Cigar tobacco modulation stage detection method and detection device

Abstract

The invention relates to a cigar tobacco modulation stage detection method and a cigar tobacco modulation stage detection device.The cigar tobacco modulation stage detection method comprises the steps that absorbance detection is conducted on a cigar tobacco sample to be detected, and absorption spectrum data of the cigar tobacco sample to be detected are obtained; inputting the absorption spectrum data of the to-be-detected cigar tobacco leaf sample into a trained modulation stage monitoring model to obtain a modulation stage of the to-be-detected cigar tobacco leaf sample; according to the modulation stage of the to-be-detected cigar tobacco leaf sample, modulation parameters of the to-be-detected cigar tobacco leaf are adjusted, and the accuracy of judgment of the modulation stage of the cigar tobacco leaf is improved.

Description

Technical Field

[0001] This application relates to the technical field of tobacco processing, and in particular to a method and device for detecting the modulation stage of cigar tobacco leaves. Background Art

[0002] The quality of cigar tobacco leaves depends on their complex modulation process, including the sun-curing and fermentation stages, which are mainly regulated by controlling environmental factors such as temperature, humidity, and light. During this process, the tobacco leaves undergo a transformation from fresh to completely dry, accompanied by significant changes in chemical and physical properties, which directly affect the flavor, aroma, and burning characteristics of the final product. However, these methods are difficult to take into account the diverse changes of tobacco leaves at different stages, and it is difficult to comprehensively evaluate the various qualities of tobacco leaves in a short time. Currently, most methods still rely on manual experience judgment or traditional chemical analysis to determine the modulation stage of cigar tobacco leaves, and then optimize the production process. However, according to experience judgment, due to different experiences of different staff members, the judgment of the modulation stage is not the same, and there are often inaccurate judgments.

[0003] Regarding the problem of inaccurate judgment of the modulation stage of cigar tobacco leaves in the related art, no effective solution has been proposed yet. Summary of the Invention

[0004] In this embodiment, a method and device for detecting the modulation stage of cigar tobacco leaves are provided to solve the problem of inaccurate judgment of the modulation stage of cigar tobacco leaves in the related art.

[0005] In the first aspect, in this embodiment, a method for detecting the modulation stage of cigar tobacco leaves is provided, including:

[0006] Performing absorbance detection on the cigar tobacco leaf sample to be detected to obtain the absorption spectrum data of the cigar tobacco leaf sample to be detected;

[0007] Inputting the absorption spectrum data of the cigar tobacco leaf sample to be detected into the trained modulation stage monitoring model to obtain the modulation stage where the cigar tobacco leaf sample to be detected is located;

[0008] Adjusting the modulation parameters of the cigar tobacco leaf to be detected according to the modulation stage where the cigar tobacco leaf sample to be detected is located.

[0009] In some of these embodiments, the training process of the modulation stage monitoring model includes:

[0010] Taking the absorption spectrum data of cigar tobacco leaves in different modulation stages as the absorption spectrum data set;

[0011] Dividing the absorption spectrum data set into an absorption spectrum data training set and an absorption spectrum data test set;

[0012] Input the absorption spectrum data training set into multiple initial modulation stage monitoring models for training to obtain each trained initial modulation stage monitoring model;

[0013] Based on the absorption spectrum data test set, select the target modulation stage monitoring model from each of the trained initial modulation stage monitoring models through the cross-validation method as the trained modulation stage monitoring model.

[0014] In some embodiments, using the absorption spectrum data of cigar tobacco leaves at different modulation stages as the absorption spectrum data set includes:

[0015] When the cigar tobacco leaves are in the withering stage, obtain the absorption spectrum data of the cigar tobacco leaves every 2 days;

[0016] When the cigar tobacco leaves are in the yellowing stage, obtain the absorption spectrum data of the cigar tobacco leaves every 1 day;

[0017] When the cigar tobacco leaves are in the browning stage, obtain the absorption spectrum data of the cigar tobacco leaves every 3 days;

[0018] When the cigar tobacco leaves are in the stem-drying stage, obtain the absorption spectrum data of the cigar tobacco leaves every 4 days.

[0019] In some embodiments, dividing the absorption spectrum data set into an absorption spectrum data training set and an absorption spectrum data test set includes:

[0020] Perform smoothing processing on the absorption spectrum data set to eliminate the noise in the absorption spectrum data set and obtain a denoised absorption spectrum data set;

[0021] Perform normalization processing on the denoised absorption spectrum data set to obtain a standardized absorption spectrum data set;

[0022] Perform baseline correction on the standardized absorption spectrum data set by using the polynomial fitting method to obtain a target absorption spectrum data set;

[0023] Divide the target absorption spectrum data set into the absorption spectrum data training set and the absorption spectrum data test set.

[0024] In some embodiments, the absorption spectrum data of the cigar tobacco leaf sample to be detected includes blue light absorbance, red light absorbance, and near-infrared light absorbance.

[0025] In some embodiments, inputting the absorption spectrum data of the cigar tobacco leaf sample to be detected into the trained modulation stage monitoring model to obtain the modulation stage where the cigar tobacco leaf sample to be detected is located includes:

[0026] By using the trained modulation stage monitoring model, the blue light absorbance, red light absorbance, and near-infrared light absorbance of the cigar tobacco leaf sample to be detected are detected, and in combination with the water content of the cigar tobacco leaf to be detected obtained from the detection, the modulation stage of the cigar tobacco leaf sample to be detected is obtained.

[0027] In some of these embodiments, the detection criteria of the trained modulation stage monitoring model include:

[0028] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.9, or the red light absorbance is greater than 0.75, and the water content of the cigar tobacco leaf sample to be detected is greater than 70%, it is determined that the cigar tobacco leaf sample to be detected is in the wilting stage;

[0029] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.65 and less than or equal to 0.9, or the red light absorbance is greater than 0.6 and less than or equal to 0.8, or the near-infrared light absorbance is greater than 0.3, and the water content of the cigar tobacco leaf sample to be detected is greater than or equal to 65% and less than 70%, it is determined that the cigar tobacco leaf sample to be detected is in the yellowing stage;

[0030] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.6 and less than or equal to 0.65, or the red light absorbance is greater than 0.4 and less than or equal to 0.6, or the near-infrared light absorbance is greater than 0.2 and less than or equal to 0.3, and the surface color of the cigar tobacco leaf sample to be detected changes from yellow to brown, it is determined that the cigar tobacco leaf sample to be detected is in the browning stage;

[0031] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.4 and less than or equal to 0.6, or when the red light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.3 and less than or equal to 0.4, or the near-infrared light absorbance is greater than 0.1 and less than or equal to 0.2, and the water content of the cigar tobacco leaf sample to be detected is greater than or equal to 30% and less than 40%; it is determined that the cigar tobacco leaf sample to be detected is in the dry rib stage.

[0032] In some of these embodiments, the wavelength detection range of the absorption spectrum of the cigar tobacco leaf sample to be detected is 200 nanometers - 2500 nanometers, the wavelength detection range of the blue light absorbance is 400 nanometers - 500 nanometers, the wavelength detection range of the red light absorbance is 600 nanometers - 700 nanometers, and the wavelength detection range of the near-infrared light absorbance is 900 nanometers - 1500 nanometers.

[0033] In some of these embodiments, adjusting the modulation parameters of the cigar tobacco leaf to be detected according to the modulation stage of the cigar tobacco leaf sample to be detected includes:

[0034] When it is detected that the cigar tobacco leaves to be detected are in the yellowing stage, increase the light intensity by a preset amplitude value, control the ambient temperature at 18°C - 22°C, and control the ambient humidity at 70% - 75%;

[0035] When it is detected that the cigar tobacco leaves to be detected are in the browning stage, increase the light intensity by the preset amplitude value, control the ambient temperature at 22°C - 25°C, and control the ambient humidity at 60% - 65%;

[0036] When it is detected that the cigar tobacco leaves to be detected are in the stem - drying stage, reduce the light intensity to a preset intensity range, control the ambient temperature at 26°C - 30°C, and control the ambient humidity at 50% - 55%.

[0037] In a second aspect, a detection device for the modulation stage of cigar tobacco leaves is provided in this embodiment, including: a spectral data detection module, a modulation stage detection module, and an adjustment module. Among them,

[0038] The spectral data detection module is used to perform absorbance detection on a cigar tobacco leaf sample to be detected, and obtain the absorption spectral data of the cigar tobacco leaf sample to be detected;

[0039] The modulation stage detection module is used to input the absorption spectral data of the cigar tobacco leaf sample to be detected into a trained modulation stage monitoring model, and obtain the modulation stage where the cigar tobacco leaf sample to be detected is located;

[0040] The adjustment module is used to adjust the modulation parameters of the cigar tobacco leaves to be detected according to the modulation stage of the cigar tobacco leaf sample to be detected.

[0041] Compared with the related technology, the detection method for the modulation stage of cigar tobacco leaves provided in this embodiment obtains the absorption spectral data of the cigar tobacco leaf sample to be detected by performing absorbance detection on the cigar tobacco leaf sample to be detected; inputs the absorption spectral data of the cigar tobacco leaf sample to be detected into a trained modulation stage monitoring model, and obtains the modulation stage where the cigar tobacco leaf sample to be detected is located; adjusts the modulation parameters of the cigar tobacco leaves to be detected according to the modulation stage where the cigar tobacco leaf sample to be detected is located, thereby improving the accuracy of judging the modulation stage of cigar tobacco leaves.

[0042] Details of one or more embodiments of the present application are set forth in the following drawings and description, so that other features, objects, and advantages of the present application will become more clearly understood. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0044] Figure 1 is a hardware structure block diagram of the terminal of the cigar tobacco leaf curing stage detection method of this embodiment.

[0045] Figure 2 is a flowchart of the cigar tobacco leaf curing stage detection method of this embodiment.

[0046] Figure 3 is a physical diagram of the cigar tobacco leaf at each curing stage of the cigar tobacco leaf curing stage monitoring method of this embodiment.

[0047] Figure 4 is an absorption spectrum curve graph of each curing stage of the cigar tobacco leaf curing stage monitoring method of this embodiment.

[0048] Figure 5 is a structure block diagram of the cigar tobacco leaf curing stage detection device of this embodiment. Detailed implementation manners

[0049] To more clearly understand the purpose, technical solution, and advantages of the present application, the present application will be described and explained below with reference to the accompanying drawings and embodiments.

[0050] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meanings as understood by those of ordinary skill in the technical field to which this application pertains. In this application, words such as "a", "an", "one kind", "the", "these", etc. do not indicate a limitation in quantity and can be singular or plural. The terms "comprising", "including", "having" and any variations thereof used in this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products or devices. The terms "connected", "linked", "coupled", etc. used in this application do not limit to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" used in this application means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the objects associated before and after are in an "or" relationship. The terms "first", "second", "third", etc. used in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0051] The method embodiments provided in this embodiment may be executed on a terminal, a computer, or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of the terminal of the cigar leaf curing stage detection method in this embodiment. As Figure 1 shown, the terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 and a memory 104 for storing data. Among them, the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown in the figure is only schematic and does not limit the structure of the above terminal. For example, the terminal may also include more or fewer components than those shown in Figure 1 the figure, or may have a different configuration from that shown in Figure 1 the figure.

[0052] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the detection method of the cigar leaf curing stage in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof.

[0053] The transmission device 106 is used to receive or send data via a network. The above-mentioned network includes a wireless network provided by a communication provider of the terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0054] In this embodiment, a method for detecting the cigar leaf curing stage is provided. Figure 2 is a flowchart of the method for detecting the cigar leaf curing stage in this embodiment, as Figure 2 shown, this process includes the following steps:

[0055] Step S201, perform absorbance detection on the cigar leaf sample to be detected, and obtain the absorption spectrum data of the cigar leaf sample to be detected.

[0056] Specifically, the chemical components (such as moisture, pigments, sugars, etc.) of cigar leaves in different curing stages will change. The traditional judgment of the curing stage relies on manual experience, which has subjectivity and errors. Since the chemical components of cigar leaves in different curing stages change, their light absorption characteristics will also change. Therefore, in this embodiment, the curing stage of cigar leaves is detected by analyzing the light absorption characteristics of cigar leaves, so as to achieve a more accurate judgment of the curing stage. Figure 3 is a physical diagram of cigar leaves in each curing stage of the method for monitoring the cigar leaf curing stage in this embodiment, as Figure 3As shown, S1 is a physical picture of cigar tobacco leaves before picking. The curing stage of cigar tobacco leaves includes a withering period S2, a yellowing period S3, a browning period S4, and a stem-drying period S5. First, select representative tobacco leaf samples from the cigar tobacco leaf production line or storage repository as the cigar tobacco leaf samples to be detected, ensuring that the samples can reflect the quality and characteristics of the overall tobacco leaves. Pretreat the tobacco leaf samples, such as cutting them into uniform small pieces or powders, to ensure the uniformity and accuracy of absorbance detection. Use high-precision spectral analysis equipment, such as a near-infrared spectrometer (NIR), an ultraviolet-visible spectrophotometer (UV-Vis), or a Fourier transform infrared spectrometer (FTIR), to detect the absorbance of the cigar tobacco leaf samples. According to the characteristics of the cigar tobacco leaves, set an appropriate spectral range (such as the blue light range is 400 nanometers - 500 nanometers), and adjust parameters such as light source intensity, number of scans, and resolution to ensure the accuracy and repeatability of data points. Scan the samples through the spectral equipment and record the absorbance values of the samples at different wavelengths, that is, the absorption spectral data.

[0057] Step S202: Input the absorption spectral data of the cigar tobacco leaf samples to be detected into the trained monitoring model for the curing stage to obtain the curing stage where the cigar tobacco leaf samples to be detected are located.

[0058] Specifically, by collecting the absorption spectral data of a large number of cigar tobacco leaf samples at different curing stages (such as the yellowing period, the browning period, the stem-drying period, etc.) as the training data for the monitoring model of the curing stage, accurately label the curing stage for each sample. Use chemometric methods (such as principal component analysis PCA, partial least squares PLS) or machine learning algorithms (such as random forest, support vector machine) to extract the key features in the absorption spectral data, select the characteristic wavelengths with strong correlation with the curing stage, reduce the data dimension, and thus improve the model efficiency. Adopt machine learning or deep learning algorithms (such as convolutional neural network CNN, long short-term memory network LSTM) as the initial model of the monitoring model for the curing stage. First, preprocess the absorption spectral data to eliminate equipment errors and background interference. Input the processed spectral data into the monitoring model for the curing stage. The model calculates the probability or score of the sample belonging to each curing stage according to the input spectral data, and optimizes the model parameters through methods such as cross-validation to obtain the trained monitoring model for the curing stage. Input the absorption spectral data of the cigar tobacco leaf samples to be detected into the trained monitoring model for the curing stage, and output the curing stage (such as the yellowing period) where the cigar tobacco leaf samples to be detected are located. Detecting the curing stage of the cigar tobacco leaf samples to be detected through the monitoring model for the curing stage trained with the absorption spectral data of cigar tobacco leaves passing through different curing stages improves the accuracy and efficiency of detection.

[0059] Step S203: Adjust the curing parameters of the cigar tobacco leaf samples to be detected according to the curing stage where the cigar tobacco leaf samples to be detected are located.

[0060] Specifically, according to the detected curing stage of the cigar tobacco leaf sample, the curing parameters of the cigar tobacco leaves on the production line where the cigar tobacco leaf to be detected is located are adjusted, and the relevant curing parameters are adjusted according to the requirements of different stages. For example, the temperature is regulated. If it is detected that the curing stage of the cigar tobacco leaf is in the yellowing stage, since a higher temperature is required in the yellowing stage to promote chlorophyll degradation, therefore, the temperature is increased; if it is detected that the curing stage of the cigar tobacco leaf is in the dry leaf stem stage, and a lower temperature is required in the dry leaf stem stage to avoid excessive drying of the tobacco leaves, therefore, the temperature is decreased. Similarly, the curing parameters also include temperature, light, ventilation, etc. A higher humidity is required in the yellowing stage to maintain the physiological activity of the tobacco leaves, while a gradually decreasing humidity is required in the browning stage and the dry leaf stem stage to promote drying. Appropriate light is required in the yellowing stage to promote chlorophyll degradation, while less light is required in the dry leaf stem stage to avoid discoloration of the tobacco leaves. Appropriate ventilation can prevent mildew of the tobacco leaves and promote uniform drying.

[0061] Through the above steps S201 to S203, absorbance detection is performed on the cigar tobacco leaf sample to be detected, and the absorption spectrum data of the cigar tobacco leaf sample to be detected is obtained; the absorption spectrum data of the cigar tobacco leaf sample to be detected is input into the trained curing stage monitoring model, and the curing stage of the cigar tobacco leaf sample to be detected is obtained; according to the curing stage of the cigar tobacco leaf sample to be detected, the curing parameters of the cigar tobacco leaf to be detected are adjusted. Compared with the prior art in which the curing stage of cigar tobacco leaves is detected through manual experience or traditional chemical analysis, in this embodiment, by analyzing the light absorption characteristics of cigar tobacco leaves in different curing stages, the curing stage monitoring model is trained with the absorption spectrum data of cigar tobacco leaves in different curing stages to obtain the trained curing stage monitoring model, and then absorbance detection is performed on the cigar tobacco leaf sample to be detected to obtain the absorption spectrum data of the cigar tobacco leaf sample to be detected. This absorption spectrum data is input into the trained curing stage monitoring model to obtain the curing stage of the cigar tobacco leaf sample to be detected, and the curing parameters are adjusted correspondingly according to the curing stage it is in. By detecting the curing stage through absorption spectrum data, the accuracy of judging the curing stage of cigar tobacco leaves is improved.

[0062] In some of these embodiments, the training process of the curing stage monitoring model includes:

[0063] The absorption spectrum data of cigar tobacco leaves in different curing stages is used as the absorption spectrum data set; the absorption spectrum data set is divided into an absorption spectrum data training set and an absorption spectrum data test set; the absorption spectrum data training set is input into multiple initial curing stage monitoring models for training to obtain the trained initial curing stage monitoring models; based on the absorption spectrum data test set, the target curing stage monitoring model is selected from the trained initial curing stage monitoring models through the cross-validation method as the trained curing stage monitoring model.

[0064] Specifically, a large number of cigar tobacco leaf samples at different curing stages are collected to train the curing stage monitoring model, and the cigar tobacco leaf samples are processed by a sample processing system. The sample processing system includes a freeze dryer, a grinding device, and a screening device. The cigar tobacco leaf samples at different curing stages collected are freeze-dried by the freeze dryer to remove the moisture in the samples and maintain their original chemical composition and structural characteristics. The freeze-dried tobacco leaf samples are ground into powder by the grinding device to improve their reactivity with reagents and ensure sample uniformity. Finally, through the screening device, larger particles are screened out to ensure uniform particle size of the samples and meet the requirements of spectral measurement, and the processed cigar tobacco leaf samples are obtained. The processed cigar tobacco leaf samples are then detected by a spectral measurement system to obtain the absorption spectral data of the cigar tobacco leaf samples at each curing stage, and all the absorption spectral data of the cigar tobacco leaf samples are used as the absorption spectral data set. 70% is selected as the absorption spectral data training set, and 30% is used as the absorption spectral data test set. Machine learning algorithms suitable for processing spectral data, such as support vector machine (SVM), random forest (RF), convolutional neural network (CNN), etc., are selected; different monitoring models are trained using the absorption spectral data training set. The absorption spectral data is used as the feature input, and the curing stage label is used as the expected output. The models are optimized by tuning parameters to obtain multiple cigar tobacco leaf curing stage monitoring models. The monitoring performance of different models is evaluated on the absorption spectral data test set, and the model with the highest cross-validation score is selected as the final monitoring model for curing stage monitoring, that is, the target curing stage monitoring model.

[0065] The following is an example of the operation process of a specific embodiment:

[0066] 1. Freeze-drying treatment: Cigar tobacco leaf samples are collected and preliminarily screened to remove damaged or unqualified leaves. The selected cigar tobacco leaves are placed in a freeze dryer for processing. The freeze-drying conditions are set as: temperature -40°C, vacuum degree 0.2 mbar, and processing time 24 hours until the samples are completely dehydrated. The freeze-dried cigar tobacco leaf samples maintain their original chemical composition and physical structure, which is beneficial to subsequent spectral measurement.

[0067] 2. Grinding and screening: The freeze-dried cigar tobacco leaf samples are ground into powder by a pulverizer. The powder particle size requirement is 80 - 100 mesh to ensure uniformity. The sample screening device is used for screening to remove larger particles and ensure the uniformity of the samples during measurement, so as to avoid spectral data deviation caused by uneven samples.

[0068] 3. Flake Preparation: Take about 1 g of the treated cigar tobacco leaf powder and mix it with 5 mL of polyurethane acrylate, and stir well to obtain a cigar tobacco leaf mixture. Place the cigar tobacco leaf mixture in an ultraviolet irradiation device for curing. The curing time is set to 3 hours to ensure that the cigar tobacco leaf sample forms a transparent or semi-transparent flake. Use a polishing device to polish the cured cigar tobacco leaf sample until the surface of the cigar tobacco leaf sample is smooth and transparent for better spectral measurement.

[0069] 4. Spectrophotometer Installation and Calibration: Place the flake of the cigar tobacco leaf sample in the sample holder of the spectrophotometer, ensure that the flake is closely attached to the holder without any position deviation. Set the wavelength range of the spectrophotometer to 200 nm - 2500 nm to ensure coverage of the ultraviolet, visible, and near-infrared light ranges. Turn on the spectrophotometer and preheat it for at least 30 minutes to ensure the stability of the instrument. Calibrate the instrument with a blank polyurethane acrylate flake to eliminate any baseline deviation.

[0070] 5. Spectral Measurement Process: Select the "scan mode" on the spectrophotometer and measure the absorbance of the cigar tobacco leaf sample according to the required wavelength range (200 nm - 2500 nm). During the measurement, ensure that the cigar tobacco leaf sample is not interfered by external light sources, and use light-shielding curtains in the laboratory to isolate other light sources. Record the absorbance data at each wavelength at least three times and take the average value to obtain the average spectral curve of the cigar tobacco leaf sample to ensure the accuracy and repeatability of the measurement.

[0071] Establish a corresponding relationship between the average spectral curves of all cigar tobacco leaf samples and their modulation stage labels to build a spectral-label mapping library. According to the mapping relationship, divide the spectral curves into spectral data sets corresponding to cigar tobacco leaves at different modulation stages:

[0072] (1) Spectral data set corresponding to fresh cigar tobacco leaves;

[0073] (2) Spectral data set corresponding to cigar tobacco leaves during the yellowing period;

[0074] (3) Spectral data set corresponding to cigar tobacco leaves during the browning period;

[0075] (4) Spectral data set corresponding to cigar tobacco leaves during the dry rib period.

[0076] 6. Data Set Division: Randomly select 70% of the data as the training set and 30% of the data as the test set. Ensure that the distribution of samples at different modulation stages in the training set and the test set is uniform.

[0077] 7. Feature extraction: Extract absorption peaks, wavelength positions, and spectral region integral values (such as absorption values in the 400 - 500 nm blue light region and 600 - 700 nm red light region) from the spectral data. Use principal component analysis (PCA) for dimensionality reduction, retaining 95% of the variance contribution rate to reduce data redundancy.

[0078] 8. Training of each model:

[0079] The trained models include:

[0080] Support Vector Machine (SVM): Suitable for high - dimensional spectral data classification problems;

[0081] Random Forest (RF): Used to evaluate feature importance and perform classification;

[0082] Convolutional Neural Network (CNN): Used to extract complex patterns of spectral curves.

[0083] The hyperparameter ranges for each model are set as follows:

[0084] SVM: Kernel function (linear, RBF), the regularization parameter C ranges from [0.1, 10];

[0085] RF: The number of trees is set to 100 - 500, and the maximum depth ranges from [5, 50];

[0086] CNN: Set 2 - 3 convolutional layers, with the kernel size of each layer being (3, 3), and the pooling layer using (2, 2).

[0087] Use the training set to train each model, taking the spectral data as input features and the modulation stage labels as output. Apply Grid Search and Cross Validation to determine the best parameter combination for each model.

[0088] Calculate the following evaluation metrics on the test set: Accuracy, Precision, Recall, and F1 Score. Compare the cross - validation scores and test set evaluation metrics of different models, and select the model with the best performance as the final modulation stage monitoring model. Table 1 is the evaluation result table of each model on the test set.

[0089] Table 1

[0090] Model Cross-validation score Accuracy Precision Recall F1 score SVM 0.777 0.758 0.726 0.837 0.730 Random Forest 0.833 0.933 0.769 0.779 0.818 CNN 0.771 0.810 0.738 0.784 0.796

[0091] 9. Optimization: Store all measurement results in a database for subsequent analysis and comparison. For different light treatment groups, record the absorbance changes at each stage. During data processing, analyze the effects of each light band on the chemical components of cigar tobacco leaves (such as chlorophyll, sugar, moisture, etc.) to provide a basis for optimizing the cigar tobacco leaf curing process. Based on the absorption spectrum data, the curing stage of cigar tobacco leaves can be optimized, adjust the light conditions at different wavelengths, and improve the flavor and quality of the final cigar tobacco leaves.

[0092] The final target is that the curing stage monitoring model determines the curing stage of cigar tobacco leaves (such as the yellowing stage, browning stage, etc.) in real time through the change characteristics of absorbance in the absorption spectrum data of cigar tobacco leaves, provides production optimization suggestions based on the absorption spectrum data, and precisely adjusts the light conditions.

[0093] In another embodiment, the absorption spectrum data of cigar tobacco leaves at different curing stages are used as an absorption spectrum data set, including: when the cigar tobacco leaves are in the withering stage, obtain the absorption spectrum data of the cigar tobacco leaves every 2 days; when the cigar tobacco leaves are in the yellowing stage, obtain the absorption spectrum data of the cigar tobacco leaves every 1 day; when the cigar tobacco leaves are in the browning stage, obtain the absorption spectrum data of the cigar tobacco leaves every 3 days; when the cigar tobacco leaves are in the stem-drying stage, obtain the absorption spectrum data of the cigar tobacco leaves every 4 days.

[0094] Specifically, the change rates of the chemical components of cigar tobacco leaves at different curing stages are different. In order to improve the accuracy of training the curing stage monitoring model, different sampling periods are set to sample cigar tobacco leaves at different curing stages. In the withering stage, collect the absorption spectrum data of cigar tobacco leaves every 2 days to monitor the gradual loss of leaf moisture and the initial changes in cell structure. The spectral data at this stage can show the gradual weakening of water-related absorption peaks (such as near the 1450 nm and 1940 nm in the near-infrared light region). In the yellowing stage, collect the absorption spectrum data of cigar tobacco leaves every 1 day to monitor the process of chlorophyll degradation and sugar accumulation. The spectral data at this stage can show significant changes in pigment absorption peaks in the visible light region (400 - 700 nm). In the browning stage, collect the absorption spectrum data of cigar tobacco leaves every 3 days to monitor the oxidation of polyphenols and the color change of the tobacco leaves. The spectral data at this stage can show the changes in absorption peaks related to polyphenols (such as specific ultraviolet or near-infrared wavelengths). In the stem-drying stage, collect the absorption spectrum data of cigar tobacco leaves every 4 days to monitor the final drying of the tobacco leaves and the stability of chemical components. The spectral data at this stage can show the further weakening of water absorption peaks and the stability of chemical component absorption peaks. By constructing a data set containing the absorption spectrum data of cigar tobacco leaves at different curing stages, it can provide data support for the monitoring, quality control, and research of the tobacco leaf curing process, and improve the accuracy of judging the curing stage of cigar tobacco leaves.

[0095] In some of these embodiments, the absorption spectrum data set is divided into an absorption spectrum data training set and an absorption spectrum data test set, including:

[0096] Perform smoothing processing on the absorption spectrum data set to eliminate the noise in the absorption spectrum data set, obtaining a denoised absorption spectrum data set; perform normalization processing on the denoised absorption spectrum data set to obtain a standardized absorption spectrum data set; use the polynomial fitting method to perform baseline correction on the standardized absorption spectrum data set to obtain a target absorption spectrum data set; divide the target absorption spectrum data set into an absorption spectrum data training set and an absorption spectrum data test set.

[0097] Specifically, before dividing the absorption spectrum data set of cigar tobacco leaf samples at each modulation stage collected, data preprocessing is performed on the absorption spectrum data set. Among them, the absorption spectrum data of cigar tobacco leaf samples at each modulation stage are presented in the form of spectral curves, and the specific processing process is as follows:

[0098] Use the Savitzky-Golay filtering method to perform smoothing processing on the spectral curve to eliminate noise; perform normalization processing on the smoothed spectral data to normalize it to the 0-1 interval to eliminate the influence of sample size differences on the results; finally, use the polynomial fitting method to remove the background interference of the spectral curve for baseline correction to obtain a target spectral curve. After all spectral curves are processed, a target spectral curve set is obtained, and the target spectral curve set is divided into a training set and a test set for model training use.

[0099] In another embodiment, the absorption spectrum data of the cigar tobacco leaf sample to be detected includes blue light absorbance, red light absorbance, and near-infrared light absorbance.

[0100] Specifically, through the analysis of the absorption spectrum data of cigar tobacco leaves, the blue light absorbance, red light absorbance, and near-infrared light absorbance have obvious changes at each modulation stage. In the yellowing period, chlorophyll is relatively stable, and photosynthesis and pigment degradation are still ongoing. There is still a relatively large amount of chlorophyll in the tobacco leaves, the blue light absorbance is relatively high, and the blue light absorption peak is obvious. In addition, during this stage, chlorophyll decomposes and sugars accumulate, and the red light absorption peak is also relatively obvious, and the red light absorbance is relatively high. In the browning period, chlorophyll gradually degrades, and the reduction of chlorophyll leads to the weakening of the blue light absorption peak and the decrease of the blue light absorbance. At this time, sugar accumulation and aroma substance synthesis are strengthened, the red light absorbance begins to weaken, and in addition, the evaporation of tobacco leaf moisture accelerates, and the absorbance of near-infrared light is relatively low. In the stem-drying period, chlorophyll is almost completely degraded, the accumulation of sugars and aromas has been completed, and the metabolic activity gradually weakens. The blue light absorbance and red light absorbance are significantly reduced. The evaporation of cigar tobacco leaf moisture accelerates and enters the dehydration stage. The absorbance of near-infrared light is basically stable, with a small change range, and basically remains at a constant level, without significant upward or downward trends.

[0101] In some of these embodiments, the absorption spectral data of the cigar tobacco leaf sample to be detected is input into the trained modulation stage monitoring model to obtain the modulation stage of the cigar tobacco leaf sample to be detected, including:

[0102] The blue light absorbance, red light absorbance, and near-infrared light absorbance of the cigar tobacco leaf sample to be detected are detected by the trained modulation stage monitoring model, and combined with the water content of the cigar tobacco leaf to be detected obtained by the detection, to obtain the modulation stage of the cigar tobacco leaf sample to be detected.

[0103] Specifically, the water content of cigar tobacco leaves is a key indicator during the modulation process, and its change directly affects the physical and chemical properties of the tobacco leaves. After using the trained modulation stage monitoring model to take the blue light absorbance, red light absorbance, and near-infrared light absorbance of the cigar tobacco leaf sample to be detected as inputs and output the preliminary modulation stage of the cigar tobacco leaf sample to be detected, the water content of the cigar tobacco leaf sample is detected, and combined with the water content of the cigar tobacco leaf to be detected obtained by the detection, to comprehensively judge the modulation stage of the cigar tobacco leaf to be detected. By detecting the water content of cigar tobacco leaves and combining it with spectral data, the modulation state of the tobacco leaves can be evaluated more comprehensively. For example, a rapid decrease in water content is usually accompanied by pigment degradation and color change. Therefore, combining spectral data with water content data can more accurately determine the modulation stage of the tobacco leaves.

[0104] In another embodiment, the detection criteria of the trained modulation stage monitoring model include:

[0105] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.9, or the red light absorbance is greater than 0.75, and the water content of the cigar tobacco leaf sample to be detected is greater than 70%, it is determined that the cigar tobacco leaf sample to be detected is in the withering stage;

[0106] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.65 and less than or equal to 0.9, or the red light absorbance is greater than 0.6 and less than or equal to 0.8, or the near-infrared light absorbance is greater than 0.3, and the water content of the cigar tobacco leaf sample to be detected is greater than or equal to 65% and less than 70%, it is determined that the cigar tobacco leaf sample to be detected is in the yellowing stage;

[0107] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.6 and less than or equal to 0.65, or the red light absorbance is greater than 0.4 and less than or equal to 0.6, or the near-infrared light absorbance is greater than 0.2 and less than or equal to 0.3, and the surface color of the cigar tobacco leaf sample to be detected changes from yellow to brown, it is determined that the cigar tobacco leaf sample to be detected is in the browning stage;

[0108] When the blue light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.4 and less than or equal to 0.6, or when the red light absorbance of the cigar tobacco leaf sample to be detected is greater than 0.3 and less than or equal to 0.4, or the near-infrared light absorbance is greater than 0.1 and less than or equal to 0.2, the water content of the cigar tobacco leaf sample to be detected is greater than or equal to 30% and less than 40%; it is determined that the cigar tobacco leaf sample to be detected is in the stem-drying stage.

[0109] Specifically, Figure 4 is the absorption spectrum curve of each modulation stage of the cigar tobacco leaf modulation stage monitoring method of this embodiment, as Figure 4 shown, the green curve is the absorption spectrum curve of the cigar tobacco leaf in the yellowing stage, the yellow curve is the absorption spectrum curve of the cigar tobacco leaf in the browning stage, the red curve is the absorption spectrum curve of the cigar tobacco leaf in the stem-drying stage, the abscissa is the wavelength, in nanometers (nm), and the ordinate is the absorbance. As Figure 4 shown, in each modulation stage, the ultraviolet light, blue light absorbance, red light absorbance, and near-infrared light absorbance all have obvious peaks, and there are large differences in each peak of each modulation stage. In this embodiment, the detection standards are obtained through multiple experimental detections and analyses, as follows:

[0110] When the blue light absorbance > 0.9 or the red light absorbance > 0.7, and the water content > 70%, it is determined that the cigar tobacco leaf sample to be detected is in the wilting stage;

[0111] When 0.65 < blue light absorbance ≤ 0.9 or 0.6 < red light absorbance ≤ 0.8 or near-infrared light absorbance > 0.3, and 65% ≤ water content < 70%, it is determined that the cigar tobacco leaf sample to be detected is in the yellowing stage;

[0112] When 0.6 < blue light absorbance ≤ 0.65 or 0.4 < red light absorbance ≤ 0.6 or 0.2 < near-infrared light absorbance ≤ 0.3, and the surface color of the tobacco leaf sample changes from yellow to brown, it is determined that the cigar tobacco leaf sample to be detected is in the browning stage;

[0113] When 0.4 < blue light absorbance ≤ 0.6 or 0.3 < red light absorbance ≤ 0.4 or 0.1 < near-infrared light absorbance ≤ 0.2, and 30% ≤ water content < 40%, it is determined that the cigar tobacco leaf sample to be detected is in the stem-drying stage.

[0114] In some of these embodiments, the wavelength detection range of the absorption spectrum of the cigar tobacco leaf sample to be detected is 200 nanometers - 2500 nanometers, the blue light absorbance wavelength detection range is 400 nanometers - 500 nanometers, the red light absorbance wavelength detection range is 600 nanometers - 700 nanometers, and the near-infrared light absorbance wavelength detection range is 900 nanometers - 1500 nanometers.

[0115] Specifically, in this embodiment, the absorption spectrum detection range is from 200 nanometers to 2500 nanometers. By selecting this range, it covers the ultraviolet, visible, and near-infrared light regions, and can comprehensively reflect the spectral characteristics of cigar tobacco leaves at different modulation stages. The blue light absorbance detection range is from 400 nanometers to 500 nanometers, which belongs to the blue light region in visible light. The change in blue light absorbance is closely related to the degradation of chlorophyll in tobacco leaves. Chlorophyll has significant absorption in the blue light region. Therefore, by detecting the blue light absorbance within this range, the pigment changes in tobacco leaves can be reflected. The red light absorbance detection range is from 600 nanometers to 700 nanometers, which belongs to the red light region in visible light. The change in red light absorbance is related to the pigment conversion and cell structure change in tobacco leaves, and is an important indicator for evaluating the maturity and modulation state of tobacco leaves. The near-infrared light absorbance detection range is from 900 nanometers to 1500 nanometers, which belongs to the near-infrared region. Near-infrared light is closely related to the moisture content and chemical composition of tobacco leaves, and can reflect the moisture balance and absorption characteristics of organic substances in tobacco leaves. By selecting these specific wavelength ranges for detection, the advantages of spectral analysis technology can be fully utilized to achieve precise monitoring and evaluation of the modulation stage of cigar tobacco leaves.

[0116] In another embodiment, according to the modulation stage of the cigar tobacco leaf sample to be detected, the modulation parameters of the cigar tobacco leaf to be detected are adjusted, including:

[0117] When it is detected that the cigar tobacco leaf to be detected is in the yellowing stage, the light intensity is increased by a preset amplitude value, and the ambient temperature is controlled at 18°C - 22°C, and the ambient humidity is controlled at 70% - 75%;

[0118] When it is detected that the cigar tobacco leaf to be detected is in the browning stage, the light intensity is increased by a preset amplitude value, and the ambient temperature is controlled at 22°C - 25°C, and the ambient humidity is controlled at 60% - 65%;

[0119] When it is detected that the cigar tobacco leaf to be detected is in the dry - rib stage, the light intensity is reduced to a preset intensity range, and the ambient temperature is controlled at 26°C - 30°C, and the ambient humidity is controlled at 50% - 55%.

[0120] Specifically, during the modulation process of cigar tobacco leaves, adjusting the modulation parameters according to the modulation stage of the cigar tobacco leaf sample to be detected is a key measure to ensure the quality of tobacco leaves. By adjusting the modulation parameters, the quality of tobacco leaves is ensured, specifically including:

[0121] When the detection result shows that the cigar tobacco leaf to be detected is in the yellowing stage, the following adjustments are made to the modulation environment:

[0122] Light intensity: The light intensity is increased by a preset amplitude value. The specific adjustment amplitude value can be set according to the actual situation. The increase in light intensity helps to accelerate the degradation of chlorophyll and promote the yellowing of tobacco leaves.

[0123] Ambient temperature: Control the ambient temperature to be between 18°C and 22°C. The suitable temperature range helps to maintain the physiological activities of the tobacco leaves and avoid excessive oxidation caused by too high temperature.

[0124] Ambient humidity: Control the ambient humidity to be between 70% and 75%. Higher humidity helps to maintain the flexibility of the tobacco leaves and prevent excessive water loss during the yellowing process of the leaves.

[0125] When the test results show that the cigar tobacco leaves to be tested are in the browning period, the modulation parameters are adjusted as follows:

[0126] Light intensity: Continue to increase the light intensity by a preset amplitude value. The specific adjustment amplitude value can be set according to the actual situation. The further increase in light intensity helps to accelerate the conversion of pigments and the accumulation of carotenoids in the tobacco leaves.

[0127] Ambient temperature: Control the ambient temperature to be between 22°C and 25°C. This temperature range helps to promote the conversion of chemical components in the tobacco leaves and avoid the decline in quality caused by too high temperature.

[0128] Ambient humidity: Control the ambient humidity to be between 60% and 65%. Moderately reducing the humidity helps to balance the moisture of the tobacco leaves and promote the browning of the tobacco leaves.

[0129] When the test results show that the cigar tobacco leaves to be tested are in the stem-drying period, the modulation parameters are adjusted as follows:

[0130] Light intensity: Reduce the light intensity to a preset intensity range. The specific light intensity range can be set according to the actual situation. The reduction in light intensity helps to reduce the photo-oxidative damage of the tobacco leaves and promote the drying of the tobacco leaves.

[0131] Ambient temperature: Control the ambient temperature to be between 26°C and 30°C. Higher temperature helps to accelerate the drying process of the tobacco leaves, but it is necessary to avoid the tobacco leaves being scorched due to too high temperature.

[0132] Ambient humidity: Control the ambient humidity to be between 50% and 55%. Lower humidity helps the rapid loss of moisture in the tobacco leaves and ensures that the tobacco leaves reach the ideal drying degree during the stem-drying period.

[0133] By scientifically adjusting the modulation parameters, the modulation efficiency and final quality of cigar tobacco leaves can be effectively improved, providing a high-quality raw material basis for subsequent fermentation and processing.

[0134] In this embodiment, a detection device for the cigar tobacco leaf modulation stage is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be elaborated again. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0135] Figure 5 is a structural block diagram of the detection device for the cigar tobacco leaf modulation stage in this embodiment. As Figure 5 shown, the device 50 includes: a spectral data detection module 51, a modulation stage detection module 52, and an adjustment module 53. Among them,

[0136] The spectral data detection module 51 is used to perform absorbance detection on the cigar tobacco leaf sample to be detected, and obtain the absorption spectral data of the cigar tobacco leaf sample to be detected;

[0137] The modulation stage detection module 52 is used to input the absorption spectral data of the cigar tobacco leaf sample to be detected into the trained modulation stage monitoring model, and obtain the modulation stage where the cigar tobacco leaf sample to be detected is located;

[0138] The adjustment module 53 is used to adjust the modulation parameters of the cigar tobacco leaf to be detected according to the modulation stage of the cigar tobacco leaf sample to be detected.

[0139] It should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combined form.

[0140] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the protection scope of this application.

[0141] Obviously, the drawings are only some examples or embodiments of this application. For those of ordinary skill in the art, this application can also be applied to other similar situations according to these drawings without creative work. In addition, it can be understood that although the work done during the development process here may be complex and time-consuming, for those of ordinary skill in the art, some design, manufacturing, or production changes made according to the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient disclosure of this application.

[0142] The term "embodiment" in this application means that the specific features, structures or characteristics described in connection with an embodiment may be included in at least one embodiment of this application. The phrase appears in various positions in the specification and does not necessarily mean the same embodiment, nor does it mean that it is independent or alternative to other embodiments and mutually exclusive. Those of ordinary skill in the art can clearly or implicitly understand that the embodiments described in this application can be combined with other embodiments without conflict.

[0143] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0144] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of patent protection. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for detecting the curing stage of cigar tobacco leaves, characterized in that: include: Performing absorbance detection on the cigar tobacco leaf sample to be detected to obtain absorption spectrum data of the cigar tobacco leaf sample to be detected; Inputting the absorption spectrum data of the cigar tobacco leaf sample to be tested into the trained modulation stage monitoring model to obtain the modulation stage of the cigar tobacco leaf sample to be tested; According to the curing stage of the cigar tobacco leaf sample to be tested, the curing parameters of the cigar tobacco leaf to be tested are adjusted.

2. The method for detecting the curing stage of cigar tobacco leaves according to claim 1, characterized in that: The modulation phase monitoring model training process includes: The absorption spectrum data of cigar tobacco leaves at different curing stages are used as absorption spectrum data sets; The absorption spectrum data set is divided into an absorption spectrum data training set and an absorption spectrum data test set; Inputting the absorption spectrum data training set into a plurality of initial modulation stage monitoring models for training to obtain each trained initial modulation stage monitoring model; Based on the absorption spectrum data test set, a target modulation phase monitoring model is selected from each trained initial modulation phase monitoring model through a cross-validation method as the trained modulation phase monitoring model.

3. The method for detecting the curing stage of cigar tobacco leaves according to claim 2, characterized in that: The absorption spectrum data of cigar tobacco leaves at different curing stages are used as the absorption spectrum data set, including: When the cigar tobacco leaves are in a withering stage, acquiring absorption spectrum data of the cigar tobacco leaves every 2 days; When the cigar tobacco leaves are in the yellowing stage, acquiring absorption spectrum data of the cigar tobacco leaves once every day; When the cigar tobacco leaves are in the browning stage, acquiring absorption spectrum data of the cigar tobacco leaves every 3 days; When the cigar tobacco leaves are in the dry rib stage, the absorption spectrum data of the cigar tobacco leaves are obtained every 4 days.

4. The method for detecting the curing stage of cigar tobacco leaves according to claim 2, characterized in that: The step of dividing the absorption spectrum data set into an absorption spectrum data training set and an absorption spectrum data test set comprises: Performing smoothing processing on the absorption spectrum data set to eliminate noise in the absorption spectrum data set to obtain a denoised absorption spectrum data set; Normalizing the denoised absorption spectrum data set to obtain a standardized absorption spectrum data set; Performing baseline correction on the standardized absorption spectrum data set by using a polynomial fitting method to obtain a target absorption spectrum data set; The target absorption spectrum data set is divided into the absorption spectrum data training set and the absorption spectrum data test set.

5. The method for detecting the curing stage of cigar tobacco leaves according to claim 1, characterized in that: The absorption spectrum data of the cigar tobacco leaf sample to be tested includes blue light absorbance, red light absorbance and near-infrared light absorbance.

6. The method for detecting the curing stage of cigar tobacco leaves according to claim 5, characterized in that: The step of inputting the absorption spectrum data of the cigar tobacco leaf sample to be detected into the trained modulation stage monitoring model to obtain the modulation stage of the cigar tobacco leaf sample to be detected includes: The trained modulation stage monitoring model is used to detect the blue light absorbance, red light absorbance and near-infrared light absorbance of the cigar tobacco leaf sample to be detected, and the modulation stage of the cigar tobacco leaf sample to be detected is obtained in combination with the moisture content of the cigar tobacco leaf to be detected.

7. The method for detecting the curing stage of cigar tobacco leaves according to claim 6, characterized in that: The post-training modulation phase monitoring model detection criteria include: When the blue light absorbance of the cigar tobacco leaf sample to be tested is greater than 0.9, or the red light absorbance is greater than 0.75, and the moisture content of the cigar tobacco leaf sample to be tested is greater than 70%, it is determined that the cigar tobacco leaf sample to be tested is in the withering stage; When the blue light absorbance of the cigar tobacco leaf sample to be tested is greater than 0.65 and less than or equal to 0.9, or the red light absorbance is greater than 0.6 and less than or equal to 0.8, or the near-infrared light absorbance is greater than 0.3, and the moisture content of the cigar tobacco leaf sample to be tested is greater than or equal to 65% and less than 70%, it is determined that the cigar tobacco leaf sample to be tested is in the yellowing stage; When the blue light absorbance of the cigar tobacco leaf sample to be tested is greater than 0.6 and less than or equal to 0.65, or the red light absorbance is greater than 0.4 and less than or equal to 0.6, or the near-infrared light absorbance is greater than 0.2 and less than or equal to 0.3, and the surface color of the cigar tobacco leaf sample to be tested changes from yellow to brown, it is determined that the cigar tobacco leaf sample to be tested is in the browning stage; When the blue light absorbance of the cigar tobacco leaf sample to be tested is greater than 0.4 and less than or equal to 0.6, or when the red light absorbance of the cigar tobacco leaf sample to be tested is greater than 0.3 and less than or equal to 0.4, or the near-infrared light absorbance is greater than 0.1 and less than or equal to 0.2, the moisture content of the cigar tobacco leaf sample to be tested is greater than or equal to 30% and less than 40%; it is determined that the cigar tobacco leaf sample to be tested is in the dry tendon stage.

8. The method for detecting the curing stage of cigar tobacco leaves according to claim 7, characterized in that: The wavelength detection range of the absorption spectrum of the cigar tobacco leaf sample to be detected is 200 nanometers to 2500 nanometers, the wavelength detection range of the blue light absorbance is 400 nanometers to 500 nanometers, the wavelength detection range of the red light absorbance is 600 nanometers to 700 nanometers, and the wavelength detection range of the near-infrared light absorbance is 900 nanometers to 1500 nanometers.

9. The method for detecting the curing stage of cigar tobacco leaves according to claim 1, characterized in that: The step of adjusting the curing parameters of the cigar tobacco leaf to be tested according to the curing stage of the cigar tobacco leaf sample to be tested comprises: When it is detected that the cigar tobacco leaves to be tested are in the yellowing stage, the light intensity is increased by a preset amplitude value, and the ambient temperature is controlled at 18° C.-22° C., and the ambient humidity is controlled at 70%-75%; When it is detected that the cigar tobacco leaves to be tested are in the browning stage, the light intensity is increased by the preset amplitude value, and the ambient temperature is controlled to be 22° C.-25° C., and the ambient humidity is controlled to be 60%-65%; When it is detected that the cigar tobacco leaves to be tested are in the dry tendon stage, the light intensity is reduced to a preset intensity range, the ambient temperature is controlled to be between 26° C. and 30° C., and the ambient humidity is controlled to be between 50% and 55%.

10. A cigar tobacco curing stage detection device, characterized in that: include: Spectral data detection module, modulation phase detection module and adjustment module, wherein: The spectral data detection module is used to perform absorbance detection on the cigar tobacco leaf sample to be detected to obtain the absorption spectrum data of the cigar tobacco leaf sample to be detected; The modulation stage detection module is used to input the absorption spectrum data of the cigar tobacco leaf sample to be detected into the trained modulation stage monitoring model to obtain the modulation stage of the cigar tobacco leaf sample to be detected; The adjustment module is used to adjust the modulation parameters of the cigar tobacco leaves to be tested according to the modulation stage of the cigar tobacco leaves sample to be tested.

Images