A method and system for predicting the over-ripening period of middle tobacco leaves

Abstract

The present invention relates to the technical field of tobacco leaf overripe period prediction, and in particular to a method and system for predicting the overripe period of the middle tobacco leaves of flue-cured tobacco, the method comprising: obtaining the dates of "topping" and "maturity of the middle tobacco leaves" of the flue-cured tobacco to be predicted, calculating the number of days for "topping-maturity of the middle tobacco leaves"; inputting the number of days for "topping-maturity of the middle tobacco leaves" into a preset prediction model, outputting the number of days for "topping-maturity of the middle tobacco leaves" of the flue-cured tobacco to be predicted, and predicting the date when the middle tobacco leaves of the flue-cured tobacco to be predicted reach an overripe state according to the number of days for "topping-maturity of the middle tobacco leaves", wherein the prediction model is constructed based on the regularity of the number of days for "topping-maturity of the middle tobacco leaves" and "topping-maturity of the middle tobacco leaves" of the flue-cured tobacco in terms of time. The present invention can accurately predict when the overripe period of the middle tobacco leaves of the flue-cured tobacco will arrive, which has practical guiding significance for clarifying the optimal harvesting period of tobacco leaves and ensuring the quality of tobacco leaves.

Description

Technical Field

[0001] The invention relates to the technical field of tobacco leaf overripe period prediction, and in particular to a method and system for predicting the overripe period of middle tobacco leaves of flue-cured tobacco. Background Art

[0002] The over-mature stage of tobacco leaves refers to the critical period when, after the tobacco leaves have grown and developed in the field and have undergone technological maturity, their appearance and internal quality begin to significantly decline and decay, and they are no longer suitable for harvesting and processing.

[0003] Tobacco leaves need to be harvested after they mature and before they are overripe, otherwise the quality will be significantly reduced. Predicting the overripe period of tobacco leaves in advance has guiding significance for production practice. It is important decision-making information for planning and managing various production resources (such as harvesting personnel, transportation capacity, storage space, supporting production materials and baking and processing capacity of curing rooms) in tobacco leaf harvesting, which helps to avoid quality losses caused by harvesting overripe tobacco leaves.

[0004] At present, the method for determining the over-ripe period of tobacco leaves is to first determine whether the tobacco leaves are "over-ripe" based on the appearance characteristics such as the degree of yellowing on the surface of the tobacco leaves and changes in leaf shape. This method relies on manual on-site qualitative judgment to obtain results. It is a qualitative, record and description of events that have occurred. It can be used to summarize past events, but it cannot be used to predict when the "over-ripe period of tobacco leaves" will arrive. Therefore, there is an urgent need for a method and system for predicting the over-ripe period of tobacco leaves in the middle of flue-cured tobacco. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting the over-ripening period of the middle tobacco leaves of flue-cured tobacco, which can accurately predict when the over-ripening period of the middle tobacco leaves of flue-cured tobacco will arrive, ensure the quality of tobacco leaves harvested, and has guiding significance for production practice.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for predicting the over-ripening period of middle tobacco leaves of flue-cured tobacco, comprising:

[0008] Obtain the dates of "topping" and "maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and calculate the number of days from "topping to maturity of middle tobacco leaves";

[0009] The number of days from "topping to maturity of middle tobacco leaves" is input into a preset prediction model, the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted is output, and the date on which the middle tobacco leaves of the flue-cured tobacco to be predicted reach an over-mature state is predicted based on the number of days from "topping to maturity of middle tobacco leaves" and "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco. The prediction model is constructed based on the regularity of the time quantity of the number of days from "topping to maturity of middle tobacco leaves" and the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco.

[0010] Optionally, the process of constructing the prediction model based on the time regularity of the number of days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-maturity" of flue-cured tobacco includes:

[0011] Set different levels of cultivation influencing factors to cultivate flue-cured tobacco sample groups with different growth and development progress;

[0012] Record the "topping" date of the flue-cured tobacco sample population, as well as the date when the flue-cured tobacco sample population "reaches maturity" and the date when the flue-cured tobacco sample population "reaches over-maturity", and obtain the number of days from "topping to maturity of the middle tobacco leaves" and "topping to over-maturity of the middle tobacco leaves" of the flue-cured tobacco sample population;

[0013] The prediction model is constructed based on the regression relationship between the number of days from "topping to maturity of the middle tobacco leaves" and the number of days from "topping to over-maturity of the middle tobacco leaves" of the flue-cured tobacco sample population.

[0014] Optionally, the cultivation influencing factors include fertilization, number of leaves left and planting density.

[0015] Optionally, constructing the prediction model based on the regression relationship between the days from “topping to middle tobacco leaves maturity” and the days from “topping to middle tobacco leaves overripe” of the flue-cured tobacco sample population includes:

[0016] Constructing an index based on the number of days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-mature" of the flue-cured tobacco sample population;

[0017] The regression relationship between the two indicators is calculated, and the regression relationship formula involving both the "topping-maturity of middle tobacco leaves" and "topping-overripeness of middle tobacco leaves" days and having the largest fit is screened out, i.e., the prediction model.

[0018] Optionally, the indicators include: the number of days from "topping to the maturity of the middle tobacco leaves" and the number of days from "topping to the over-maturity of the middle tobacco leaves", as well as derived indicators based on the number of days from "topping to the maturity of the middle tobacco leaves" and the number of days from "topping to the over-maturity of the middle tobacco leaves".

[0019] Optionally, the derived indicators include: "Topping--Middle Tobacco Leaves Over-Mature" Days - "Topping--Middle Tobacco Leaves Mature" Days, "Topping--Middle Tobacco Leaves Mature" Days + "Topping--Middle Tobacco Leaves Over-Mature", "Topping--Middle Tobacco Leaves Over-Mature" Days / "Topping--Middle Tobacco Leaves Mature", "Topping--Middle Tobacco Leaves Mature" Days × "Topping--Middle Tobacco Leaves Over-Mature", "Topping--Middle Tobacco Leaves Mature" Days × "Topping--Middle Tobacco Leaves Mature", "Topping--Middle Tobacco Leaves Over-Mature" Days × "Topping--Middle Tobacco Leaves Mature", "Topping--Middle Tobacco Leaves Over-Mature" Days × "Topping--Middle Tobacco Leaves Over-Mature".

[0020] Optionally, the prediction model is:

[0021] d2=(d1-7.9236) / 0.6783

[0022] Among them, d2 is the number of days from "topping to over-ripening of tobacco leaves in the middle", and d1 is the number of days from "topping to ripening of tobacco leaves in the middle".

[0023] To further achieve the above-mentioned object, the present invention also provides a prediction system for the over-maturity period of the middle tobacco leaves of flue-cured tobacco, comprising: a collection module, a prediction module;

[0024] The acquisition module is used to obtain the dates of "topping" and "maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and calculate the number of days from "topping to maturity of middle tobacco leaves";

[0025] The prediction module is used to input the number of days from "topping to maturity of middle tobacco leaves" into a preset prediction model, output the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and predict the date when the middle tobacco leaves of the flue-cured tobacco to be predicted will reach an over-mature state based on the number of days from "topping to over-maturity of middle tobacco leaves"; wherein the prediction model is constructed based on the regularity of the number of days from "topping to maturity of middle tobacco leaves" and "topping to over-maturity of middle tobacco leaves" of flue-cured tobacco in terms of time.

[0026] The beneficial effects of the present invention are:

[0027] The present invention uses the number of days from "topping to middle tobacco leaves maturing" and the number of days from "topping to middle tobacco leaves being overripe" as basic variable indicators, and based on this, constructs a series of derived indicators with different calculation relationships, and further explores the time law of the number of days from "topping to middle tobacco leaves maturing" and the number of days from "topping to middle tobacco leaves being overripe", establishes a regression relationship expression, constructs a prediction model, and verifies through error calculation that the prediction model of the present invention is reasonable and applicable, has excellent effect, can accurately predict when the overripe period of tobacco leaves will arrive, ensures the quality of tobacco leaf harvesting, has guiding significance for production practice, can provide important decision-making for the planning and operation of various production resources in tobacco leaf harvesting, and avoids quality loss caused by harvesting overripe tobacco leaves. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0029] Figure 1 A flow chart of a method for predicting the over-ripe period of middle tobacco leaves in a flue-cured tobacco according to an embodiment of the present invention;

[0030] Figure 2 It is a schematic diagram of the days for "topping-maturity of the middle tobacco leaves" and "topping-overripeness of the middle tobacco leaves" of the flue-cured tobacco in an embodiment of the present invention, wherein d1 is the days for "topping-maturity of the middle tobacco leaves", and d2 is the days for "topping-overripeness of the middle tobacco leaves";

[0031] Figure 3 A regression analysis diagram of the index relationship formula with the largest degree of fit selected in an embodiment of the present invention;

[0032] Figure 4 This is a comparative analysis chart of the predicted value and the measured value of the number of days for "topping - over-ripening of the middle tobacco leaves" in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0035] "Maturity" and "over-maturity" are two different physiological states of tobacco leaves in their growth and development under specific environmental conditions. They are the process of orderly expression of tobacco leaf genes and gradual development of physiological and biochemical processes under the joint action of environmental conditions and tobacco leaf gene expression regulatory mechanisms. They are the embodiment of the objective laws of biological growth and development in tobacco leaves. The two are adjacent and connected in the life process of tobacco leaves, and there is a causal relationship and orderly law in time. "Accumulated temperature" in the environment refers to the sum of the daily average temperature accumulated over a period of time. It is an important indicator for studying the relationship between temperature and the development speed of biological organisms. It can express the effect of temperature on the growth and development of biological organisms from the two aspects of intensity and action time. Obviously, the "accumulated temperature" in the process of tobacco leaf maturation and aging is proportional to the "number of days of growth". Therefore, the number of days of tobacco leaf field growth can be used as an independent variable affecting tobacco leaf aging, and a model of it and aging can be established.

[0036] This embodiment examines the number of days from the "topping" of the tobacco plant to the time when the fresh tobacco leaves in the middle reach "maturity", and the number of days from the "topping" to the time when the fresh tobacco leaves in the middle reach "aging"; using this as the basic variable indicator, a series of derivative indicators with different calculation relationships are constructed to explore the regularity of the two in terms of time quantity, and to establish a regression relationship expression; and then based on the regression relationship expression, the over-maturity period of the tobacco leaves is predicted according to the maturity period of the tobacco leaves.

[0037] This embodiment provides a method for predicting the over-ripe period of the middle tobacco leaves of flue-cured tobacco. Figure 1 As shown, including:

[0038] Obtain the dates of "topping" and "maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and calculate the number of days from "topping to maturity of middle tobacco leaves";

[0039] The number of days from "topping to maturity of middle tobacco leaves" is input into a preset prediction model, and the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted is output, and the date on which the middle tobacco leaves of the flue-cured tobacco to be predicted reach an over-maturity state is predicted based on the number of days from "topping to maturity of middle tobacco leaves" and "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco. The prediction model is constructed based on the regularity of the time quantity of the number of days from "topping to maturity of middle tobacco leaves" and the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco.

[0040] "Topping" refers to cutting off the entire inflorescence when the top buds of the tobacco plant are fully open to terminate its reproductive growth.

[0041] "Mature middle tobacco leaves" means that the leaves in the middle of the tobacco plant have reached the standard of maturity for harvesting. Its appearance characteristics are that 6-7% of the tobacco leaf surface area is yellow-green to light yellow, and 2 / 3 of the main veins turn white and shiny.

[0042] "Topping - Middle tobacco leaves ripening" refers to the time from "topping" to "maturity of middle tobacco leaves" of the tobacco plant.

[0043] The specific process of building a prediction model is as follows:

[0044] Step 1. Cultivating flue-cured tobacco sample groups at different over-maturity stages;

[0045] Fertilization, number of leaves left, and tobacco planting density are important factors affecting the maturity and over-maturity of tobacco leaves. In order to obtain tobacco leaf samples with different over-maturity periods, three important cultivation measures, namely, fertilization amount, number of leaves left, and planting density, were selected as influencing factors in this study. The setting levels of each factor are shown in Table 1.

[0046] Table 1

[0047]

[0048] The Box-Behnken experimental design method was used to develop a three-factor, three-level response surface experimental design, with a total of 16 treatments, as shown in Table 2.

[0049] Table 2

[0050]

[0051]

[0052] The experimental field is located in Dazhai Township, Gulin County, Luzhou City, Sichuan Province. The soil is mainly yellow soil and purple soil, with heavy texture. Soil physical and chemical properties: pH is 6.49, organic matter is 3.11g / kg, alkaline nitrogen is 140.93mg / kg, available phosphorus is 40.06mg / kg, and available potassium is 121mg / kg. The flue-cured tobacco variety for the test is Zhongchuan 208. Tobacco seedlings are transplanted in time, and 60 tobacco plants are planted in each treatment area. Other field management measures outside the treatment factors are carried out according to the high-quality flue-cured tobacco cultivation management measures plan.

[0053] Step 2. Record the inspection of relevant indicators of tobacco leaves during over-ripening period;

[0054] When the tobacco plants in each treatment entered the budding and topping stage, the topping work was carried out to remove the top inflorescence of the tobacco plants. Twenty tobacco plants with normal growth were randomly selected from each treatment plot, and their topping dates were recorded. Then, the appearance characteristics of their middle tobacco leaves (9-11 leaves) were inspected every day to determine and record the dates when they reached "mature" and "overmature". Figure 2 As shown, d1 is the number of days from "topping to the maturity of the middle tobacco leaves"; d2 is the number of days from "topping to the over-maturity of the middle tobacco leaves".

[0055] The data of 20 materials recorded in each treatment were averaged and used, and the results are shown in Table 3. The two index values ​​d1 and d2 were obtained through actual field investigations, and "d2-d1", "d1+d2", "d2 / d1", "d1×d2", "d1×d1" and "d2×d2" were all derived indices generated by calculation.

[0056] Table 3

[0057]

[0058]

[0059] Step 3. The expression of the number of days d2 for "topping--the middle tobacco leaves are over-ripe", i.e., the establishment of the prediction model;

[0060] In order to explore the relationship between the number of days d1 from "topping to middle tobacco leaves mature" and the number of days d2 from "topping to middle tobacco leaves overripe", the regression relationship between these indicators was calculated, in order to screen out the relationship equation with the highest degree of fit involving both indicators d1 and d2. The expressions reflecting the regression relationship between d1 and d2 established based on the indicators in Table 3 are shown in Table 4. The degree of fit R of each regression equation in the table is 2 The range of values ​​is [0.5573-0.9966], and most of the R 2 The value is above 0.8, which indicates that there is an obvious and regular correlation between the two indexes d1 and d2 in the process of tobacco leaf aging, showing a high correlation; 2The maximum value is y = 1.6783x + 7.9236, R 2 =0.9966, where the x variable is d2 and the y variable is d1+d2. The regression analysis is as follows Figure 3 shown.

[0061] It shows that among the indicators involved, this relationship can most accurately reflect the relationship between d1 and d2.

[0062] Substituting the independent variable x for "d2" and the dependent variable y for "d1+d2", we get the following expression:

[0063] d1+d2=1.6783×d2+7.9236

[0064] d1-7.9236=0.6783×d2

[0065] The final formula, i.e. the prediction model is: d2 = (d1-7.9236) / 0.6783.

[0066] Thus, we get a relationship with d1 as the independent variable and d2 as the dependent variable. After knowing the number of days d1 from "topping to maturity of the middle tobacco leaves" through field investigation, we can use this relationship to get the number of days d2 from "topping to over-maturity of the middle tobacco leaves", and further predict the specific date when the tobacco leaves will reach the over-maturity state in the future.

[0067] Table 4

[0068]

[0069] To further optimize the technical solution, this embodiment also provides a prediction system for the over-ripe period of the middle tobacco leaves of flue-cured tobacco, including: a collection module, a prediction module;

[0070] The collection module is used to obtain the days from "topping to middle tobacco leaf maturity" of the flue-cured tobacco to be predicted;

[0071] The prediction module is used to input the number of days from "topping to maturity of middle tobacco leaves" into a preset prediction model, output the number of days from "topping to over-maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and predict the date when the middle tobacco leaves of the flue-cured tobacco to be predicted will reach the over-maturity state based on the number of days from "topping to over-maturity of middle tobacco leaves"; wherein the prediction model is constructed based on the regularity of the number of days from "topping to maturity of middle tobacco leaves" and "topping to over-maturity of middle tobacco leaves" in terms of time.

[0072] In order to verify the application effect of this embodiment, the measured value d1 in Table 5 is substituted into the prediction model to obtain the predicted value d2', and the relative error between d2' and d2 is calculated. The results are shown in Table 5. The comparative analysis of d2' and d2 is shown in Figure 4 shown.

[0073] Table 5

[0074]

[0075]

[0076] The relative errors between all predicted values ​​d2' and d2 are between -1.96% and 5%, and most of them are within ±2%. The root mean square error (RMSE) is used to measure the error size of the prediction results. Where yi is the actual value, is the predicted value, and n is the number of samples. When the root mean square error is less than 2, it indicates that the model is reasonably usable. The RMSE of the prediction model in this embodiment is 0.9354, which is less than 2, indicating that the obtained model has excellent prediction effect and excellent usability.

[0077] The embodiments described above are only descriptions of the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design concept and spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for predicting the over-ripe stage of flue-cured tobacco leaves in the middle part, characterized in that: include: Get the dates of "topping" and "maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and calculate the number of days from "topping to maturity of middle tobacco leaves"; The number of days from "topping to middle tobacco leaves maturity" is input into a preset prediction model, the number of days from "topping to middle tobacco leaves over-mature" of the flue-cured tobacco to be predicted is output, and the date when the middle tobacco leaves of the flue-cured tobacco to be predicted reach an over-mature state is predicted based on the number of days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-mature" is predicted, wherein the prediction model is constructed based on the regularity of the number of days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-mature" in terms of time quantity of the flue-cured tobacco, and the prediction model is: d2=(d1-7.9236) / 0.6783 Among them, d2 is the number of days from "topping to over-ripening of tobacco leaves in the middle", and d1 is the number of days from "topping to ripening of tobacco leaves in the middle".

2. The method for predicting the over-ripe stage of the middle tobacco leaves of flue-cured tobacco according to claim 1, characterized in that: The process of constructing the prediction model based on the time law of the number of days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-mature" in flue-cured tobacco includes: Set different levels of cultivation influencing factors to cultivate flue-cured tobacco sample groups with different growth and development progress; Record the "topping" date of the flue-cured tobacco sample population, as well as the date of "reaching maturity" and the date of "reaching over-maturity" of the flue-cured tobacco sample population, and obtain the number of days from "topping-maturity of middle tobacco leaves" and "topping-over-maturity of middle tobacco leaves" of the flue-cured tobacco sample population; The prediction model is constructed based on the regression relationship between the number of days from "topping to middle tobacco leaves maturity" and the number of days from "topping to middle tobacco leaves overripe" of the flue-cured tobacco sample population.

3. The method for predicting the over-ripe stage of the middle tobacco leaves of flue-cured tobacco according to claim 2, characterized in that: The cultivation influencing factors include fertilization, number of leaves left and planting density.

4. The method for predicting the over-ripe stage of the middle tobacco leaves of flue-cured tobacco according to claim 2, characterized in that: The prediction model is constructed based on the regression relationship between the days from "topping to middle tobacco leaves maturity" and "topping to middle tobacco leaves over-mature" of the flue-cured tobacco sample population, including: Constructing an index based on the number of days from "top to middle tobacco leaves mature" and "top to middle tobacco leaves overripe" of the flue-cured tobacco sample population; The regression relationship between the two indicators is calculated, and the regression relationship formula involving both the "topping-middle tobacco leaves maturity" days and the "topping-middle tobacco leaves over-mature" days with the largest fit is screened out, that is, the prediction model.

5. The method for predicting the over-ripe stage of the middle tobacco leaves of flue-cured tobacco according to claim 4, characterized in that: The indicators include: the number of days from "topping to the maturity of the middle tobacco leaves" and the number of days from "topping to the over-maturity of the middle tobacco leaves", as well as derived indicators based on the number of days from "topping to the maturity of the middle tobacco leaves" and the number of days from "topping to the over-maturity of the middle tobacco leaves".

6. The method for predicting the over-ripe stage of the middle tobacco leaves according to claim 5, characterized in that: The derived indicators include: "topping - middle tobacco leaves are over-ripe" days - "topping - middle tobacco leaves are mature" days, "topping - middle tobacco leaves are mature" days + "topping - middle tobacco leaves are over-ripe" days, "topping - middle tobacco leaves are over-ripe" days / "topping - middle tobacco leaves are mature" days, "topping - middle tobacco leaves are mature" days × "topping - middle tobacco leaves are over-ripe" days, "topping - middle tobacco leaves are mature" days × "topping - middle tobacco leaves are mature" days, "topping - middle tobacco leaves are over-ripe" days × "topping - middle tobacco leaves are over-ripe".

7. A prediction system for the over-ripe period of middle tobacco leaves, characterized in that: The method for predicting the over-ripe period of the middle tobacco leaves of the flue-cured tobacco according to any one of claims 1 to 6 comprises: a collection module and a prediction module; The acquisition module is used to obtain the dates of "topping" and "maturity of middle tobacco leaves" of the flue-cured tobacco to be predicted, and calculate the number of days from "topping to maturity of middle tobacco leaves"; The prediction module is used to input the "topping-middle tobacco leaves mature" days into a preset prediction model, output the "topping-middle tobacco leaves overripe" days of the flue-cured tobacco to be predicted, and predict the date when the middle tobacco leaves of the flue-cured tobacco to be predicted reach an overripe state based on the "topping-middle tobacco leaves overripe" days; The prediction model is constructed based on the time regularity of the number of days from "topping to the maturity of the middle tobacco leaves" and "topping to the over-maturity of the middle tobacco leaves" of flue-cured tobacco.

Images