Cigar tobacco air-curing state monitoring, regulating and controlling method and system

Abstract

The invention relates to the technical field of cigar tobacco processing, in particular to a cigar tobacco air-curing state monitoring, regulating and controlling method and system. During application, images are acquired in a multi-angle and random manner, and the state change of the tobacco leaves in each airing stage can be comprehensively and accurately monitored in combination with spectral analysis, so that a basis is provided for timely adjustment of environmental conditions. Through fine management of the airing process, switching control of key nodes can be controlled, and improvement of the overall quality of cigars is facilitated. The whole airing state monitoring and regulating process can be executed automatically, manual intervention is reduced, and working efficiency and accuracy are improved. The method is suitable for different types of cigar tobacco leaves, various parameters can be flexibly adjusted according to actual conditions, and the method has high universality and practicability.

Description

Technical Field

[0001] This application relates to the field of cigar tobacco processing technology, specifically to a method and system for monitoring and controlling the drying status of cigar tobacco leaves. Background Technology

[0002] In the traditional cigar tobacco drying process, judging the drying status has long relied on manual experience, mainly determining the timing of switching between key stages such as wilting, yellowing, browning, color fixation, and dryness by observing subjective indicators such as the color, feel, and aroma of the tobacco leaves. However, this method has significant drawbacks: First, the human eye has limited ability to distinguish color changes, especially in the transition from yellowing to browning and from color fixation to dryness, where subtle color differences can easily lead to misjudgment; second, it cannot quantify internal physiological states, such as the degree of chlorophyll degradation, polyphenol oxidation activity, and the moisture gradient between the midrib and mesophyll, often resulting in problems such as "dry outside and moist inside" or "insufficient browning"; third, manual inspections are incomplete and infrequent, making it difficult to reflect the uniformity of tobacco leaves throughout the warehouse. Although some studies have attempted to introduce temperature and humidity sensors or single-point spectrometers, a multi-perspective, full-process, non-contact dynamic monitoring system is lacking, and a reliable mapping relationship between optical characteristics and biochemical states has not been established. Existing technologies also fail to effectively integrate spatial distribution, such as tobacco leaf arrangement, continuous monitoring, and multi-dimensional parameters, resulting in insufficient precision in automated control and making it difficult to meet the stringent requirements of high-end cigars for consistent drying, pure aroma, and uniform combustion. Therefore, there is an urgent need for an intelligent monitoring and control method based on multi-view image acquisition, specific band spectral analysis, hue stability criteria, and moisture gradient assessment to achieve objective, precise, and closed-loop control of the entire cigar drying process. Summary of the Invention

[0003] In view of this, this application provides a method and system for monitoring and controlling the drying state of cigar tobacco leaves, which can realize intelligent monitoring and control methods such as multi-view image acquisition, specific band spectral analysis, hue stability criteria and moisture gradient assessment, so as to achieve objective, accurate and closed-loop control of the entire cigar drying process.

[0004] In a first aspect, this application provides a method for monitoring and controlling the drying state of cigar tobacco leaves, comprising: after cigar tobacco leaves are tied to drying poles to form tobacco leaf rows, randomly extracting a first preset number of first monitoring images in the direction of collection of the tobacco leaf rows; multiple tobacco leaf rows forming tobacco leaf columns, randomly extracting a second preset number of second monitoring images in the direction of collection of the tobacco leaf columns; randomly extracting a third preset number of third monitoring images in the direction of collection of the tobacco leaf columns at an angle; multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images forming an image group to be identified; adjusting the environmental conditions to a withering period condition, and if the first preset proportion area in the image group to be identified changes to the yellowing period spectrum, ending the withering period and entering the yellowing period control; adjusting the environmental conditions to a yellowing period condition, and if the second preset proportion area in the image group to be identified changes to the browning period spectrum, ending the yellowing period and entering the browning period control; adjusting the environmental conditions to a browning period pre-reaction condition, randomly extracting a second preset number of second monitoring images in the image group to be identified; For three preset proportions of tobacco leaf temperature, if the temperature difference between the tobacco leaf temperature and the ambient temperature is less than a preset temperature difference, the pre-reaction condition of the browning stage is maintained; if the temperature difference between the tobacco leaf temperature and the ambient temperature is greater than or equal to the preset temperature difference, the environmental condition is adjusted to switch to the active metabolic condition of the browning stage; after maintaining the active metabolic condition of the browning stage for a preset active reaction duration, if the browning degree of the fourth preset proportion of the image group to be identified reaches the leaf condition of the color-fixing stage, then the color-fixing stage control is entered; the environmental condition is adjusted to the color-fixing stage condition, and if the color parameter of the fourth preset proportion of the image group to be identified meets the stable parameter, then the dry vein stage control is entered; and the environmental condition is adjusted to the dry vein stage condition, and the moisture monitoring area containing the midrib and leaf mesophyll is randomly extracted from the image group to be identified, and the moisture gradient ratio of the midrib moisture content and leaf mesophyll moisture content is detected based on the moisture monitoring area. If the midrib moisture content decreases to a preset moisture content range and the moisture gradient ratio stabilizes within a preset gradient range, then the drying completion information is generated.

[0005] In conjunction with the first aspect, one possible implementation further includes: randomly re-extracting the first monitoring image, the second monitoring image, and the third monitoring image every first preset time interval.

[0006] In conjunction with the first aspect, one possible implementation further includes: randomly changing the position of the first camera corresponding to the first monitoring image, the position of the second camera corresponding to the second monitoring image, and the position of the third camera corresponding to the third monitoring image every second preset time interval.

[0007] In conjunction with the first aspect, in one possible implementation, the step of ending the wilting period and entering the yellowing period control when the first preset proportion area in the image group to be identified changes to the yellowing period spectrum includes: acquiring a first initial average reflectance in the wavelength range of 675-685nm at the beginning of the wilting period; monitoring a first real-time average reflectance in the wavelength range of 675-685nm; and determining that the change has occurred to the yellowing period spectrum if the decrease in the first real-time average reflectance relative to the first initial average reflectance is greater than 30%.

[0008] In conjunction with the first aspect, in one possible implementation, the step of ending the yellowing period and entering the browning period control when the second preset proportion area in the image group to be identified changes to the browning period spectrum includes: acquiring a second initial average reflectance in the 615-625 nm wavelength range at the beginning of the yellowing period; monitoring a second real-time average reflectance in the 615-625 nm wavelength range; and determining that the change has occurred to the browning period spectrum if the decrease in the second real-time average reflectance relative to the second initial average reflectance is greater than 8%.

[0009] In conjunction with the first aspect, in one possible implementation, the random extraction of tobacco leaf temperature from a third preset proportion area in the image group to be identified includes: extracting a temperature monitoring area from the image group to be identified based on the third preset proportion area; detecting temperature data of the temperature monitoring area; and obtaining an average temperature based on the temperature data and recording it as the tobacco leaf temperature.

[0010] In conjunction with the first aspect, in one possible implementation, the step of entering the color-fixing period control if the browning degree of the fourth preset proportion area in the image group to be identified reaches the leaf condition of the color-fixing period includes: acquiring multispectral images of the image group to be identified at consecutive time points; extracting the hue angle of the multispectral image in the CIELAB color space; calculating the hue change of the hue angle between adjacent time points; and if the absolute value of the hue change is continuously less than 2° and maintained for a third preset duration, determining that no new hue is generated in the tobacco leaves and entering the color-fixing period.

[0011] In conjunction with the first aspect, in one possible implementation, the step of entering the drying period control if the color parameter of the fourth preset proportion area in the image group to be identified meets the stable parameter includes: obtaining the hue angle of the image group to be identified in the CIELAB color space; and if the hue angle is within the target range of 25° to 40°, and the absolute value of the change in the hue angle is continuously less than 1.5° for more than 24 hours, then it is determined that the color parameter meets the stable parameter and the drying period is entered.

[0012] In conjunction with the first aspect, in one possible implementation, the step of randomly extracting water monitoring regions containing both the midrib and mesophyll from the image group to be identified, and detecting the water gradient ratio of the midrib water content and the mesophyll water content based on the water monitoring regions, includes: identifying and extracting a first preset number of water monitoring regions containing both the midrib and mesophyll from the image group to be identified based on preset midrib features and preset mesophyll features; within each water monitoring region, detecting a first average water content of the midrib based on the location of the preset midrib features; within each water monitoring region, filtering a second preset number of target mesophyll regions based on the location of the preset mesophyll features, and detecting a second average water content of the target mesophyll regions; taking the average of multiple first average water contents from multiple water monitoring regions to obtain the midrib water content; taking the average of multiple second average water contents from multiple water monitoring regions to obtain the mesophyll water content; and calculating the ratio of the midrib water content to the mesophyll water content to obtain the water gradient ratio.

[0013] Secondly, this application provides a cigar tobacco leaf drying state monitoring and control system, comprising: a data acquisition module configured to: after cigar tobacco leaves are tied to drying rods to form tobacco leaf rows, randomly extract a first preset number of first monitoring images in the acquisition direction towards the tobacco leaf rows; multiple tobacco leaf rows form tobacco leaf columns, and randomly extract a second preset number of second monitoring images in the acquisition direction towards the tobacco leaf columns; randomly extract a third preset number of third monitoring images in the acquisition direction of the tobacco leaf columns at an angle; multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images form an image group to be identified; and a stage control module, communicatively connected to the data acquisition module, the stage control module being configured to: adjust the environmental conditions to the withering stage condition, and if the first preset proportion area in the image group to be identified changes to the yellowing stage spectrum, end the withering stage and enter the yellowing stage control; adjust the environmental conditions to the yellowing stage condition, and if the second preset proportion area in the image group to be identified changes to the browning stage spectrum, end the yellowing stage and enter the brown ...; adjust the environmental conditions to the yellowing stage condition, and if the second preset proportion area in the image group to be identified changes to the browning stage, end the yellow In the browning pre-reaction condition, the tobacco leaf temperature of the third preset proportion area in the image group to be identified is randomly extracted. If the temperature difference between the tobacco leaf and the ambient temperature is less than a preset temperature difference, the browning pre-reaction condition is maintained. If the temperature difference between the tobacco leaf and the ambient temperature is greater than or equal to a preset temperature difference, the ambient condition is adjusted to switch to the browning active metabolism condition. After maintaining the browning active metabolism condition for a preset active reaction time, if the browning degree of the fourth preset proportion area in the image group to be identified reaches the color-fixing leaf condition, then the color-fixing control condition is entered. The process involves: adjusting the environmental conditions to a color-fixing period; if the color parameters of the fourth preset proportion area in the image group to be identified meet the stable parameters, then entering the dry-stem stage control; and adjusting the environmental conditions to a dry-stem stage, randomly extracting the moisture monitoring area containing the midrib and leaf mesophyll in the image group to be identified, detecting the moisture gradient ratio of the midrib moisture content and leaf mesophyll moisture content based on the moisture monitoring area, and if the midrib moisture content decreases to a preset moisture content range and the moisture gradient ratio stabilizes within the preset gradient range, then generating drying completion information.

[0014] This application employs multi-angle, random image acquisition combined with spectral analysis to comprehensively and accurately monitor the state changes of tobacco leaves at each drying stage, providing a basis for timely adjustments to environmental conditions. Through refined management of the drying process, the switching control of key nodes can be controlled, contributing to improved overall cigar quality. The entire drying state monitoring and control process is highly automated, reducing manual intervention and improving work efficiency and accuracy. This method is applicable to different types of cigar tobacco leaves, allowing for flexible adjustment of various parameters according to actual conditions, demonstrating strong versatility and practicality. Attached Figure Description

[0015] Figure 1 The diagram shows the steps of a method for monitoring and controlling the drying state of cigar tobacco leaves according to an embodiment of this application.

[0016] Figure 2 The diagram shows the internal structure of a cigar drying room.

[0017] Figure 3 The diagram shows the steps of a method to randomly change the acquisition method of monitoring images.

[0018] Figure 4 The diagram shows the process of transitioning to the yellowing stage.

[0019] Figure 5 The diagram shows the process of transitioning to the browning stage.

[0020] Figure 6 The diagram shows the steps involved in monitoring tobacco leaf temperature.

[0021] Figure 7 The diagram shows the process of transitioning to the color-fixing period.

[0022] Figure 8 The diagram shows the process of transitioning to the dry rib stage.

[0023] Figure 9 The diagram shows the steps involved in calculating the moisture gradient ratio.

[0024] Figure 10 The diagram shows the system structure of the cigar tobacco drying status monitoring and control system. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0026] An exemplary method for monitoring and controlling the drying status of cigar tobacco leaves is as follows: Figure 1 The diagram shows the steps of a method for monitoring and controlling the drying state of cigar tobacco leaves according to an embodiment of this application.

[0027] This application provides a method for monitoring and controlling the drying state of cigar tobacco leaves. In one embodiment, such as... Figure 1 As shown, the method for monitoring and controlling the drying state of cigar tobacco leaves includes: Step 110: After the cigar tobacco leaves are tied to the drying pole to form a tobacco leaf row, a first preset number of first monitoring images are randomly extracted in the collection direction facing the tobacco leaf row; multiple tobacco leaf rows form a tobacco leaf column, and a second preset number of second monitoring images are randomly extracted in the collection direction facing the tobacco leaf column; a third preset number of third monitoring images are randomly extracted in the collection direction facing the tobacco leaf column.

[0028] In this step, multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images form a group of images to be identified. Figure 2 The diagram shows the internal structure of a cigar drying room. (Refer to...) Figure 2 This application relates to a cigar drying room, which includes drying racks comprising multiple parallel drying rods 1 to which cigar tobacco leaves 2 are tied. The length direction of the drying rods 1 is the x-axis, and the cigar tobacco leaves 2 tied to the drying rods 1 form tobacco rows arranged along the x-axis. The height direction of the cigar drying room is the z-axis, and multiple drying rods 1 on the same horizontal plane form tobacco rows arranged along the y-axis, with the tobacco rows also arranged along the y-axis. On a single horizontal plane, multiple drying rods 1 are arranged parallel along the y-axis to form a drying layer; multiple drying layers are arranged along the z-axis. Multiple cameras are installed on the walls of the cigar drying room, with one or more cameras positioned on the wall facing the xz plane to capture a first monitoring image; and multiple cameras positioned on the wall facing the yz plane to capture a second and a third monitoring image. The first monitoring image is mainly used to monitor multiple rows of tobacco leaves on the xz plane; the second monitoring image is mainly used to monitor the end leaves of the tobacco leaves on the yz plane and the part of the tobacco leaves inside the end; the third monitoring image, taken from an oblique perspective, is mainly used to monitor the part of the tobacco leaves inside the end of the tobacco leaves. The first, second, and third monitoring images reflect the tobacco leaf drying status in the cigar drying room. Furthermore, the first, second, and third monitoring images are all acquired randomly, which further improves the randomness of tobacco leaf monitoring, thus reflecting the tobacco leaf drying status more objectively. This step constructs the image group to be identified by randomly acquiring images from multiple perspectives (frontal view, end view, oblique view), effectively covering the three-dimensional spatial distribution of tobacco leaf rows / columns, avoiding monitoring blind spots, and significantly improving sample representativeness and the objectivity of the drying status assessment.

[0029] Step 120: Adjust the environmental conditions to the withering period conditions. If the first preset proportion area in the image group to be identified changes to the yellowing period spectrum, end the withering period and enter the yellowing period control.

[0030] In this step, the yellowing period spectrum can be obtained using data referenced in existing technologies. The yellowing initiation is determined based on the decrease in reflectance in the 675-685 nm band, achieving a precise switch from the wilting period to the yellowing period. This avoids entering a high-humidity environment too early or too late, ensuring the orderly degradation of chlorophyll and the formation of aroma precursors.

[0031] Step 130: Adjust the environmental conditions to the yellowing period condition. If the second preset ratio area in the image group to be identified changes to the browning period spectrum, end the yellowing period and enter the browning period control.

[0032] In this step, the decrease in reflectance in the 615-625 nm band is used as the browning trigger criterion to accurately capture the starting point of the polyphenol oxidation reaction, ensuring that the browning reaction starts in the optimal physiological window and improving the uniformity of browning and the efficiency of aroma synthesis.

[0033] Step 140: Adjust the environmental conditions to the browning stage pre-reaction condition. Randomly extract the tobacco leaf temperature of the third preset proportion area in the image group to be identified. If the temperature difference between the tobacco leaf temperature and the ambient temperature is less than the preset temperature difference, maintain the browning stage pre-reaction condition. If the temperature difference between the tobacco leaf temperature and the ambient temperature is greater than or equal to the preset temperature difference, adjust the environmental conditions to switch to the browning stage active metabolism condition.

[0034] In this step, the temperature difference between tobacco leaves and the environment (ΔT) is introduced as an indicator of metabolic activity to distinguish between pre-reaction and active metabolic conditions, so as to achieve the browning period according to the physiological state of the tobacco leaves themselves rather than a fixed time, thereby enhancing the adaptability of the process.

[0035] Step 150: After maintaining the active metabolic conditions during the browning period for a preset active reaction time, if the browning degree of the fourth preset proportion area in the image group to be identified reaches the leaf condition during the color fixation period, then the color fixation period control is initiated.

[0036] In this step, the color-fixing period is entered based on the degree of browning, to ensure that the pigments are fully formed and evenly distributed, and to prevent unstable color or insufficient aroma from being caused by entering the drying process before the browning is completed.

[0037] Step 160: Adjust the environmental conditions to the color fixation period condition. If the color parameters of the fourth preset proportion area in the image group to be identified meet the stable parameters, then enter the dry rib control period.

[0038] In this step, color stability is determined by the hue angle change being consistently less than the threshold, and the color fixation endpoint is quantitatively determined to avoid premature entry into the drying stage due to subjective misjudgment, which could lead to color reversion or color spots later.

[0039] Step 170: Adjust the environmental conditions to the dry-stem stage conditions, randomly extract the moisture monitoring area containing the midrib and leaf mesophyll from the image group to be identified, and detect the moisture gradient ratio of the midrib moisture content and leaf mesophyll moisture content based on the moisture monitoring area. If the midrib moisture content decreases to the preset moisture content range and the moisture gradient ratio stabilizes within the preset gradient range, then generate drying completion information.

[0040] In this step, the moisture content of the main vein and leaf mesophyll is monitored simultaneously and the gradient ratio is calculated. This ensures that the main vein is fully dried and verifies that the internal moisture migration tends to be balanced, thereby accurately determining that the drying process is completely finished and avoiding the risks of external dryness and internal moisture or excessive drying.

[0041] This embodiment employs multi-angle, random image acquisition combined with spectral analysis to comprehensively and accurately monitor the state changes of tobacco leaves at each drying stage, providing a basis for timely adjustments to environmental conditions. Through refined management of the drying process, the switching control of key nodes can be controlled, contributing to improved overall cigar quality. The entire drying state monitoring and control process is highly automated, reducing manual intervention and improving efficiency and accuracy. This method is applicable to different types of cigar tobacco leaves, allowing for flexible adjustment of parameters according to actual conditions, demonstrating strong versatility and practicality.

[0042] Specifically, the first preset quantity, the second preset quantity, the third preset quantity, the first preset ratio area, the second preset ratio area, the third preset ratio area, and the fourth preset ratio area can be set according to the monitoring requirements. The higher the requirements for the drying of cigar tobacco leaves, the larger the values ​​of each quantity parameter.

[0043] Specifically, the preset values ​​for moisture content range, gradient range, temperature difference, and active reaction time can all be obtained through pre-testing.

[0044] Based on the above technical solution, the following are three specific embodiments that can be used in medium-sized cigar drying rooms, reflecting the different requirements of parameter settings for different drying quality levels: Example 1: Standard grade cigar tobacco (basic quality): Image acquisition quantity: First preset quantity = 10 images / drying layer, second preset quantity = 6 images / drying layer, third preset quantity = 6 images / drying layer, each drying layer can cover 200-300 tobacco leaves; The first to fourth preset area ratios are all 70%; Preset temperature difference = 0.5℃ Preset active reaction time = 48 hours Preset moisture content range: 13-14% Preset moisture gradient ratio range: 1.1-1.2 Suitable for filler leaves with priority given to production volume and moderate sensory requirements, with low monitoring density and a certain degree of process tolerance.

[0045] Example 2, Premium Grade Cigar Tobacco Leaves (Mid-to-High-End Wrapper / Filler): Image acquisition quantity: First preset quantity = 25 images / drying layer, second preset quantity = 18 images / drying layer, third preset quantity = 18 images / drying layer, each drying layer can cover 800-1200 tobacco leaves; Area ratio threshold: The first to fourth preset area ratios are all 85%; Preset temperature difference = 0.3℃ (more sensitive to metabolic changes) Preset reaction time = 60 hours (extending the enzymatic reaction). Preset moisture content range = 12-13% (lower moisture content preserves aroma) Preset moisture gradient ratio range = 1.05-1.1 (narrower gradient ensures uniformity) It is suitable for tobacco leaves that require high uniformity of color and complexity of aroma, improving monitoring coverage and control accuracy.

[0046] Example 3: Top-grade handmade cigar wrapper (high consistency requirement): Image acquisition quantity: First preset quantity = 50 images / drying layer, second preset quantity = 35 images / drying layer, third preset quantity = 35 images / drying layer, each drying layer can cover 2000-3000 tobacco leaves; Area ratio threshold: The first to fourth preset area ratios are all 95%; Preset temperature difference = 0.2℃ (extremely high metabolic sensitivity) Preset active reaction time = 72 hours (to fully develop the delicate aroma) Preset moisture content range: 12.0-12.5% ​​(strict moisture control to prevent cracking) Preset moisture gradient ratio range = 1.0-1.1 (near-perfect equilibrium) For the production of top-grade cigar wrappers, which require flawless appearance and extremely uniform burning, the highest density monitoring and the most stringent thresholds are employed.

[0047] The environmental parameters for each operating condition can be set using existing technologies: The operating conditions during the wilting period are: ambient temperature of 20-25℃, relative humidity of 80-85%, and ventilation of 0.5-1.0 times / hour for air exchange; generally, step 120 lasts for 24-48 hours. The operating conditions during the yellowing period are: ambient temperature of 25-28℃, relative humidity of 85-90%, ventilation rate of 0.3-0.5 times / hour for air exchange, and carbon dioxide concentration of 800-1200ppm; generally, step 130 lasts for 5-7 days. The pre-reaction conditions during the browning period are: ambient temperature of 28-30℃ and relative humidity of 78-82%; The active metabolic conditions during the browning period are: ambient temperature of 30-32℃, relative humidity of 75-78%, and carbon dioxide concentration of 1500-2000ppm; generally, steps 140 and 150 last for 8-10 days. The conditions for color fixing are: ambient temperature of 30-35℃, relative humidity of 65-70%, and ventilation of 1.5-2.0 times / hour for air exchange; generally, step 160 lasts for 4-6 days. The working conditions during the drying period are: ambient temperature of 35-40℃, relative humidity of 55-60%, and ventilation of 2.5-3.0 times / hour for air exchange; generally, step 170 lasts for 7-10 days.

[0048] Figure 3 The diagram illustrates the steps of a method for randomly changing the acquisition method of monitoring images. In one embodiment, as shown... Figure 3 As shown, the method for monitoring and controlling the drying state of cigar tobacco leaves also includes: Step 101: Randomly extract the first monitoring image, the second monitoring image, and the third monitoring image every first preset time interval.

[0049] This step can be performed after step 110. By dynamically and randomly re-extracting multi-view monitoring images every first preset time interval (e.g., 1 hour), continuous, unbiased, and highly timely sampling of the tobacco leaf drying status can be achieved. This effectively captures the dynamic changes in color, shape, and spatial distribution during the drying process, avoids misjudgment caused by single or fixed-position sampling, and improves the accuracy of stage switching judgment.

[0050] In one embodiment, such as Figure 3 As shown, the method for monitoring and controlling the drying state of cigar tobacco leaves also includes: Step 102: Every second preset time interval, randomly change the position of the first monitoring image corresponding to the first camera, the position of the second monitoring image corresponding to the second camera, and the position of the third monitoring image corresponding to the third camera.

[0051] This step can be performed after step 110. By dynamically adjusting the position of each camera at every second preset time interval (e.g., 2 hours), the limitations of fixed-view observation are reduced, the monitoring blind spots caused by tobacco leaf obstruction, uneven lighting, or installation deviation are effectively reduced, the spatial diversity and representativeness of image acquisition are enhanced, and the comprehensiveness and reliability of the assessment of the drying status of the whole warehouse of tobacco leaves are improved.

[0052] Figure 4 The diagram illustrates the process of transitioning to the yellowing stage. In one embodiment, as shown... Figure 4 As shown, step 120, "if the first preset proportion area in the image group to be identified changes to the yellowing period spectrum, end the wilting period and enter the yellowing period control", includes: Step 121: At the beginning of the withering period, obtain the first initial average reflectance in the wavelength range of 675-685 nm.

[0053] In this step, a baseline reflectance in the 675-685nm band is acquired at the beginning of the withering period to establish a reference standard and provide a precise starting point for subsequent dynamic judgment. A multispectral imaging system, such as an industrial camera equipped with a 680nm narrowband filter, can be used.

[0054] Step 122: Monitor the first real-time average reflectance in the wavelength range of 675-685nm.

[0055] In this step, the real-time reflectance of the same wavelength band is continuously monitored to capture the changes in optical response caused by chlorophyll degradation in a non-contact and non-destructive manner, so as to achieve objective and quantitative tracking of the yellowing process.

[0056] Step 123: If the decrease in the first real-time average reflectance relative to the first initial average reflectance is greater than 30%, it is considered to have transitioned to the yellowing period spectrum.

[0057] In this step, a decrease in reflectance of >30% is used as the criterion, corresponding to the physiological node where the chlorophyll residue rate drops below 15%. This ensures that the yellowing stage is accurately triggered when chlorophyll is fully degraded and carotenoid color development is complete, avoiding premature heating and high humidity leading to steaming or entering the stage too late, which would affect aroma formation.

[0058] Figure 5 The diagram illustrates the process of transitioning to the browning stage. In one embodiment, as shown... Figure 5 As shown, step 130, "if the second preset proportion area in the image group to be identified changes to the browning period spectrum, end the yellowing period and enter the browning period control," includes: Step 131: Obtain the second initial average reflectance in the wavelength range of 615-625nm at the beginning of the yellowing period.

[0059] In this step, a baseline reflectance in the 615–625 nm band is established at the beginning of the yellowing period to provide an individualized, unbiased reference for subsequent browning initiation judgment, eliminating the influence of batch-to-batch differences. A multispectral imaging system, such as an industrial camera equipped with a 620 nm narrowband filter, can be used.

[0060] Step 132: Monitor the second real-time average reflectance in the 615-625nm wavelength range.

[0061] In this step, the real-time reflectivity of this band is continuously monitored to sensitively capture the optical changes caused by the generation of brown pigments (such as melanoidins), thus achieving non-contact, dynamic tracking of the initiation of browning.

[0062] Step 133: If the decrease in the second real-time average reflectance relative to the second initial average reflectance is greater than 8%, it is considered to have transitioned to the browning stage spectrum.

[0063] In this step, a reflectance decrease of >8% is used as the switching threshold to precisely correspond to the physiological node where the polyphenol oxidation reaction is significantly initiated, ensuring that the process enters the browning stage at the optimal time and avoiding aroma loss due to insufficient browning or premature heating.

[0064] Figure 6 The diagram illustrates the steps of a method for monitoring tobacco leaf temperature. In one embodiment, as shown... Figure 6 As shown, step 140, "randomly extracting the tobacco leaf temperature of the third preset proportion area in the image group to be identified," includes: Step 141: Extract the temperature monitoring area from the image group to be identified based on the third preset area ratio.

[0065] In this step, a specific area for temperature monitoring is determined. Based on a third preset area ratio, a representative temperature monitoring area is extracted from the image group to be identified. This temperature monitoring area, selected based on the third preset area ratio, is used to reflect the temperature status of the entire batch of tobacco leaves during processing.

[0066] Step 142: Detect temperature data in the temperature monitoring area.

[0067] In this step, the actual temperature data of the selected temperature monitoring area is detected. Temperature measurements of the designated area are performed using appropriate temperature detection techniques or equipment (e.g., infrared thermal imaging).

[0068] Step 143: Obtain the average temperature based on the temperature data and record it as the tobacco leaf temperature.

[0069] In this step, based on the temperature data collected in step 142, the average value of these data is calculated as the temperature of the tobacco leaves. This average temperature value can more accurately reflect the overall temperature trend of the tobacco leaves in the selected area and reduce the error caused by local outliers.

[0070] Figure 7 The diagram illustrates the process of transitioning to the color-fixing period. In one embodiment, as shown... Figure 7 As shown, step 150, "if the browning degree of the fourth preset proportion area in the image group to be identified reaches the leaf condition at the color-fixing stage, then proceed to the color-fixing stage control," includes: Step 151: Obtain multispectral images of the image group to be identified at consecutive time points.

[0071] In this step, time-series data on the color evolution of tobacco leaves is constructed by acquiring multispectral images at continuous time points, providing a highly timely input for dynamically determining the termination of browning.

[0072] Step 152: Extract the hue angle of the multispectral image in the CIELAB color space.

[0073] In this step, the image is converted to the CIELAB space and the hue angle is extracted to represent the hue of the tobacco leaves in a standardized and quantifiable way.

[0074] Step 153: Calculate the hue change of the hue angle between adjacent time points.

[0075] In this step, the change in hue angle is calculated, focusing on whether a new hue is generated, rather than just looking at the color depth, thus improving the rationality of the judgment.

[0076] Step 154: If the absolute value of the hue change is consistently less than 2° and remains at the third preset duration, it is determined that no new hue is generated in the tobacco leaves and the tobacco leaves enter the color fixation period.

[0077] In this step, Δh < 2 and a sustained third preset duration are used as the criterion to distinguish between true browning cessation and short-term fluctuations, ensuring accurate timing of the color-fixing period and preventing premature drying that could lead to color reversion or uneven browning. Specifically, the setting of the third preset duration is strongly correlated with the overall duration of the browning period, for example, it is set to a value between 5% and 10% of the browning period duration, avoiding setting the third preset duration too small or too large as a reference for the drying period transformation.

[0078] In this embodiment, tobacco leaf images are continuously acquired through multispectral imaging, converted to the quantifiable CIELAB color space, and the hue angle (h°) is extracted as a characterization parameter for the stability of browning pigments. The hue angle reflects the "type" of color (such as yellow, reddish-brown, etc.), and its change is directly related to whether new pigments are still being generated. When the absolute value of the change in hue angle at adjacent time points is consistently less than 2° and maintained for a sufficient duration (such as 24 hours), it indicates that the color development reactions such as polyphenol oxidation have basically terminated, and the tobacco leaf color has entered a plateau period. At this time, it is determined that the leaf condition has reached the color fixation period, and it can be safely transferred to the color fixation control stage.

[0079] Figure 8 The diagram illustrates the process of transitioning to the dry rib stage. In one embodiment, as shown... Figure 8 As shown, step 160, "if the color parameter of the fourth preset proportion area in the image group to be identified meets the stable parameter, then enter the dry rib period control," includes: Step 161: Obtain the hue angle of the image group to be identified in the CIELAB color space.

[0080] In this step, by using the hue angle in the CIELAB color space as the evaluation standard, we can more accurately reflect the human eye's perception of color changes, thus providing a more scientific and objective method to monitor changes in tobacco leaf color.

[0081] Step 162: If the hue angle is within the target range of 25° to 40°, and the absolute value of the change in hue angle is less than 1.5° for more than 24 hours, then the color parameters are determined to meet the stable parameters and enter the dry tanning stage.

[0082] In this step, the hue angle is set between 25° and 40°, and the absolute value of its change must remain less than 1.5° for at least 24 hours as the evaluation criterion. This helps to accurately identify the period when the color change of tobacco leaves has stagnated, i.e., when a stable color state has been reached. This method effectively avoids misjudgments caused by short-term fluctuations or measurement errors, ensuring that the drying and strengthening period control only begins when a stable state has truly been reached, thus improving the accuracy and reliability of the processing. Furthermore, this strategy also helps to optimize the tobacco processing and ensure consistent product quality.

[0083] Figure 9 The diagram illustrates the steps involved in calculating the moisture gradient ratio. In one embodiment, as shown... Figure 9 As shown, step 170, "randomly extracting water monitoring areas containing the midrib and mesophyll from the image group to be identified, and detecting the water gradient ratio between the water content of the midrib and the water content of the mesophyll based on the water monitoring areas," includes: Step 171: Based on the preset midrib features and preset leaf mesophyll features, identify and extract a first preset number of water monitoring areas that simultaneously contain midribs and leaf mesophyll from the image group to be identified.

[0084] In this step, by using preset image features of the main vein (such as high texture, low reflectivity, linear structure) and leaf mesophyll (uniform, veinless, medium reflectivity), multiple local areas containing both the main vein and adjacent leaf mesophyll are automatically located and extracted in the image group to be identified as water monitoring units, thereby realizing the extraction of the main vein and leaf mesophyll regions.

[0085] Step 172: Within each moisture monitoring area, based on the positioning of the pre-set main vein characteristics, the first average moisture content of the main vein is detected.

[0086] In this step, within each moisture monitoring area, the main vein region is located based on its morphology, and its average moisture content is detected using moisture-sensitive wavelengths (such as 970nm and 1450nm near-infrared). Near-infrared (NIR) moisture sensors or hyperspectral imaging systems can be used to non-contactly retrieve the main vein moisture content by utilizing the absorption characteristics of water molecules in characteristic wavelengths such as 970nm and 1450nm. The main vein moisture content reflects the internal moisture transport status of the tobacco leaf and is a key parameter for determining whether the drying process is complete.

[0087] Step 173: Within each moisture monitoring area, based on the positioning of preset leaf mesophyll characteristics, select a second preset number of target leaf mesophyll areas and detect the second average moisture content of the target leaf mesophyll areas.

[0088] In this step, within each moisture monitoring area, a second preset number of sub-regions are selected based on leaf mesophyll characteristics to avoid an excessive number of leaf mesophyll regions being identified. Their average moisture content is then calculated to represent the dryness of the tobacco leaf's water storage body.

[0089] Step 174: Based on the first average moisture content of multiple moisture monitoring areas, the average value is taken again to obtain the moisture content of the main vein.

[0090] In this step, the moisture values ​​of the main vein measured in all moisture monitoring areas are averaged again to form a globally uniform moisture content of the main vein, eliminating the deviation caused by single-point anomalies or local unevenness.

[0091] Step 175: Based on the multiple second average moisture contents of multiple moisture monitoring areas, the average value is taken again to obtain the leaf mesophyll moisture content.

[0092] In this step, the leaf mesophyll moisture value of all monitored areas is averaged twice to obtain the overall leaf mesophyll moisture content, which reflects the substrate drying level of the entire batch of tobacco leaves.

[0093] Step 176: Calculate the ratio of the water content of the midrib to the water content of the leaf mesophyll to obtain the water gradient ratio.

[0094] In this step, the ratio of midrib moisture content to mesophyll moisture content (i.e., the moisture gradient ratio) is calculated. This ratio characterizes the degree of uniformity in moisture distribution within the tobacco leaf. The closer the gradient ratio is to 1.0, the more balanced the drying process inside and outside the leaf, and the more thorough the moisture migration.

[0095] An example cigar tobacco drying status monitoring and control system is as follows: Figure 10 The diagram shown is a system structure schematic of a cigar tobacco drying state monitoring and control system. This application also provides a cigar tobacco drying state monitoring and control system, in one embodiment, as follows: Figure 10 As shown, the system includes: a data acquisition module 1001 and a stage control module 1002.

[0096] The data acquisition module 1001 is configured as follows: after cigar tobacco leaves are tied to drying rods to form tobacco leaf rows, a first preset number of first monitoring images are randomly extracted in the acquisition direction facing the tobacco leaf rows; multiple tobacco leaf rows form tobacco leaf columns, and a second preset number of second monitoring images are randomly extracted in the acquisition direction facing the tobacco leaf columns; a third preset number of third monitoring images are randomly extracted in the acquisition direction facing the tobacco leaf columns; multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images form an image group to be identified.

[0097] The stage control module 1002 is communicatively connected to the data acquisition module 1001. The stage control module 1002 is configured to: adjust the environmental conditions to the wilting stage condition; if the first preset proportion area in the image group to be identified changes to the yellowing stage spectrum, end the wilting stage and enter the yellowing stage control; adjust the environmental conditions to the yellowing stage condition; if the second preset proportion area in the image group to be identified changes to the browning stage spectrum, end the yellowing stage and enter the browning stage control; adjust the environmental conditions to the browning stage pre-reaction stage condition; randomly extract the tobacco leaf temperature from the third preset proportion area in the image group to be identified; if the temperature difference between the tobacco leaf temperature and the ambient temperature is less than a preset temperature difference, maintain the browning stage pre-reaction stage condition; if the temperature difference between the tobacco leaf temperature and the ambient temperature is greater than or equal to a preset temperature difference, adjust... The environmental conditions are switched to the browning stage active metabolism condition; after maintaining the browning stage active metabolism condition for a preset active reaction time, if the browning degree of the fourth preset proportion area in the image group to be identified reaches the color-fixing stage leaf condition, then the color-fixing stage control is entered; the environmental conditions are adjusted to the color-fixing stage condition, and if the color parameter of the fourth preset proportion area in the image group to be identified meets the stable parameter, then the dry vein stage control is entered; and the environmental conditions are adjusted to the dry vein stage condition, and the moisture monitoring area containing the midrib and leaf mesophyll is randomly extracted from the image group to be identified. Based on the moisture monitoring area, the moisture gradient ratio of the midrib moisture content and the leaf mesophyll moisture content is detected. If the midrib moisture content decreases to the preset moisture content range and the moisture gradient ratio stabilizes within the preset gradient range, then the drying completion information is generated.

[0098] This embodiment employs multi-angle, random image acquisition combined with spectral analysis to comprehensively and accurately monitor the state changes of tobacco leaves at each drying stage, providing a basis for timely adjustments to environmental conditions. Through refined management of the drying process, the switching control of key nodes can be controlled, contributing to improved overall cigar quality. The entire drying state monitoring and control process is highly automated, reducing manual intervention and improving efficiency and accuracy. This method is applicable to different types of cigar tobacco leaves, allowing for flexible adjustment of parameters according to actual conditions, demonstrating strong versatility and practicality.

[0099] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0100] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0101] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0102] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features of the invention herein.

[0103] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for monitoring and controlling the drying state of cigar tobacco leaves, characterized in that, include: After the cigar tobacco leaves are tied to the drying pole to form a tobacco leaf row, a first preset number of first monitoring images are randomly extracted in the collection direction facing the tobacco leaf row; Multiple rows of tobacco leaves are arranged into a tobacco leaf column, and a second preset number of second monitoring images are randomly extracted in the collection direction of the tobacco leaf column; A third preset number of third monitoring images are randomly extracted from the sampling direction of the tobacco leaf row viewed at an angle; multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images form an image group to be identified; Adjust the environmental conditions to the withering period conditions. If the first preset proportion area in the image group to be identified changes to the yellowing period spectrum, the withering period ends and the yellowing period control begins. Adjust the environmental conditions to the yellowing period conditions. If the second preset ratio area in the image group to be identified changes to the browning period spectrum, the yellowing period ends and the browning period control begins. The environmental conditions are adjusted to the browning stage pre-reaction condition. The tobacco leaf temperature of the third preset proportion area in the image group to be identified is randomly extracted. If the temperature difference between the tobacco leaf temperature and the ambient temperature is less than the preset temperature difference, the browning stage pre-reaction condition is maintained. If the temperature difference between the tobacco leaf temperature and the ambient temperature is greater than or equal to the preset temperature difference, the environmental conditions are adjusted to switch to the browning stage active metabolism condition. After maintaining the browning period active metabolic condition for a preset active reaction time, if the browning degree of the fourth preset proportion area in the image group to be identified reaches the color-fixing period leaf condition, then the color-fixing period control is entered. The environmental conditions are adjusted to the color fixation period conditions. If the color parameters of the fourth preset proportion area in the image group to be identified meet the stable parameters, then the dry rib period control is entered. as well as The environmental conditions are adjusted to the dry-stem stage. A moisture monitoring area containing the midrib and leaf mesophyll is randomly extracted from the image group to be identified. The moisture gradient ratio of the midrib moisture content and the leaf mesophyll moisture content is detected based on the moisture monitoring area. If the midrib moisture content decreases to a preset moisture content range and the moisture gradient ratio stabilizes within the preset gradient range, then drying completion information is generated.

2. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, Also includes: The first monitoring image, the second monitoring image, and the third monitoring image are randomly extracted again every first preset time interval.

3. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, Also includes: The positions of the first monitoring image corresponding to the first camera, the second monitoring image corresponding to the second camera, and the third monitoring image corresponding to the third camera are randomly changed every second preset time interval.

4. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, The step of ending the wilting period and entering the yellowing period control when the first preset proportion area in the image group to be identified changes to the yellowing period spectrum includes: At the start of the withering period, a first initial average reflectance in the wavelength range of 675-685 nm was obtained; The first real-time average reflectance was monitored in the wavelength range of 675-685 nm; and If the decrease in the first real-time average reflectance relative to the first initial average reflectance is greater than 30%, it is considered to have transitioned to the yellowing period spectrum.

5. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, The step of ending the yellowing period and entering the browning period control when the second preset proportion area in the image group to be identified changes to the browning period spectrum includes: A second initial average reflectance in the wavelength range of 615-625 nm was obtained at the beginning of the yellowing period; Monitoring the second real-time average reflectance in the 615-625 nm wavelength range; and If the decrease in the second real-time average reflectance relative to the second initial average reflectance is greater than 8%, it is considered to have transitioned to the browning period spectrum.

6. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, The random extraction of tobacco leaf temperature from the third preset area ratio in the image group to be identified includes: From the group of images to be identified, extract the temperature monitoring area based on the third preset area ratio; Detecting temperature data in the temperature monitoring area; and The average temperature is obtained from the temperature data and recorded as the tobacco leaf temperature.

7. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, If the browning degree of the fourth preset proportion area in the image group to be identified reaches the leaf condition of the color-fixing period, then entering the color-fixing period control includes: Acquire multispectral images of the image group to be identified at consecutive time points; Extract the hue angle of the multispectral image in the CIELAB color space; Calculate the hue change of the hue angle between adjacent time points; and If the absolute value of the hue change is consistently less than 2° and remains at the third preset duration, it is determined that no new hue is generated in the tobacco leaves and the tobacco leaves enter the color fixation period.

8. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, The step of entering the drying phase control if the color parameter of the fourth preset proportion area in the image group to be identified meets the stable parameter includes: Obtain the hue angle of the image group to be identified in the CIELAB color space; and If the hue angle is within the target range of 25° to 40°, and the absolute value of the change in the hue angle remains less than 1.5° for more than 24 hours, then the color parameters are determined to meet the stable parameters and the process enters the dry rib period.

9. The method for monitoring and controlling the drying state of cigar tobacco leaves according to claim 1, characterized in that, The step of randomly extracting a water monitoring region containing the midrib and mesophyll from the image group to be identified, and detecting the water gradient ratio between the midrib water content and the mesophyll water content based on the water monitoring region, includes: Based on preset midrib features and preset leaf mesophyll features, a first preset number of water monitoring areas containing both midrib and leaf mesophyll are identified and extracted from the image group to be identified. Within each of the moisture monitoring areas, the first average moisture content of the main vein is detected based on the positioning of the preset main vein characteristics; Within each of the moisture monitoring areas, based on the positioning of the preset mesophyll characteristics, a second preset number of target mesophyll areas are selected, and the second average moisture content of the target mesophyll areas is detected. Based on the multiple first average moisture contents of the multiple moisture monitoring areas, the average value of the main vein is taken again to obtain the moisture content of the main vein. The leaf mesophyll moisture content is obtained by taking the average of multiple second average moisture contents from multiple moisture monitoring areas; and The ratio of the water content of the midrib to the water content of the leaf mesophyll is calculated to obtain the water gradient ratio.

10. A system for monitoring and controlling the drying state of cigar tobacco leaves, characterized in that, include: The data acquisition module is configured to: after cigar tobacco leaves are tied to drying poles to form a tobacco leaf row, randomly extract a first preset number of first monitoring images in the acquisition direction facing the tobacco leaf row; Multiple rows of tobacco leaves are arranged into a tobacco leaf column, and a second preset number of second monitoring images are randomly extracted in the collection direction of the tobacco leaf column; A third preset number of third monitoring images are randomly extracted from the sampling direction of the tobacco leaf row viewed at an angle; A group of images to be identified is composed of multiple first monitoring images, multiple second monitoring images, and multiple third monitoring images; as well as A stage control module, communicatively connected to the data acquisition module, is configured to: adjust the environmental conditions to the wilting stage; if the first preset proportion area in the image group to be identified changes to the yellowing stage spectrum, end the wilting stage and enter the yellowing stage control; adjust the environmental conditions to the yellowing stage; if the second preset proportion area in the image group to be identified changes to the browning stage spectrum, end the yellowing stage and enter the browning stage control; adjust the environmental conditions to the browning stage pre-reaction stage; randomly extract the tobacco leaf temperature of the third preset proportion area in the image group to be identified; if the temperature difference between the tobacco leaf temperature and the ambient temperature is less than a preset temperature difference, maintain the browning stage pre-reaction stage; if the temperature difference between the tobacco leaf temperature and the ambient temperature is greater than or equal to a preset temperature difference, adjust the environmental conditions... The system switches to the browning stage active metabolic state. After maintaining the browning stage active metabolic state for a preset active reaction time, if the browning degree of the fourth preset proportion area in the image group to be identified reaches the color-fixing stage leaf condition, then it enters the color-fixing stage control. The system adjusts the environmental conditions to the color-fixing stage condition. If the color parameters of the fourth preset proportion area in the image group to be identified meet the stable parameters, then it enters the dry vein stage control. The system also adjusts the environmental conditions to the dry vein stage condition, randomly extracts the moisture monitoring area containing the midrib and leaf mesophyll in the image group to be identified, and detects the moisture gradient ratio of the midrib moisture content and leaf mesophyll moisture content based on the moisture monitoring area. If the midrib moisture content decreases to a preset moisture content range and the moisture gradient ratio stabilizes within a preset gradient range, then the drying completion information is generated.

Images