Method and system for rapidly detecting water holding characteristic of tobacco leaves

Abstract

The invention relates to a method and system for rapidly detecting the water holding characteristic of tobacco leaves. Obtaining weight change data of the at least two groups of tobacco leaf samples, and obtaining fitting parameters based on the weight change data and a preset model function; determining at least two groups of time vectors based on all the fitting parameters and a derivative function corresponding to a preset model function, and determining a correlation coefficient based on each time vector and all the fitting parameters; and determining a target time vector set based on all the correlation coefficients and a preset correlation coefficient threshold, and obtaining a detection duration interval based on the target time vector set. According to the method, the correlation coefficient representing the correlation between the short-time detection time and the water retention characteristic parameters can be accurately obtained by utilizing statistical analysis and a kinetic model, and the optimal detection time interval is obtained, so that the detection time and the labor cost are greatly shortened, the instrument loss and the fault risk caused by long-time operation can be reduced, and the detection efficiency is improved. And rapid quality evaluation and process guidance of a production field are realized.

Description

Technical Field

[0001] The embodiments in this specification belong to the field of tobacco leaf water-holding characteristic detection technology, and specifically relate to a method and system for rapidly detecting the water-holding characteristics of tobacco leaves. Background Technology

[0002] As one of the most critical indicators in the entire cigarette production process, tobacco leaf moisture content is a key focus in the homogenization control of threshing, re-drying, and cigarette manufacturing. During the threshing, re-drying, moistening, and re-drying processes, as well as the cigarette processing and tobacco finishing stages, frequent moisture absorption and release processes occur between the tobacco leaves and the environment. Therefore, exploring the moisture absorption and release characteristics of tobacco leaves themselves and during their processing—that is, the water-holding capacity of tobacco leaves—has a significant impact on guiding parametric processing of tobacco leaves and improving tobacco quality.

[0003] Current research on the water-holding capacity of tobacco leaves mainly relies on multi-station gravimetric gas vapor adsorption analyzers (Dynamic Vapor / Gas Sorption Analyzer, DVS). The detection principle is to observe the weight change of tobacco leaves under different environmental temperature and humidity conditions, thereby measuring the water-holding characteristics of the tobacco leaves. However, in actual production applications, the detection time for the water-holding characteristics of tobacco leaves is too long, which can easily lead to problems such as affecting production progress, increasing consumption, and equipment malfunctions. Summary of the Invention

[0004] The embodiments of this disclosure provide a method and system for rapidly detecting the water-holding properties of tobacco leaves.

[0005] In a first aspect of this disclosure, a method for rapidly detecting the water-holding properties of tobacco leaves is provided. The method includes acquiring weight change data from at least two sets of tobacco leaf samples, and obtaining fitting parameters based on each weight change data and a pre-defined model function. The method further includes determining at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the pre-defined model function, and determining correlation coefficients based on each time vector and all fitting parameters. Furthermore, the method includes determining a target time vector set based on all correlation coefficients and a pre-defined correlation coefficient threshold, and obtaining a detection time interval based on the target time vector set.

[0006] In a second aspect of this disclosure, a system for rapidly detecting the water-holding properties of tobacco leaves is provided. The system includes a fitting parameter determination module configured to acquire weight change data of at least two sets of tobacco leaf samples and obtain fitting parameters based on each weight change data and a preset model function. The system also includes a correlation coefficient determination module configured to determine at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the preset model function, and determine correlation coefficients based on each time vector and all fitting parameters. Furthermore, the system includes a duration interval determination module configured to determine a target set of time vectors based on all correlation coefficients and a preset correlation coefficient threshold, and obtain a detection duration interval based on the target set of time vectors.

[0007] In a third aspect of this disclosure, a computer program product is provided, comprising a computer program that is executed by a processor to implement the method according to the first aspect.

[0008] In a fourth aspect of this disclosure, a machine-readable storage medium is provided. The machine-readable storage medium stores machine-executable instructions, which are executed by a processor to implement the method provided according to a first aspect of this disclosure.

[0009] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram of an example environment in which some embodiments of this disclosure may be implemented is shown;

[0012] Figure 2 A flowchart of a method for rapidly detecting the water-holding properties of tobacco leaves, according to some embodiments of this disclosure, is shown.

[0013] Figure 3 A schematic diagram of the main components of a multi-station gravimetric gas vapor adsorption apparatus according to some embodiments of the present disclosure is shown;

[0014] Figure 4 A schematic diagram of the variation curve of the duration derivative function according to some embodiments of this disclosure is shown;

[0015] Figure 5 A schematic diagram of the constant correlation coefficient variation curve is shown for some embodiments of this disclosure;

[0016] Figure 6 A schematic diagram of a time-dependent moisture content variation curve is shown for some embodiments of this disclosure;

[0017] Figure 7 A block diagram of a system for rapidly detecting the water-holding properties of tobacco leaves, according to some embodiments of this disclosure, is shown; and

[0018] Figure 8 A block diagram of an electronic device that can implement several embodiments of the present disclosure is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0020] The terms “comprising” and “having”, and any variations thereof, in this specification, claims, and the foregoing drawings are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. Depending on the context, the word “if” as it applies herein may be interpreted as “when”, “when”, “in response to determination”, or “in response to detection”.

[0021] As mentioned above, current research on the water-holding capacity of tobacco leaves mainly relies on a multi-station gravimetric gas vapor adsorption analyzer (DVS). The principle is to observe the weight changes of tobacco leaves under different environmental temperature and humidity conditions to measure their water-holding characteristics. However, the DVS requires tobacco samples to reach dynamic equilibrium at each set humidity level. As a porous biomass material, tobacco leaves reach equilibrium extremely slowly. Under specific temperature and humidity conditions, it takes at least 15 hours from the start of moisture exchange between the tobacco sample and the environment to reaching dynamic equilibrium, and each measurement requires 3-5 equilibrium cycles. This results in an average testing time of approximately 60 hours for a single set of tobacco samples. This leads to two problems in practical production applications: firstly, it prevents timely acquisition of water-holding capacity data before tobacco processing, potentially delaying process planning and affecting production schedules; secondly, it increases the consumption of carrier gas, personnel, and electricity, as well as the risks associated with equipment malfunctions.

[0022] Therefore, embodiments of this disclosure propose a method for rapidly detecting the water-holding properties of tobacco leaves. The method includes acquiring weight change data from at least two sets of tobacco leaf samples, and obtaining fitting parameters based on each weight change data and a preset model function. The method further includes determining at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the preset model function, and determining correlation coefficients based on each time vector and all fitting parameters. Furthermore, the method includes determining a target time vector set based on all correlation coefficients and a preset correlation coefficient threshold, and obtaining a detection time interval based on the target time vector set.

[0023] In this way, based on the weight change data of tobacco leaf samples from different origins, statistical analysis and kinetic models can be used to accurately obtain the correlation coefficient characterizing the correlation between short-term detection time and water-holding characteristic parameters. Combined with the preset correlation coefficient threshold, the optimal detection time range can be obtained. This not only significantly shortens the detection time, reduces equipment occupancy costs, power consumption, high-purity carrier gas consumption and labor costs, but also reduces the risk of instrument wear and tear and failure due to long-term operation. It can be widely applied to tobacco leaf raw materials from different production areas, grades or parts, thereby realizing rapid quality evaluation and process guidance on the production site.

[0024] Figure 1 Schematic diagrams are shown illustrating example environments in which some embodiments of this disclosure can be implemented. For example... Figure 1As shown, the example environment 100 may include a multi-station gravimetric gas vapor adsorption analyzer (Dynamic Vapor / Gas Sorption Analyzer, or DVS for short) 101. This multi-station gravimetric gas vapor adsorption analyzer 101 acquires the weight change data of tobacco leaf samples of different origin grades as they continuously change from the initial relative humidity to the equilibrium moisture content, and the weight change data as they continuously change from the step to the target relative humidity to the equilibrium moisture content, by setting the initial relative humidity, the target relative humidity, and the constant temperature. Here, the constant temperature setting range is 25-45℃, and the initial relative humidity is less than the target relative humidity. For example, the constant temperature can be set to 25℃, the initial relative humidity to 60%, and the target relative humidity to 80%. At this time, all weight change data can include the weight change data of tobacco leaf samples continuously changing to equilibrium moisture content at a temperature of 25℃ and a humidity of 60% (that is, the weight of tobacco leaf samples corresponding to multiple consecutive time periods, and the weight of tobacco leaf samples corresponding to the last few time periods remains unchanged), and the weight change data of tobacco leaf samples continuously changing to equilibrium moisture content at a temperature of 25℃ and a humidity step from 60% to 80% (that is, the weight of tobacco leaf samples corresponding to multiple consecutive time periods, and the weight of tobacco leaf samples corresponding to the last few time periods remains unchanged).

[0025] Understandably, before using a multi-station gravimetric gas vapor adsorption (GFPA) instrument to treat tobacco leaf samples with vapor adsorption, the testing personnel can obtain tobacco leaf raw materials of different origins and grades. Using a perforator, 20 circular tobacco leaf samples with a radius of 0.75 cm are prepared from each raw material. Then, all tobacco leaf samples from each raw material are placed in a constant temperature and humidity chamber for equilibration. Finally, all tobacco leaf samples from each equilibrated raw material are placed in the multi-station gravimetric GFPA instrument. The constant temperature and humidity chamber can be set to maintain constant temperature, constant humidity, and equilibration time; for example, a constant temperature of 25℃, a constant humidity of 60%, and an equilibration time of 24 hours can be set.

[0026] Example environment 100 may further include a processing terminal 102, which establishes a communication connection with a multi-station gravimetric gas vapor adsorption instrument 101 to acquire weight change data corresponding to tobacco leaf samples of various origin grades collected by the multi-station gravimetric gas vapor adsorption instrument 101, and determines fitting parameters based on the weight change data and a preset model function. Here, the preset model function may be, for example, a Weibull distribution model function. The parameters in the Weibull distribution model function are solved by substituting the weight change data into the fitting data, and the solved parameters are used as the fitting parameters.

[0027] Furthermore, the processing terminal 102 can determine at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the preset model function, and determine the correlation coefficient based on each time vector and all fitting parameters. Here, each set of time vectors has multiple durations, the total number of durations being consistent with the total number of tobacco sample groups, and each time vector has a corresponding constant. It can be understood that the correlation coefficient can be used to characterize the correlation between the detection time and the water-holding characteristic parameter. The closer the correlation coefficient is to 1, the stronger the correlation between the corresponding detection time and the water-holding characteristic parameter; the closer the correlation coefficient is to 0, the weaker the correlation between the corresponding detection time and the water-holding characteristic parameter.

[0028] Furthermore, the processing terminal 102 can determine a target time vector set based on all correlation coefficients and a preset correlation coefficient threshold, and obtain a detection duration interval based on the target time vector set. Here, the target time vector set can be understood as including target time vectors corresponding to all correlation coefficients greater than the preset correlation coefficient threshold. Each target time vector has a target duration consistent with the number of tobacco sample groups. The optimal detection duration interval is determined by combining all target durations possessed by all target time vectors.

[0029] Understandably, after determining the detection time range, for subsequent tobacco leaf samples of different origins and grades, when using the multi-station gravimetric gas vapor adsorption instrument 101 to obtain the corresponding weight change data, the detection time can be controlled within the detection time range. By comparing the weight, moisture content ratio, or curve characteristics fitted based on short-term data of different tobacco leaf samples at the end of the detection, the water-holding characteristics can be quickly and reliably evaluated and compared, thereby guiding production decisions.

[0030] It should be understood that the architecture and functionality in example environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. Embodiments of this disclosure can also be applied to other environments with different architectures and / or functionalities.

[0031] Figure 2 A flowchart illustrating a method for rapidly detecting the water-holding properties of tobacco leaves, according to some embodiments of this disclosure, is shown. Method 200 may, for example, be derived from... Figure 1 The processing terminal in the example environment shown executes. For example... Figure 2 As shown in box 202, method 200 can acquire weight change data of at least two sets of tobacco leaf samples, and obtain fitting parameters based on each weight change data and a preset model function. Here, the processing terminal can... Figure 1The example environment shown uses a multi-station gravimetric gas vapor adsorption instrument to acquire weight change data corresponding to tobacco leaf samples of various origin grades. The parameters of the preset model function are solved by substituting the weight change data into the preset model function for fitting, and the solved parameters are used as the fitting parameters. In one example, tobacco leaf samples with significant differences in origin grades can be selected as the implementation objects, such as acquiring weight change data corresponding to tobacco leaf samples from four origin grades: Hunan Chenzhou C-grade, Sichuan Liangshan C22, Hubei Enshi C-grade, and Henan Luohe C22.

[0032] Understandably, before using a multi-station gravimetric gas vapor adsorption (GFPA) instrument to treat tobacco leaf samples with vapor adsorption, the testing personnel can obtain tobacco leaf raw materials of different origins and grades. Using a perforator, 20 circular tobacco leaf samples with a radius of 0.75 cm are prepared from each raw material. Then, all tobacco leaf samples from each raw material are placed in a constant temperature and humidity chamber for equilibration. Finally, all tobacco leaf samples from each equilibrated raw material are placed in the multi-station gravimetric GFPA instrument. The constant temperature and humidity chamber can be set to maintain constant temperature, constant humidity, and equilibration time; for example, a constant temperature of 25℃, a constant humidity of 60%, and an equilibration time of 24 hours can be set.

[0033] Please see Figure 3 The diagram shows a schematic representation of the main components of a multi-station gravimetric gas vapor adsorption apparatus according to some embodiments of the present disclosure. Figure 3As shown, the multi-station gravimetric gas vapor adsorption analyzer 300 may include at least a dry-path MFC, a wet-path MFC, a gas / vapor DVS switching valve, a DVS reagent tube heater, a reagent tube thermostatic bath, a test chamber, and a test position thermostatic bath. The dry-path MFC is used to precisely control the flow rate of the drying carrier gas; the wet-path MFC is used to precisely control the flow rate of water vapor flowing through the steam generator; the gas / vapor DVS switching valve is used to direct the water vapor flowing out of the wet-path MFC to the DVS saturated tube in the reagent tube thermostatic bath; the DVS reagent tube heater is used to control the gas temperature in the DVS reagent tube (not used in the embodiments of this disclosure); and the reagent tube thermostatic bath is used to precisely control the DVS saturated tube to a constant temperature and ensure... The relative humidity of the water vapor flowing into the DVS saturation tube is 100%. Inside the test chamber, a sample crucible and a microbalance are placed to uniformly purge the tobacco sample within the crucible with a mixture of dry carrier gas and 100% relative humidity water vapor at a specified relative humidity ratio. The microbalance continuously collects weight change data of the tobacco sample and continuously purges DVS protective gas around the balance beam and bearings to prevent adsorbed vapor from diffusing to sensitive parts of the balance, causing corrosion, condensation, or measurement interference. A constant temperature bath at the test position is used to precisely control the internal temperature of the test chamber to a constant temperature; for example, the sample tube is used to precisely control the temperature of the tobacco sample. Furthermore, when using a multi-station gravimetric gas vapor adsorption analyzer to treat tobacco samples for vapor adsorption, samples of the same origin and grade can be placed in sample crucibles 1 and 4, and samples of other origin and grade tobacco samples can be placed in sample crucibles 2 and 3. This effectively ensures the reliability and efficiency of the weight change data obtained from tobacco samples of different origin and grades.

[0034] The multi-station gravimetric gas vapor adsorption analyzer of this disclosure acquires weight change data of tobacco leaf samples of different origin grades as they continuously change to equilibrium moisture content at the initial relative humidity, and as they continuously change to equilibrium moisture content at the target relative humidity, by setting an initial relative humidity, a target relative humidity, and a constant temperature. Here, the constant temperature is set in the range of 25-45°C, and the initial relative humidity is less than the target relative humidity. For example, the constant temperature can be set to 25°C, the initial relative humidity to 60%, and the target relative humidity to 80%. In this case, all weight change data can include weight change data of tobacco leaf samples continuously changing to equilibrium moisture content at a temperature of 25°C and a humidity of 60% (i.e., multiple consecutive time periods and the tobacco leaf sample weight corresponding to each time period, with the tobacco leaf sample weight remaining unchanged for the last few time periods), and weight change data of continuously changing to equilibrium moisture content at a temperature of 25°C and a humidity step from 60% to 80% (i.e., multiple consecutive time periods and the tobacco leaf sample weight corresponding to each time period, with the tobacco leaf sample weight remaining unchanged for the last few time periods).

[0035] In some implementations, when the processing terminal obtains fitting parameters based on the weight change data and a preset model function, it can determine the first equilibrium moisture content of the tobacco sample at the initial relative humidity, the second equilibrium moisture content at the target relative humidity, and the moisture content at at least two time periods based on the weight change data. The initial relative humidity is less than the target relative humidity. Here, the first equilibrium moisture content can be understood as the same moisture content collected by the tobacco sample for multiple consecutive time periods at the initial relative humidity, that is, the moisture content of the tobacco sample when it reaches equilibrium moisture content at the initial relative humidity; the second equilibrium moisture content can be understood as the same moisture content collected by the tobacco sample for multiple consecutive time periods at the target relative humidity, that is, the moisture content of the tobacco sample when it reaches equilibrium moisture content at the target relative humidity; the at least two time periods can be understood as multiple randomly selected time periods within the time period from when the tobacco sample is at the initial relative humidity to when it reaches equilibrium moisture content at the target relative humidity.

[0036] Subsequently, the processing terminal can determine the moisture content ratio based on the water content, the first equilibrium moisture content, and the second equilibrium moisture content at each time period. Here, the water content, the first equilibrium moisture content, and the second equilibrium moisture content at each time period can be substituted into the moisture content ratio calculation formula shown below to obtain the moisture content ratio corresponding to each time period:

[0037]

[0038] In the above formula, y represents the moisture content ratio. Let be the water content at time t. The second equilibrium water content, This represents the first equilibrium water content.

[0039] Subsequently, the processing terminal can fit a preset model function based on all durations and the corresponding humidity ratios to obtain the fitting parameters. Here, the preset model function can be understood as a Weibull distribution model function. By substituting all durations and the corresponding humidity ratios to perform fitting, the parameters in the Weibull distribution model function are solved, and the solved parameters are used as the fitting parameters.

[0040] In one example, the default model function can be seen in the function expression shown below:

[0041]

[0042] In the above formula, y is the moisture content ratio, t is the duration, and a and b are the parameters to be solved (i.e., the fitting parameters). Among them, a can be used as a water-holding characteristic parameter, and the larger the value, the stronger the water-holding capacity of the corresponding tobacco leaf sample; b can be used as a shape parameter.

[0043] In one example, taking the weight change data corresponding to tobacco leaf samples from four different origins—Chenzhou (Hunan), Liangshan (Sichuan), Enshi (Hubei), and Luohe (Henan)—as an example, the fitting parameters corresponding to the Hunan Chenzhou C-grade tobacco leaf sample can be expressed as (a1, b1) = (131.58, 1.12), the fitting parameters corresponding to the Sichuan Liangshan C22 tobacco leaf sample can be expressed as (a2, b2) = (153.15, 1.09), the fitting parameters corresponding to the Hubei Enshi C-grade tobacco leaf sample can be expressed as (a3, b3) = (163.27, 1.07), and the fitting parameters corresponding to the Henan Luohe C22 tobacco leaf sample can be expressed as (a4, b4) = (191.65, 1.24).

[0044] In box 204, method 200 can determine at least two sets of time vectors based on all fitted parameters and the derivative function corresponding to the preset model function, and determine the correlation coefficient based on each time vector and all fitted parameters. Here, each set of time vectors has multiple durations, the total number of durations being consistent with the total number of tobacco sample groups, and each time vector has a corresponding constant. It is understood that the correlation coefficient can be used to characterize the correlation between the detection time and the water-holding characteristic parameter; the closer the correlation coefficient is to 1, the stronger the correlation between the corresponding detection time and the water-holding characteristic parameter; the closer the correlation coefficient is to 0, the weaker the correlation between the corresponding detection time and the water-holding characteristic parameter.

[0045] In some implementations, when the processing terminal determines at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the preset model function, it can select at least two constants within a preset constant range. Here, the preset constant range can be set to... That is, to randomly traverse multiple constants within the range of constants less than 0, for example, by using software programming to exhaustively search for as many constants as possible from this range of constants less than 0.

[0046] The processing terminal then substitutes each fitted parameter into the derivative function corresponding to the preset model function, and solves the derivative function for each fitted parameter based on each constant to obtain the solution time. The derivative function corresponding to the preset model function can be found in the function expression shown below:

[0047]

[0048] In the above formula, To substitute the derivative value of the fitting parameters corresponding to the i-th group of tobacco leaf samples, where t is the time duration, and The fitting parameters are for the i-th group of tobacco samples, where i takes the values ​​1, 2, 3...n, and n is the number of all tobacco sample groups (e.g., when the number of all tobacco sample groups is 4, n is 4).

[0049] It is understandable that by substituting the constants as the derivative values ​​of the fitting parameters corresponding to the i-th group of tobacco leaf samples (i.e., (where k is a constant), the FindRoot function of the Wolfram Mathematica mathematical software is used to solve for the derivatives of each substituted constant and fitting parameter to obtain the corresponding solution time.

[0050] The processing terminal then integrates all solution times corresponding to each constant according to the numbering order of all tobacco leaf samples to obtain a time vector. The time vector can be seen in the vector expression shown below:

[0051]

[0052] In the above formula, Let j be the time vector corresponding to a constant number of iterations. Let j be a constant representing the number of iterations and the solution time corresponding to the nth group of tobacco leaf samples.

[0053] Please see Figure 4 The diagram illustrates a variation curve of a duration derivative function according to some embodiments of the present disclosure. Figure 4 As shown, the duration derivative function variation curve 400 can be based on the fitting parameters mentioned in the above examples corresponding to the Hunan Chenzhou C-type tobacco sample (a1=131.58, b1=1.12), the fitting parameters corresponding to the Sichuan Liangshan C22 tobacco sample (a2=153.15, b2=1.09), the fitting parameters corresponding to the Hubei Enshi C-type tobacco sample (a3=163.27, b3=1.07), and the fitting parameters corresponding to the Henan Luohe C22 tobacco sample (a4=1). The results obtained are: (a1=131.58, b1=1.12), (b2=153.15, b2=1.09), (a3=163.27, b3=1.07), and (a4=191.65, b4=1.24).

[0054] In some implementations, when determining the correlation coefficient based on each time vector and all fitted parameters, the processing terminal can extract water-holding characteristic parameters from each fitted parameter and integrate all water-holding characteristic parameters according to the numbering order of all tobacco leaf samples to obtain a set of water-holding characteristic parameters. Here, referring to the above embodiments, it can be seen that each fitted parameter includes water-holding characteristic parameters and shape parameters. By integrating the water-holding characteristic parameters from each fitted parameter according to the numbering order of all tobacco leaf samples, the resulting set of water-holding characteristic parameters corresponds to the time vector. For example, when the time vector is represented as... At that time, the corresponding set of water-holding characteristic parameters is expressed as: .

[0055] The processing terminal can then substitute the time vectors and water-holding characteristic parameter sets into a preset correlation coefficient formula to obtain the correlation coefficient. The preset correlation coefficient formula can be found in the following correlation coefficient calculation formula:

[0056]

[0057] In the above formula, Let be the correlation coefficient between the time vector corresponding to the constant with traversal number j and the set of water-holding characteristic parameters. Let j be the time vector corresponding to a constant number of iterations. This is a set of water-holding characteristic parameters.

[0058] In box 206, method 200 can determine a target time vector set based on all correlation coefficients and a preset correlation coefficient threshold, and obtain a detection duration interval based on the target time vector set. Here, the target time vector set can be understood as including target time vectors corresponding to all correlation coefficients greater than the preset correlation coefficient threshold. Each target time vector has a target duration consistent with the number of tobacco sample groups. The optimal detection duration interval is determined by combining all target durations possessed by all target time vectors.

[0059] Understandably, after determining the detection time range, for subsequent tobacco leaf samples of different origins and grades, the detection time can be controlled within this range when obtaining the corresponding weight change data using a multi-station gravimetric gas vapor adsorption instrument. By comparing the weight, moisture content ratio, or curve characteristics fitted from short-term data of different tobacco leaf samples at the end of the detection, the water-holding characteristics can be quickly and reliably evaluated and compared, thereby guiding production decisions.

[0060] In some implementations, when determining the target time vector set based on all correlation coefficients and a preset correlation coefficient threshold, the processing terminal can filter out all correlation coefficients greater than the preset threshold from all correlation coefficients. Here, the preset correlation coefficient threshold can be understood as a threshold used to distinguish strong correlations. For example, it can be set to 0.7, meaning that a correlation coefficient greater than 0.7 indicates a strong correlation between the corresponding time vector and the water-holding characteristic parameter set, while a correlation coefficient less than or equal to 0.7 indicates a weak correlation between the corresponding time vector and the water-holding characteristic parameter set.

[0061] Please see Figure 5 The diagram illustrates a constant correlation coefficient variation curve according to some embodiments of the present disclosure. Figure 5 As shown in the figure, the constant correlation coefficient variation curve 500 shows multiple constants in the range of -0.0030 to 0 and the corresponding correlation coefficients of each constant. It can be seen that the correlation coefficients of multiple constants in the range of approximately -0.0026 to 0 are all greater than 0.7, which means that they have a strong correlation with the set of water holding characteristic parameters.

[0062] Subsequently, the processing terminal can determine the target constant interval based on all correlation coefficients greater than a preset correlation coefficient threshold, and determine the target constant set from the target constant interval according to a preset step size. Here, based on all correlation coefficients greater than the preset correlation coefficient threshold, the constants corresponding to each correlation coefficient can be determined. The interval consisting of the smallest and largest constants selected from all constants is taken as the target constant interval, and multiple consecutive target constants are determined from this target constant interval according to a preset step size (e.g., 0.0001), with the interval between each two adjacent target constants being the preset step size. For example, taking the target constant interval as (-0.0026, -0.001), the target constant set can be determined to include -0.0026, -0.0025, -0.0024, ... -0.001.

[0063] Subsequently, the processing terminal can solve for the derivative function of each fitted parameter based on the target constants in the target constant set to obtain the target duration. It is understood that the process of determining the target duration can be found above, and will not be elaborated upon here.

[0064] Subsequently, the processing terminal can integrate all target durations corresponding to each target constant according to the numbering order of all tobacco leaf samples to obtain target time vectors, and then integrate all target time vectors into a target time vector set. Here, the target time vectors corresponding to each target constant have target durations consistent with the number of tobacco leaf sample groups, and are arranged according to the numbering order of all tobacco leaf samples.

[0065] In one example, see the constant-correlation coefficient-time vector correspondence table shown below:

[0066]

[0067] It can be seen that the constant (i.e., k) ranges from -0.0026 to -0.001, and all the corresponding constants (i.e., p) are greater than 0.7. The t1, t2, t3 and t4 corresponding to each constant together form the target time vector as the target duration.

[0068] In some implementations, when the processing terminal obtains the detection duration interval based on the target time vector set, it can identify the minimum and maximum target durations from the target time vector set, and obtain the detection duration interval based on the minimum and maximum target durations. In one example, taking the constant-correlation coefficient-time vector correspondence table mentioned above as an example, the minimum target duration of 150.872 and the maximum target duration of 335.38 can be identified within the target constant interval (-0.0026, -0.001). Considering increasing operational safety redundancy, reserving buffers for sample variability, and production management habits, the minimum and maximum target durations are adjusted upwards respectively, thus obtaining an integer value range that is easy to schedule and manage in production, such as (200, 350) as the final recommended detection duration interval.

[0069] It can be seen that the final determined detection time range is significantly shorter than the traditional detection time (e.g., from more than 70 hours to less than 24 hours), which can reduce the experimental risks and various investments, while still meeting most of the information for characterizing the water-holding characteristics of tobacco leaf samples, and there is trend comparability between different origin grades.

[0070] In some implementations, to effectively determine the reliability of the moisture content ratio of tobacco leaf samples from different origins, the processing terminal can, after acquiring at least two sets of weight change data for tobacco leaf samples, construct a time-based moisture content ratio change curve based on each weight change data, and determine the similarity between each time-based moisture content ratio change curve and all other time-based moisture content ratio change curves. Here, the moisture content ratio determination process mentioned above can be referred to to obtain the moisture content ratio corresponding to multiple consecutive time periods in each weight change data. Then, based on all time periods and the moisture content ratio corresponding to each time period, a time-based moisture content ratio change curve is constructed, and the similarity between each time-based moisture content ratio change curve and all other time-based moisture content ratio change curves is calculated based on the slope trend of each time-based moisture content ratio change curve.

[0071] It is understandable that the slope change trend of the humidity ratio change curve for each duration can be composed of the slopes corresponding to multiple consecutive durations. The slope corresponding to each duration can be calculated based on the corresponding duration, the humidity ratio of the corresponding duration, the humidity ratio of the adjacent preceding duration, and the humidity ratio of the adjacent preceding duration. The slope change trend of any two duration humidity ratio change curves can be predicted by a pre-trained neural network to obtain the corresponding prediction similarity. The maximum value among all prediction similarities corresponding to each duration humidity ratio change curve is taken as the similarity between the corresponding duration humidity ratio change curve and all other duration humidity ratio change curves.

[0072] Of course, the pre-trained neural network mentioned in this disclosure can be a predictive neural network architecture well known in the art. When training this neural network, the training set includes slope change trend samples of multiple time-based humidity ratio change curves and similarity labels between any two time-based humidity ratio change curve slope change trend samples. The loss function can be set to calculate the mean square error between the predicted similarity and the corresponding similarity label. The corresponding predicted similarity is obtained by using the slope change trend samples of any two time-based humidity ratio change curves as input. Then, the total loss is calculated by the loss function based on multiple predicted similarities and the similarity labels corresponding to each predicted similarity. The optimizer is then used to update the weights of the neural network based on the total loss to minimize the total loss until the maximum number of training epochs is reached. In addition, embodiments of this disclosure may also use other calculation processes (such as Euclidean distance) to determine the similarity between each time-based humidity ratio change curve and all other time-based humidity ratio change curves, which will not be elaborated here.

[0073] Subsequently, the processing terminal can determine whether each similarity exceeds a preset similarity threshold, and in response to determining that any similarity does not exceed the preset similarity threshold, it can determine that the weight change data corresponding to that similarity is abnormal. Here, when any similarity does not exceed the preset similarity threshold, it indicates that there is a significant difference between the slope trend of the corresponding weight change data's time-dependent moisture content ratio change curve and all other time-dependent moisture content ratio change curves, which may be caused by unreasonable weight change data. Therefore, the corresponding weight change data can be determined to be abnormal, and the testing personnel can be notified to re-process the corresponding tobacco leaf sample with vapor adsorption using a multi-station gravimetric gas vapor adsorption instrument.

[0074] please Figure 6 The diagram illustrates a time-dependent moisture content variation curve according to some embodiments of the present disclosure. Figure 6As shown, the time-dependent moisture content ratio (WHM) change curve 600 can be obtained based on the weight change data corresponding to the tobacco leaf samples from Hunan Chenzhou C-type (i.e., the fitting parameters are a1=131.58, b1=1.12), Sichuan Liangshan C22 tobacco leaf samples (i.e., the fitting parameters are a2=153.15, b2=1.09), Hubei Enshi C-type tobacco leaf samples (i.e., the fitting parameters are a3=163.27, b3=1.07), and Henan Luohe C22 tobacco leaf samples (i.e., the fitting parameters are a4=191.65, b4=1.24). It can be seen that there is a high degree of similarity between the slope trends of each WHM change curve and all other WHM change curves, thus confirming that all weight change data are reasonable.

[0075] Figure 7 A block diagram of a system for rapidly detecting the water-holding properties of tobacco leaves according to some embodiments of this disclosure is shown. The various embodiments in this specification are described in a progressive manner, with reference to each other for similar or identical parts. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple, and relevant parts can be referred to in the description of the method embodiments. Figure 7 As shown, the system 700 for rapidly detecting the water-holding properties of tobacco leaves may include at least a fitting parameter determination module 702, configured to acquire weight change data of at least two sets of tobacco leaf samples, and obtain fitting parameters based on each weight change data and a preset model function. The system 700 also includes a correlation coefficient determination module 704, configured to determine at least two sets of time vectors based on all fitting parameters and the derivative function corresponding to the preset model function, and determine the correlation coefficient based on each time vector and all fitting parameters. Furthermore, the system 700 also includes a time interval determination module 706, configured to determine a target time vector set based on all correlation coefficients and a preset correlation coefficient threshold, and obtain a detection time interval based on the target time vector set.

[0076] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0077] Figure 8 Block diagrams of electronic devices that can implement various embodiments of the present disclosure are shown. For example... Figure 8 As shown, the electronic device 800 includes a processor 801, which can perform various appropriate actions and processes based on computer program instructions loaded into random access memory (RAM) 803 according to computer program instructions stored in read-only memory (ROM) 802. The RAM 803 may also store various programs and data required for the operation of the electronic device 800. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0078] The various processes and procedures described above, such as method 200, can be executed by processor 801. For example, in some embodiments, method 200 may be implemented as a software program tangibly contained in a machine-readable medium. In some embodiments, part or all of the software program may be loaded into and / or installed onto electronic device 800 via ROM 802. When the software program is loaded into RAM 803 and executed by processor 801, one or more actions of method 200 described above may be performed.

[0079] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload programmable logic devices (CPLDs), and so on.

[0080] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] This disclosure can be a method, apparatus, system, and / or program product. The program product may include a machine-readable storage medium on which machine-readable program instructions for performing various aspects of this disclosure are loaded. The machine-readable program instructions described herein can be downloaded from the machine-readable storage medium to various computing / processing devices, or downloaded via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the machine-readable program instructions from the network and forwards them to the machine-readable storage medium in the respective computing / processing device.

[0082] Machine program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. Machine-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the machine-readable program instructions to implement various aspects of this disclosure.

[0083] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0084] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for rapidly detecting the water-holding properties of tobacco leaves, characterized in that, include: Obtain weight change data for at least two sets of tobacco leaf samples, and obtain fitting parameters based on each set of weight change data and a preset model function; Based on all the fitting parameters and the derivative function corresponding to the preset model function, at least two sets of time vectors are determined, and based on each time vector and all the fitting parameters, the correlation coefficient is determined. as well as Based on all the aforementioned correlation coefficients and the preset correlation coefficient threshold, a target time vector set is determined, and a detection duration interval is obtained based on the target time vector set.

2. The method according to claim 1, characterized in that, The fitting parameters are obtained based on the weight change data and the preset model function, including: Based on the weight change data, the first equilibrium moisture content of the tobacco sample at the initial relative humidity, the second equilibrium moisture content at the target relative humidity, and the moisture content at at least two time periods are determined, wherein the initial relative humidity is less than the target relative humidity. Based on the moisture content, the first equilibrium moisture content, and the second equilibrium moisture content at each specified duration, the moisture content ratio is determined; and The preset model function is fitted based on all the stated durations and the humidity ratio corresponding to each stated duration to obtain the fitting parameters.

3. The method according to claim 1, characterized in that, Based on all the fitting parameters and the derivative function corresponding to the preset model function, at least two sets of time vectors are determined, including: Select at least two constants within a preset range; Substitute each of the fitting parameters into the derivative function corresponding to the preset model function, and solve the derivative function of each fitting parameter based on each of the constants to obtain the solution time; and According to the numbering order of all the tobacco leaf samples, the solution durations corresponding to each constant are integrated to obtain a time vector.

4. The method according to claim 3, characterized in that, The fitting parameters include water-holding characteristic parameters and shape parameters; The determination of the correlation coefficient based on each of the time vectors and all the fitting parameters includes: The water-holding characteristic parameters are extracted from each of the fitted parameters, and then integrated according to the numbering order of all the tobacco leaf samples to obtain a set of water-holding characteristic parameters; and Substitute each of the time vectors and the set of water-holding characteristic parameters into the preset correlation coefficient formula to obtain the correlation coefficient.

5. The method according to claim 4, characterized in that, The step of determining the target time vector set based on all the correlation coefficients and a preset correlation coefficient threshold includes: From all the correlation coefficients, select all correlation coefficients that are greater than a preset correlation coefficient threshold; A target constant interval is determined based on all correlation coefficients greater than the preset correlation coefficient threshold, and a target constant set is determined from the target constant interval according to a preset step size; Based on each target constant in the set of target constants, the derivative function of each fitting parameter is solved to obtain the target duration; and According to the numbering order of all the tobacco leaf samples, all the target durations corresponding to each target constant are integrated to obtain target time vectors, and all the target time vectors are integrated into a target time vector set.

6. The method according to claim 5, characterized in that, The step of obtaining the detection duration interval based on the target time vector set includes: Identify the minimum target duration and the maximum target duration from the set of target time vectors; and Based on the minimum target duration and the maximum target duration, the detection duration interval is obtained.

7. The method according to claim 1, characterized in that, The method further includes: Based on the weight change data, a time-dependent moisture content ratio change curve is constructed, and the similarity between each time-dependent moisture content ratio change curve and all other time-dependent moisture content ratio change curves is determined. Determine whether each of the aforementioned similarities exceeds a preset similarity threshold; and In response to determining that any of the similarities does not exceed the preset similarity threshold, the weight change data corresponding to the similarity is determined to be abnormal.

8. A system for rapidly detecting the water-holding properties of tobacco leaves, characterized in that, include: The fitting parameter determination module is configured to acquire weight change data of at least two sets of tobacco leaf samples, and obtain fitting parameters based on each set of weight change data and a preset model function; The correlation coefficient determination module is configured to determine at least two sets of time vectors based on all the fitting parameters and the derivative function corresponding to the preset model function, and to determine the correlation coefficient based on each time vector and all the fitting parameters. as well as The duration interval determination module is configured to determine a target time vector set based on all the aforementioned correlation coefficients and a preset correlation coefficient threshold, and to obtain a detection duration interval based on the target time vector set.

9. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-7.

10. An electronic device, characterized in that, include: One or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method as described in any one of claims 1-7.

Images