filaments is corrected based on the sum of squared residuals to obtain the corrected density, including: When the predicted density of the sample filaments is greater than the measured density, the predicted density of the sample filaments is subtracted from the sum of squared residuals to obtain the corrected density. When the predicted density of the sample filament is less than the measured density, the predicted density of the sample filament is added to the sum of squared residuals to obtain the corrected density.

4. The method according to claim 1, characterized in that, The first density prediction model is obtained as follows: Based on the measured thickness, measured moisture content, and measured density of the sample stems, a regression model is constructed with stem thickness and stem moisture content as independent variables and stem density as the dependent variable, thus obtaining the first density prediction model.

5. The method according to claim 1, characterized in that, The measured thickness of the sample filament was obtained in the following manner: The silicone rod and the tobacco stem are fed into a shredder for cutting, and the resulting silicone sheets are collected. The thickness of multiple silicone sheets is measured and the average thickness is calculated. The average thickness is then used as the measured thickness of the sample strands in the corresponding batch.

6. The method according to claim 1, characterized in that, The measured moisture content of the sample stems was obtained in the following manner: Collect shredded strands at the discharge port of the shredder; The collected stem samples were placed in a dry container of known mass and weighed to obtain the wet weight of the sample; Place the container containing the stem sample into an oven and dry it to constant weight at a preset temperature; Remove the container and place it in a desiccator to cool to room temperature. Weigh it again to obtain the dry weight of the sample. The measured moisture content of the sample stems is calculated based on the sample wet weight and the sample dry weight.

7. The method according to claim 1, characterized in that, The measured density of the sample filaments was obtained in the following manner: A container with a standard volume is filled with a stem sample at the discharge port of the shredder and weighed to obtain the weight of the stem sample. The measured density of the sample filaments is determined based on the ratio of the weight to the standard volume.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the program to implement the filament thickness prediction method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the filament thickness prediction method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the filament thickness prediction method as described in any one of claims 1 to 7.

Images