Evaluation methods, devices and media for the uniformity of tobacco structure distribution

Abstract

This disclosure relates to a method, apparatus, and medium for evaluating the uniformity of tobacco shred structure distribution, and pertains to the field of cigarette manufacturing technology. The method includes: acquiring an image of tobacco shreds; processing the tobacco shred image to obtain the tobacco shred length; grouping the tobacco shred lengths at preset intervals, with the group boundaries defined as independent variable l and the sum of accumulated tobacco shred areas defined as dependent variable F; transforming the independent variable l and dependent variable F to obtain transformed independent variable l and dependent variable F; performing regression analysis on the transformed independent variable l and dependent variable F to establish a tobacco shred length distribution model; calculating the characteristic length of the tobacco shreds using the tobacco shred length distribution model; and establishing tobacco shred structural features based on the characteristic length of the tobacco shreds to evaluate the uniformity of tobacco shred structure distribution. This disclosure improves the robustness and convenience of evaluating the uniformity of tobacco shred structure distribution.

Description

Technical Field

[0001] This disclosure relates to the field of cigarette manufacturing technology, and in particular to a method, apparatus and medium for evaluating the uniformity of tobacco shred distribution. Background Technology

[0002] The structure of tobacco shreds refers to the proportion of the weight of tobacco shreds of different sizes, such as long shreds, medium shreds, short shreds, and broken shreds, and is a crucial factor affecting cigarette quality. For a long time, uneven tobacco shred structure has led to tangling and clumping, causing problems such as combustion cone drop and fluctuating draw resistance during combustion, significantly impacting cigarette quality. Therefore, a reasonable proportion of long, medium, and short shreds, and a uniform tobacco shred structure, are key to ensuring stable cigarette quality. Currently, tobacco shred structure testing mainly utilizes sieving to separate tobacco shreds of different sizes, with the result expressed as the proportion of the cumulative mass on each layer or a specific layer of the sieve to the total weight. This characterization method only indicates the discrete distribution of tobacco shred size but cannot describe the uniformity of the tobacco shred structure distribution.

[0003] In existing technologies, a distribution equation for the size characteristics of tobacco shreds is established, and characteristic quantities describing the structural distribution law of tobacco shreds are analyzed to obtain a characterization method that can describe the structural distribution of tobacco shreds during processing. Furthermore, Chinese patent document CN104166803A discloses a technique entitled "A Method for Characterizing the Uniformity of Tobacco Shred Structural Distribution." This technique uses the principle of similarity to characterize several dimensions reflecting the structure of tobacco shreds with a comprehensive numerical value, and then uses the uniformity coefficient method to quantitatively evaluate the uniformity of the tobacco shred structural distribution. While these methods can characterize the uniformity of tobacco shred structural distribution to a certain extent, their calculation data all come from sieving test data. The process inevitably involves data offsets caused by over-sieving and under-sieving, leading to deviations in the calculated results of tobacco shred structural distribution uniformity. Therefore, the characterization of tobacco shred structural distribution uniformity currently remains limited to the application of sieving test data, and the industry lacks a more robust and effective evaluation method. Summary of the Invention

[0004] This disclosure proposes a method, apparatus, and medium for evaluating the uniformity of tobacco shred structure distribution, in order to solve the aforementioned technical problems.

[0005] According to a first aspect of this disclosure, a method for evaluating the uniformity of tobacco shred structure distribution is provided, comprising: acquiring a tobacco shred image; processing the tobacco shred image to obtain the tobacco shred length; grouping the tobacco shred lengths at preset intervals, wherein the boundary of the grouping is the independent variable l, and the sum of the cumulative tobacco shred areas is the dependent variable F; transforming the independent variable l and the dependent variable F to obtain the transformed independent variable l and the dependent variable F; performing regression on the transformed independent variable l and the dependent variable F to establish a tobacco shred length distribution model; calculating the characteristic length of the tobacco shred using the tobacco shred length distribution model; and establishing tobacco shred structure features based on the tobacco shred characteristic length to evaluate the uniformity of tobacco shred structure distribution.

[0006] In some embodiments, the Box-Cox transformation is utilized. Transform the independent variable l and the dependent variable F.

[0007] In some embodiments, regression is performed on the transformed independent variable l and the dependent variable F to establish a tobacco shred length distribution model, wherein the tobacco shred length distribution model is F λ =a+bl.

[0008] According to a second aspect of this disclosure, a device for evaluating the uniformity of tobacco shred structure distribution is provided, comprising: an acquisition module for acquiring tobacco shred images; a processing module for processing the tobacco shred images to obtain tobacco shred lengths; a grouping module for grouping the tobacco shreds at preset intervals, wherein the boundary of the grouping is an independent variable l, and the sum of the cumulative tobacco shred areas is a dependent variable F; a transformation module for transforming the independent variable l and the dependent variable F to obtain transformed independent variable l and dependent variable F; a regression module for regressing the transformed independent variable l and dependent variable F to establish a tobacco shred length distribution model; a calculation module for calculating the characteristic length of the tobacco shreds using the tobacco shred length distribution model; and a building module for establishing tobacco shred structure features based on the characteristic length of the tobacco shreds to evaluate the uniformity of tobacco shred structure distribution.

[0009] According to a third aspect of this disclosure, an apparatus for evaluating the uniformity of tobacco structure distribution is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the tobacco structure distribution uniformity evaluation method as described above based on instructions stored in the memory.

[0010] According to a fourth aspect of this disclosure, a computer-storeable medium is provided having computer program instructions stored thereon, which, when executed by a processor, implement the method for evaluating the uniformity of tobacco structure distribution as described above.

[0011] By adopting the above technical solutions, the beneficial technical effects that the embodiments of this disclosure can achieve are as follows: This disclosure uses visual inspection technology to measure the length of tobacco shreds, establishes a tobacco shred length distribution model, realizes accurate and convenient calculation of the characteristic length values ​​of tobacco shreds, establishes a tobacco shred structure characteristic value index based on the tobacco shred length value, and defines the tobacco shred structure characteristic value as a comprehensive index for evaluating the uniformity of tobacco shred structure distribution, thereby improving the robustness and convenience of the characterization of the uniformity of tobacco shred structure distribution. This solution is robust, simple, and feasible, and has sufficient scientific validity and operability. Attached Figure Description

[0012] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0013] This disclosure can be more clearly understood with reference to the accompanying drawings and the following detailed description.

[0014] Figure 1 This is a flowchart illustrating a method for evaluating the uniformity of tobacco structure distribution according to some embodiments of the present disclosure.

[0015] Figure 2 This is a block diagram illustrating an apparatus for evaluating the uniformity of tobacco structure distribution according to some embodiments of the present disclosure.

[0016] Figure 3 This is a block diagram illustrating an evaluation device for the uniformity of tobacco structure distribution according to other embodiments of the present disclosure.

[0017] Figure 4 This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. Detailed Implementation

[0018] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0019] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0021] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0022] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] Currently, the evaluation of the uniformity of tobacco shred structure distribution is based on sieving test data. However, the sieving process can lead to data deviations due to over-sieving or under-sieving, which in turn causes errors in the calculation results of the uniformity of tobacco shred structure distribution.

[0025] In view of this, this disclosure proposes a method, device and medium for evaluating the uniformity of tobacco structure distribution. The method establishes a tobacco length distribution model and calculates the characteristic length value of tobacco through visual inspection technology. Based on the characteristic length value of tobacco, the characteristic value of tobacco structure is calculated to characterize the overall uniformity of tobacco structure distribution, thereby improving the robustness and convenience of characterizing the uniformity of tobacco structure distribution.

[0026] Figure 1 This is a flowchart illustrating a method for evaluating the uniformity of tobacco shred structure distribution according to some embodiments of the present disclosure. Figure 1 As shown, the method for evaluating the uniformity of tobacco shred structure distribution includes steps 110 to 170.

[0027] In step 110, an image of the tobacco shreds is obtained.

[0028] In some embodiments, approximately 500g of tobacco from a cigarette-making machine is taken and evenly spread on a detection platform. The tobacco on the detection platform is observed using a high-resolution lens, and an image of the tobacco is obtained through image denoising and edge detection, which is then transmitted and saved to a computer.

[0029] In step 120, the tobacco image is processed to obtain the tobacco length.

[0030] In some embodiments, computer image processing algorithms are used to analyze and process the acquired tobacco images to obtain the length of each identifiable tobacco shred. Since longer tobacco shreds may not be completely separated, resulting in multiple tobacco shreds being entangled, data with a length greater than 50mm are deleted.

[0031] In step 130, the length of the tobacco shreds is grouped at preset intervals, with the boundary of the group being the independent variable l and the sum of the cumulative tobacco shred areas being the dependent variable F.

[0032] In some embodiments, based on the obtained tobacco length data, the tobacco length is grouped at intervals of 0.5 mm, with the boundary of the group as the independent variable l and the sum of the cumulative tobacco area as the dependent variable F, and the data is processed.

[0033] In step 140, the independent variable l and the dependent variable F are transformed to obtain the transformed independent variable l and the dependent variable F.

[0034] In some embodiments, the Box-Cox transform is used. Transform F and l.

[0035] In step 150, regression is performed on the transformed independent variable l and the dependent variable F to establish a tobacco shred length distribution model.

[0036] In some embodiments, regression is performed on F after the Box-Box transformation and the tobacco length l to establish a tobacco length distribution model. Tobacco length distribution model: F λ =a+bl.

[0037] In step 160, the characteristic length of the tobacco shreds is calculated using the tobacco shred length distribution model.

[0038] In step 170, tobacco shred structural features are established based on the characteristic length of the tobacco shreds to evaluate the uniformity of tobacco shred structural distribution.

[0039] In some embodiments, according to the model, when F = 0.5, the corresponding l represents 50% of the tobacco shreds having a length greater than l, and the length of the tobacco shreds at this time is denoted as l. 0.5 , can represent the overall length of the sample tobacco shreds, and similarly can be represented by l. 0.1 This indicates that 10% of the tobacco shreds are longer than l. 0.9 This indicates that 90% of the tobacco shreds are longer than l, expressed using the structural characteristic value of the tobacco shreds: (l) 0.1 -l 0.9 ) / l 0.5 This value characterizes the uniformity of the overall distribution of tobacco shreds; the smaller the value, the more uniform the distribution.

[0040] This disclosure utilizes visual inspection technology to determine the length of tobacco shreds. By establishing a tobacco shred length distribution model, it achieves accurate and convenient calculation of the characteristic length of tobacco shreds. Based on the tobacco shred length values, it establishes a tobacco shred structural characteristic value index, defining the tobacco shred structural characteristic value as a comprehensive index for evaluating the uniformity of tobacco shred structural distribution, thereby improving the robustness and convenience of characterizing the uniformity of tobacco shred structural distribution. The method provided in this disclosure is robust, simple, and feasible, possessing sufficient scientific validity and operability.

[0041] The key technical point of this disclosure is to establish a tobacco shred length distribution model, through which the characteristic length value of tobacco shreds can be accurately estimated, and a tobacco shred structure characteristic value index can be established based on the characteristic length value of tobacco shreds; the tobacco shred structure characteristic value is used to reflect the uniformity of the tobacco shred structure distribution, and the smaller the value, the more uniform the distribution.

[0042] In some embodiments, a certain specification of finished tobacco shreds from Cigarette Factory A is used as the research object. A YQ-2 tobacco shreds vibrating sorting sieve is used, with the upper sieve screen replaced from 3.35mm to 3.1mm in aperture, to sieve the test finished tobacco shreds. The sieved shreds (>3.1mm), medium (2.5~3.1mm), and short shreds (<2.5mm) are evenly distributed according to the scheme in "Table 1: Test Plan". The total weight of each sample is 10kg. In each test, 500g of tobacco shreds are taken at normal speed and their structure is detected by visual recognition equipment.

[0043] Table 1: Experimental Plan

[0044] Test number Fiber percentage Medium fiber percentage Short filament percentage 1 100 0 0 2 60 30 10 3 40 50 10 4 20 50 30 5 0 100 0

[0045] This disclosure establishes a tobacco shred length distribution model F. λ =a+bl, and then fit the tobacco structure data of each experiment. The results are as follows:

[0046] Table 2: Experimental Data Fitting Results

[0047] Test number λ a b <![CDATA[R 2 (Adjustment) 1 -0.22 0.915 0.037 0.999 2 -0.242 0.909 0.057 0.999 3 -0.228 0.894 0.061 0.999 4 -0.243 0.868 0.088 0.999 5 -0.179 0.879 0.062 0.999

[0048] As can be seen from the data in the table above, the model has a high goodness of fit and the fitting effect is ideal.

[0049] This publication calculates and evaluates the uniformity of tobacco structure under different treatments in various experiments. The specific results are shown below:

[0050] Table 3: Percentage of stem widths in different groups within the specified width range obtained through image detection of stems from Factory A

[0051]

[0052] Regarding the uniformity of tobacco shred distribution, except for test 1, the uniformity of tobacco shred length gradually improved as the proportion of long filaments decreased, with test 5 exhibiting the highest uniformity. Test 1, composed entirely of long filaments, showed slightly better uniformity than test 2. Based on the established model and the structural characteristic values ​​of the tobacco shreds, the visually detected shred structure conforms to the expected experimental design, thus demonstrating the effectiveness of the disclosed scheme.

[0053] Figure 2 This is a block diagram illustrating an apparatus for evaluating the uniformity of tobacco shred structure distribution according to some embodiments of the present disclosure. Figure 2As shown, the tobacco shred structure distribution uniformity evaluation device 200 includes an acquisition module 210, a processing module 220, a grouping module 230, a transformation module 240, a regression module 250, a calculation module 260, and an establishment module 270.

[0054] The acquisition module 210 is configured to acquire images of tobacco shreds;

[0055] Processing module 220 is configured to process the tobacco image to obtain the tobacco length;

[0056] The grouping module 230 is configured to group the tobacco strands at preset intervals, with the boundary of the group being the independent variable l and the sum of the cumulative tobacco strand areas being the dependent variable F.

[0057] The transformation module 240 is configured to transform the independent variable l and the dependent variable F to obtain the transformed independent variable l and the dependent variable F;

[0058] The regression module 250 is configured to perform regression on the transformed independent variable l and the dependent variable F to establish a tobacco shred length distribution model;

[0059] The calculation module 260 is configured to calculate the characteristic length of the tobacco using the tobacco length distribution model;

[0060] Module 270 is established so that the user can establish tobacco shred structure features based on the tobacco shred characteristic length to evaluate the uniformity of tobacco shred structure distribution.

[0061] In the apparatus of this embodiment, visual inspection technology is used to measure the length of tobacco shreds. By establishing a tobacco shred length distribution model, the characteristic length values ​​of tobacco shreds can be accurately and conveniently calculated. Based on the tobacco shred length values, a tobacco shred structure characteristic value index is established, and the tobacco shred structure characteristic value is defined as a comprehensive index for evaluating the uniformity of tobacco shred structure distribution. This improves the robustness and convenience of characterizing the uniformity of tobacco shred structure distribution. This solution is robust, simple, and feasible, and has sufficient scientific validity and operability.

[0062] Figure 3 This is a block diagram illustrating an evaluation apparatus for the uniformity of tobacco shred structure distribution according to other embodiments of this disclosure. Figure 3 As shown, the tobacco shred structure distribution uniformity evaluation device 300 includes a memory 310 and a processor 320 coupled to the memory 310. The memory 310 is used to store instructions for executing embodiments of the tobacco shred structure distribution uniformity evaluation method. The processor 320 is configured to execute the tobacco shred structure distribution uniformity evaluation method in any of the embodiments of this disclosure based on the instructions stored in the memory 310.

[0063] Figure 4This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. Figure 4 As shown, the computer system 400 can be represented in the form of a general computing device. The computer system 400 includes a memory 410, a processor 420, and a bus 430 connecting different system components.

[0064] The memory 410 may include, for example, system memory, non-volatile storage media, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs. The system memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. The non-volatile storage media may store, for example, instructions for executing at least one of the methods for evaluating the uniformity of tobacco structure distribution in corresponding embodiments. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.

[0065] The processor 420 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Correspondingly, each module, such as the acquisition module, processing module, grouping module, transformation module, regression module, calculation module, and establishment module, can be implemented by executing instructions from the central processing unit (CPU) in its runtime memory, or by dedicated circuitry executing the corresponding steps.

[0066] Bus 430 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.

[0067] The computer system 400 may also include an input / output interface 440, a network interface 450, and a storage interface 460. These interfaces 440, 450, and 460, as well as the memory 410 and processor 420, can be connected via a bus 430. The input / output interface 440 provides a connection interface for input / output devices such as a monitor, mouse, and keyboard. The network interface 450 provides a connection interface for various networked devices. The storage interface 460 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.

[0068] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations thereof, can be implemented by computer-readable program instructions.

[0069] These computer-readable program instructions are provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device to produce a machine, such that execution of the instructions by the processor produces means for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.

[0070] These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer to work in a particular manner to produce an article of manufacture, including instructions that implement the functions specified in one or more boxes in a flowchart and / or block diagram.

[0071] This disclosure may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0072] This disclosure utilizes visual inspection technology to determine the length of tobacco shreds. By establishing a tobacco shred length distribution model, it achieves accurate and convenient calculation of the characteristic length values ​​of tobacco shreds. Based on the tobacco shred length values, it establishes a tobacco shred structure characteristic value index and defines the tobacco shred structure characteristic value as a comprehensive index for evaluating the uniformity of tobacco shred structure distribution. This improves the robustness and convenience of characterizing the uniformity of tobacco shred structure distribution. This scheme is robust, simple, and feasible, and has sufficient scientific validity and operability.

[0073] This concludes the detailed description of the method, apparatus, and medium for evaluating the uniformity of tobacco structure distribution according to this disclosure. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0074] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method of evaluating the uniformity of distribution of a tobacco structure, characterized by, The method comprises: acquiring a tobacco shred image; processing the tobacco shred image to obtain a tobacco shred length; grouping the tobacco shred length at preset intervals, with the grouping boundary being an independent variable l and the cumulative sum of the tobacco shred area being a dependent variable F; Transforming the independent variable l and the dependent variable F to obtain transformed independent variable l and the dependent variable F, comprising: transforming transforming the independent variable l and the dependent variable F; A regression is performed on the transformed independent variable l and dependent variable F to establish a cut tobacco length distribution model, wherein the cut tobacco length distribution model is ; calculating a tobacco shred characteristic length using the tobacco shred length distribution model; Based on the tobacco length characteristic, a tobacco structure characteristic is established to evaluate the uniformity of tobacco structure distribution, including: according to a tobacco length distribution model, when F=0.5, it represents that 50% of the tobacco length is greater than l, at this time the tobacco length is recorded as l 0.5 , when F=0.1, it represents that 10% of the tobacco length is greater than l, at this time the tobacco length is recorded as l 0.1 , and when F=0.9, it represents that 90% of the tobacco length is greater than l, at this time the tobacco length is recorded as l 0.9 , and a tobacco structure characteristic value is: to represent the uniformity of the overall distribution of the tobacco.

2. A tobacco shred structure uniformity evaluation device characterized by comprising: comprise: a memory; and a processor coupled to the memory, the processor being configured to execute a tobacco shred structure distribution uniformity evaluation method as claimed in claim 1 based on instructions stored in the memory.

3. A computer storable medium, characterized by A computer program product, having stored thereon computer program instructions, which instructions, when executed by a processor, implement a tobacco shred structure distribution uniformity evaluation method as claimed in claim 1.

Images