Patents
Literature
1978 results about "Tobacco leaf" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Tobacco leaf curing process control method and device based on reinforcement learning
The invention provides a tobacco leaf curing process control method and device based on reinforcement learning, and relates to the field of tobacco leaf manufacturing. The method comprises the steps that environment parameters and tobacco leaf physical and chemical indexes in a baking room are obtained, the environment parameters comprise temperature field distribution data, humidity data and gas concentration data, and the tobacco leaf physical and chemical indexes comprise water content data, morphological data and physiological activity data of tobacco leaves; constructing a multi-dimensional state vector based on the environmental parameters and the physical and chemical indexes of the tobacco leaves; processing the multi-dimensional state vector through a pre-trained hierarchical reinforcement learning model to generate a dynamic control parameter; and the heating power, the ventilation rate and the humidity compensation amount of the baking equipment are adjusted according to the dynamic control parameters. Through the technical scheme provided by the invention, the problem of insufficient adaptability of a traditional PID control method for baking tobacco leaves is solved, the adaptive capacity of the tobacco leaf baking control process is improved, and the tobacco leaf baking quality is improved.
Owner:YUNNAN TOBACCO CORP QUJING BRANCH
Enterobacter hormaechei XW-01 as well as microbial preparation and application thereof
The invention discloses enterobacter hormaechei XW-01 and a microbial preparation thereof, the strain (preservation number is CCTCC NO: M 20242595) can efficiently degrade protein, total sugar and nicotine in tobacco leaves, sensory indexes such as aroma and aroma quantity are remarkably improved, and protease activity is remarkably improved when the enterobacter hormaechei XW-01 and wheat bran act synergistically. The microbial preparation is obtained through the processes of strain activation, fermentation culture and microbial agent preparation, and when the microbial preparation is applied to tobacco leaf treatment, through the steps of water content adjustment, preparation spraying, sealed fermentation, low-temperature drying and the like, the technical breakthrough that the protein content is reduced, the tar release amount is reduced, and the comprehensive quality grade is improved is achieved. Compared with a traditional method, the technology has the advantages that the treatment period is shortened, the cost is greatly reduced, the COD value of wastewater is greatly reduced, the cigarette quality and the production environmental protection property are remarkably improved, and the method has a wide industrial application prospect.
Owner:HENAN AGRICULTURAL UNIVERSITY
Tobacco leaf insect pest identification method
PendingCN121095514ACharacter and pattern recognitionBiological modelsInfraredFeature extraction algorithm
The invention discloses a method for identifying insect pests of tobacco leaves. The method comprises the following steps: S1, acquiring near infrared spectrum data and visible light image data of the tobacco leaves; s2, pre-processing parameters are dynamically adjusted according to the data quality indexes, smoothing processing and derivative calculation are carried out on the near infrared spectrum data, and spectrum feature vectors are obtained; s3, processing the visible light image data through a feature extraction algorithm to generate an image feature vector; s4, splicing the preprocessed spectral feature vector and the preprocessed image feature vector to form a fused feature vector; s5, a convolutional neural network model is used to process the fusion feature vector, and the convolutional neural network model comprises an attention mechanism so as to identify the insect pest type; and S6, outputting a pest recognition result. The method can solve the problems that in the prior art, the morphological characteristics of the tobacco diseases cannot be comprehensively captured due to data singleness, near infrared spectrum data are easily interfered by environmental factors, and the characteristics are lost after preprocessing, so that the accuracy of identifying the insect pests of the tobacco is improved.
Owner:GUIZHOU TOBACCO CO LIUPANSHUI CO
Method for correcting and enhancing distortion of flue-cured tobacco leaf image
The invention provides a flue-cured tobacco leaf image distortion correction enhancement method, and belongs to the technical field of flue-cured tobaccos. Distortion segmentation point detection is carried out on an obtained flue-cured tobacco leaf image, and an illumination change area caused by unevenness of a tobacco leaf surface is identified by using an illumination homogenization algorithm based on a Poisson equation; secondly, constructing a distortion jump point matrix to mark gray abrupt change positions caused by shadows and light reflection between adjacent areas, then decomposing and reconstructing multi-scale image features by adopting a Laplacian pyramid image fusion algorithm, and eliminating optical interference generated by surface fluctuation through a designed fusion rule; and finishing processing when the accuracy reaches a set range, otherwise, carrying out correction and optimization again, thereby solving the technical problem that the image quality and the subsequent analysis accuracy are influenced by shadow and light reflection generated during image acquisition due to unevenness of the tobacco leaves in the prior art.
Owner:TOBACCO RESEARCH INSTITUTE OF CHINESE ACADEMY OF AGRICULTURAL SCIENCES (QINGZHOU TOBACCO RESEARCH INSTITUTE OF CHINA NATIONAL TOBACCO COMPANY)
Nucleic acid product, kit and method for detecting aspergillus and application of nucleic acid product, kit and method in detecting mildewed tobacco leaves
PendingCN121137233AMicrobiological testing/measurementMicroorganism based processesBiotechnologyNucleotide
The invention discloses a nucleic acid product, a kit and a method for detecting aspergillus and application of the nucleic acid product, the kit and the method in detecting mildewed tobacco leaves. The nucleic acid product comprises a primer pair and a probe for detecting aspergillus, the primer pair comprises an upstream primer with a nucleotide sequence as shown in SEQ ID NO: 1 and a downstream primer with a nucleotide sequence as shown in SEQ ID NO: 2, and the nucleotide sequence of the probe is as shown in SEQ ID NO: 3. The nucleic acid product can specifically detect aspergillus, can realize rapid detection of tobacco mildew based on qPCR technology, has high sensitivity, simple operation, low cost and fast detection speed, can complete the whole detection process within several hours, does not need uncapping in amplification and detection processes, and avoids aerosol pollution caused by uncapping detection in common PCR.
Owner:CHINA TOBACCO SICHUAN IND CO LTD
Method for discriminating color uniformity of flue-cured tobacco leaves
The invention provides a method for discriminating color uniformity of flue-cured tobacco leaves, and belongs to the technical field of flue-cured tobacco leaf detection.The method comprises the steps that a camera and a light source system are arranged above a conveying belt to dynamically obtain flue-cured tobacco leaf images, and a tobacco leaf area is extracted in a self-adaptive mode through an inter-class variance maximization algorithm; the method comprises the following steps: constructing four color feature matrixes of gradual change, sudden change, stability and chaos, optimizing linear independence of feature vectors by adopting a Gram-Schmidt orthogonalization process, and eliminating correlation among features through a feature space reconstruction algorithm based on feature vector orthogonalization; and calculating the pixel average value and the standard deviation of the tobacco leaf area, counting the number of pixels in the specified interval to obtain a color uniformity value, and adjusting the filter parameters and the image processing frequency according to the frequency domain characteristics to form a closed-loop feedback control system, thereby solving the technical problem that the accuracy of the color uniformity judgment of the cured tobacco leaves is insufficient.
Owner:TOBACCO RESEARCH INSTITUTE OF CHINESE ACADEMY OF AGRICULTURAL SCIENCES (QINGZHOU TOBACCO RESEARCH INSTITUTE OF CHINA NATIONAL TOBACCO COMPANY)
Detection method of volatile compounds in tobacco leaves and clustering analysis method of tobacco leaves
The invention relates to the technical field of tobacco leaf element analysis, in particular to a detection method for volatile compounds in tobacco leaves and a clustering analysis method for the tobacco leaves. The method for detecting the volatile compounds in the tobacco leaves comprises the following steps: drying and pulverizing tobacco leaves to be detected to prepare sample powder of the tobacco leaves to be detected; extracting the mixed solution of the tobacco leaf sample powder to be detected and the internal standard solution by adopting a headspace solid-phase microextraction method to prepare an extracting solution; carrying out gas chromatography-mass spectrometry detection on the extract liquor; wherein an extraction head used by the headspace solid-phase microextraction method is a divinylbenzene / carbon molecular sieve / polydimethylsiloxane composite coating extraction head, and the parameters of the headspace solid-phase microextraction method are as follows: the extraction temperature is 75-85 DEG C, the extraction time is 45-55 minutes, the desorption time is 4-6 minutes, and the equilibrium time is 3-7 minutes. The method for detecting the volatile compounds in the tobacco leaves, provided by the invention, can effectively separate and analyze the volatile components, and is simple and efficient.
Owner:CHINA TOBACCO SICHUAN IND CO LTD
Method for manufacturing reconstituted tobacco through thick slurry method, reconstituted tobacco through thick slurry method and aerosol generating product
The invention belongs to the technical field of tobacco, and particularly relates to a method for manufacturing reconstituted tobacco through a thick slurry method, the reconstituted tobacco through the thick slurry method and an aerosol generating product. The invention provides a method for manufacturing reconstituted tobacco through a thick slurry method. The method comprises the following steps that A, reconstituted tobacco slurry containing a cross-linked essence and fragrance carrier is prepared; and B, the reconstituted tobacco slurry is subjected to tape casting, spreading and forming, and the reconstituted tobacco is obtained after drying and shaping. The cross-linked carrier generated by the reaction of cyclodextrin and binary acid is a better carrier for the tobacco flavor and perfume, has a loading rate higher than that of a traditional carrier (such as beta-cyclodextrin), also has better thermal stability, and is not easy to decompose during heating. As the thick slurry method inevitably needs a high-temperature drying step, the essence and fragrance carrier with good thermal stability can significantly improve the loading effect of the essence and fragrance in the product. The invention also provides the reconstituted tobacco and the aerosol generating product prepared by the method.
Owner:HUBEI CHINA TOBACCO INDUSTRY CO LTD +1
Deep learning flue-cured tobacco intelligent control method based on image recognition and moisture
The invention relates to the technical field of agricultural intelligent control, in particular to a deep learning flue-cured tobacco intelligent control method based on image recognition and moisture, which comprises the following steps of: acquiring a tobacco leaf surface image through image acquisition equipment, performing preprocessing and moisture monitoring analysis, and calculating a moisture content index by utilizing a near infrared spectrum technology; inputting the image into a deep convolutional neural network state recognition model, synchronously outputting tobacco leaf maturity grade and disease type information, constructing a long-short-term memory network time sequence prediction model, predicting a future water loss trend based on historical and current moisture data, generating a water loss state vector, and integrating environment parameters collected in real time. And performing fusion analysis on the multi-source information by adopting a multi-modal fusion algorithm to generate an optimal control strategy including adjustment of temperature and humidity, ventilation and irrigation parameters. Accurate sensing, intelligent decision making and closed-loop control of the flue-cured tobacco process are achieved, the flue-cured tobacco quality and production efficiency are remarkably improved, and the method is suitable for large-scale intelligent flue-cured tobacco production management.
Owner:CETC BIGDATA RES INST CO LTD +1
Orbital transfer type automatic material guiding device and material guiding method
The invention belongs to the technical field of tobacco processing equipment, and relates to an orbital transfer type automatic guide device and a guide method.The device comprises a grading and uniformizing module and a grading orbital transfer guide module which share one conveying belt, and the grading and uniformizing module is sequentially provided with a two-stage tobacco leaf uniformizing mechanism composed of centrosymmetric spiral structure guide shifting rollers in the conveying direction; the grading track-changing material guide module is provided with a plurality of track-changing material guide mechanisms consisting of spiral material guide shifting rollers and longitudinal belt conveyors; the problems that in the prior art, the material uniformizing effect is poor, material guiding distribution is unbalanced, and material blocking is likely to happen are effectively solved, the occurrence rate of material blocking is greatly reduced, production continuity is guaranteed, and frequent manual intervention is not needed.
Owner:CHINA TOBACCO SHAANXI IND
Use of pantoea B-3 for degrading cellulose in tobacco
The application discloses application of Pantoea B-3 in degrading cellulose in tobacco, and aims to solve the technical problems that cellulose in tobacco is difficult to degrade and there is lack of effective microbial method to improve tobacco quality. The Pantoea B-3 strain is isolated and screened from a cigar, and the preservation number is CCTCC NO: M 20221165. Metabolic enzyme products of the Pantoea B-3 strain can reduce the cellulose content in tobacco, improve the stimulation and bad smell in the smoking process of tobacco, and improve the safety of tobacco smoking. The process flow of the application is simple and efficient, the cost of tobacco treatment is low, the treatment period is short, the application is safe and reliable, the cellulose content in tobacco can be obviously reduced, and the quality of tobacco can be improved, and the application has good popularization and application value.
Owner:HENAN AGRICULTURAL UNIVERSITY
Preparation method and application of tobacco source aroma raw material rich in small molecule aroma components
The invention discloses a preparation method and application of a tobacco source aroma raw material rich in micromolecular aroma components, and the preparation method comprises the following steps: crushing and sieving tobacco leaves, adopting a 40% ethanol solution as a solvent, and carrying out long-time extraction and vacuum concentration under proper conditions to prepare a tobacco extract with set baume degree; the method comprises the following steps: unfreezing, activating and culturing a Wickerham LY13 strain to obtain a high-activity bacterial solution; inoculating the bacterial liquid into the tobacco extract, fermenting under a controlled condition, and enhancing the aroma components in a biotransformation manner; after fermentation is completed, fragrance components in different molecular weight ranges are finely separated out through a high-temperature sterilization and multi-stage membrane separation technology; the four groups of separated permeate liquid are used as the tobacco source flavor raw materials to be added into cigarettes, sensory evaluation is carried out, and the result shows that after the tobacco source flavor raw materials prepared through the method are applied to the cigarettes, the sensory quality of the cigarettes can be remarkably improved, and the effects of coordinating the tobacco flavor, increasing the smoke concentration, improving the aftertaste and the like are achieved.
Owner:CHINA TOBACCO HENAN IND CO LTD
Tobacco leaf nitrogen efficient sesame cake fertilizer and preparation method thereof
PendingCN121673132ABio-organic fraction processingMicroorganism based treatmentPolyaspartic acidCuring of tobacco
The invention provides a tobacco leaf nitrogen efficient sesame cake fertilizer and a preparation method thereof, and relates to the field of fertilizers. The nitrogen efficient sesame cake fertilizer for tobacco leaves comprises a solid material and water, the solid material comprises the following raw materials in percentage by mass: 60%-70% of sesame cake, 6%-8% of cottonseed cake, 12%-26% of rice husk and 8%-10% of polyaspartic acid, wherein the total mass of the raw materials is 100%. The nitrogen efficient sesame cake fertilizer for the tobacco leaves can effectively improve the quality of the tobacco leaves, improve the growth vigor of the tobacco leaves and improve the hacking degree of flue-cured tobacco leaves to a certain extent, and the cottonseed cake is added due to the fact that gossypol with a bactericidal effect is contained in the cottonseed cake, and the occurrence of soil diseases can be relieved or inhibited.
Owner:CHINA TOBACCO GUANGDONG IND
Tobacco leaf growth detection method and device, electronic equipment and storage medium
PendingCN121305365AData processing applicationsCharacter and pattern recognitionAgricultural engineeringHorticulture
The embodiment of the invention discloses a tobacco leaf growth detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring at least one tobacco leaf image corresponding to each growth stage of planted tobacco leaves in a tobacco leaf planting area; based on the at least one tobacco leaf image and a target tobacco leaf growth analysis model, obtaining an analysis result output by the model; and generating a tobacco growth report based on a preset report generation mode and the analysis result. Through the technical scheme of the embodiment of the invention, the whole growth period of the tobacco leaves can be realized, the growth state can be monitored in real time and automatically analyzed, and the efficiency and accuracy of tobacco leaf planting management are improved.
Owner:CHINA TOBACCO GUANGXI IND
Flue-cured tobacco flavor type distinguishing method and device based on visible-near infrared spectrum
PendingCN120870041ACharacter and pattern recognitionColor/spectral properties measurementsVisible near infraredNear infrared spectra
The invention provides a flue-cured tobacco flavor type discrimination method based on visible-near infrared spectroscopy, which comprises the following steps: realizing original state nondestructive detection of bundled tobacco leaves based on visible-near infrared spectroscopy without destructive pretreatment such as grinding and compaction; wherein when the visible-near infrared spectrum is processed, based on a threshold segmentation method, the characteristic wave band is extracted, the characteristic wave band is within 500.14-649.75 nm, and the spectral reflectivity value is smaller than or equal to 0.3, or the characteristic wave band is within 700.52-799.26 nm, and the spectral reflectivity value is larger than or equal to 0.5; taking a pixel point of which the characteristic wave band is within 1001.71-1298.17 nm and the spectral reflectivity value is less than or equal to 0.55, or the characteristic wave band is within 1502.16-1598.29 nm and the spectral reflectivity value is greater than or equal to 0.4, and the difference value between the upper and lower bounds of the spectral reflectivity in the wave band is greater than or equal to 0.1 as a region of interest, and calculating the mean value of the spectral reflectivity of all pixel points in the region of interest, as a single spectrum curve of a tobacco leaf sample of the tobacco bundle, a tobacco leaf stem and a shadow part are effectively removed, and a tobacco leaf surface area is effectively extracted and reserved.
Owner:ZHENGZHOU TOBACCO RES INST OF CNTC
Flue-cured tobacco yield prediction method fusing airborne laser radar point cloud and orthoimage
ActiveCN121459225ACharacter and pattern recognitionNeural learning methodsLidar point cloudAtmospheric sciences
The invention relates to the technical field of crop yield estimation through remote sensing images, and provides a flue-cured tobacco yield prediction method fusing airborne laser radar point cloud and an orthoimage, and the method comprises the steps: obtaining the LiDAR point cloud and the orthoimage of a measurement region; performing tobacco field identification, tobacco field two-dimensional polygon extraction and tobacco field area calculation on the orthoimage by using a pre-trained U-Net semantic segmentation network model; tobacco field leaf area index extraction is carried out based on LiDAR point cloud, and then a tobacco field average leaf area index is calculated; obtaining a tobacco leaf surface density value of the tobacco field; and predicting the flue-cured tobacco yield based on the tobacco field area, the tobacco field average leaf area index and the tobacco leaf surface density value of the tobacco field. A new method is provided for flue-cured tobacco yield prediction, the method has the advantages of remarkably reducing the number of field workers, the workload and the labor intensity, and the method is free of contact and damage, simple, easy to implement, high in precision, high in timeliness and economical and feasible.
Owner:SHANDONG LINYI TOBACCO
Self-adaptive prediction control method and system for cut tobacco drying moisture and storage medium
The invention discloses a self-adaptive prediction control method and system for cut tobacco drying moisture and a storage medium. The method comprises the steps that historical cut tobacco drying process data are acquired and denoised; standardizing the denoised historical tobacco leaf drying process data, and constructing a sample data set by adopting a multi-scale segmentation strategy based on a sliding window mechanism; constructing a neural network prediction model architecture based on differential recursion; training a neural network prediction model based on differential recursion by using the sample data set; collecting tobacco leaf drying process data on line, standardizing the data, constructing input features, inputting the input features into the trained neural network prediction model based on differential recursion, and outputting an outlet material instantaneous moisture prediction vector, a hot air valve opening prediction vector and a moisture removal air door opening prediction vector of a future prediction step length; and generating and issuing a tobacco leaf drying control instruction according to a model prediction result. The problem that in the prior art, the cut tobacco drying quality is not stable can be solved.
Owner:CENT SOUTH UNIV
Method for separation and purification of taxadiene from tobacco and GC-MSMS quantitative detection
The invention relates to the technical field of chemical separation and purification, and discloses a method for separation and purification of taxadiene from tobacco and GC-MSMS quantitative detection.The method for separation and purification of taxadiene from tobacco comprises the following steps that S1, tobacco leaves are made into powder, an extracting agent is added, ultrasonic extraction is conducted for multiple times, and extract liquor is obtained; s2, evaporating the extract to dryness, adding an organic solvent, and dissolving to form a concentrated solution; s3, the concentrated solution is added into a silica gel column for gradient elution, and an extraction sample is obtained; and S4, evaporating the extracted sample to dryness, adding acetonitrile for dissolving, and carrying out secondary recrystallization to obtain purified taxadiene. According to the method, the efficiency and purity of separating the taxadiene from the tobacco are improved, and the taxadiene is accurately quantified.
Owner:CHONGQING CHINA TOBACCO IND CO LTD
Tobacco leaf spiral picking mechanism and tobacco leaf spiral picking device
The utility model discloses a spiral tobacco leaf picking mechanism and a spiral tobacco leaf picking device.The spiral tobacco leaf picking mechanism comprises a front spiral tooth and a rear spiral tooth which are located in the middle, and the front spiral tooth comprises a cylindrical front spiral tooth body and 2-6 front picking pieces which are evenly and longitudinally arranged on the circumference of the front spiral tooth body in a cross shape; the outer surface of the front picking piece is in a wave shape, and a front connecting rod is arranged at the end of the outer side of a front spiral tooth body. The rear spiral tooth comprises a cylindrical rear spiral tooth body and a rear picking rack spirally wound on the circumferential surface of the rear spiral tooth body, the outer surface of the rear picking rack is arranged to be in a gear shape, and a rear connecting rod is arranged at the end of the outer side of the rear spiral tooth body. The spiral tobacco leaf picking mechanism has the advantages that the spiral tobacco leaf picking mechanism can separate tobacco leaves on the front side, the rear side, the left side and the right side, step-by-step picking is achieved, the picking efficiency is high, the picking effect is good, time and labor are saved, and the labor intensity of tobacco planters is greatly reduced.
Owner:SHANDONG WEIFANG TOBACCO CO LTD +2
Application of inhibiting or knocking out tobacco polyphenol oxidase gene NtPPO12 in inhibiting tobacco browning
The present application provides an application of inhibiting or knocking out tobacco polyphenol oxidase gene NtPPO12 in inhibiting tobacco browning. The present application screens an important gene NtPPO12 related to tobacco browning through transcriptome sequencing and molecular biology experiments, further verifies the promoter activity and gene expression site of NtPPO12, and deeply researches the function of the gene through gene editing and overexpression. The present application proves by molecular biology experiments that the NtPPO12 gene provided by the present application is a key gene related to browning in the mature curing process of tobacco, and by regulating the expression amount of the NtPPO12 gene, the browning degree of tobacco can be controlled, and the tobacco maturity and curing resistance can be improved, which is beneficial to reducing the picking frequency, improving the curing characteristics, and improving the appearance and internal quality of tobacco leaves, so it has a broad market application prospect.
Owner:TOBACCO RESEARCH INSTITUTE OF CHINESE ACADEMY OF AGRICULTURAL SCIENCES (QINGZHOU TOBACCO RESEARCH INSTITUTE OF CHINA NATIONAL TOBACCO COMPANY) +1
Tobacco leaf weighing device for flue-cured tobacco baking
The utility model provides a tobacco leaf weighing device for flue-cured tobacco baking, which comprises a baking room, a baking frame, a humidity sensor, a temperature sensor and a control module are arranged in the baking room, the baking frame comprises a vertical support frame and a transverse placing frame, the placing frame comprises a lower rod and an upper rod, the upper rod is fixedly arranged on the vertical frame, and the humidity sensor is arranged on the lower rod. The lower rod is connected to the upper rod through a connecting rod, a gap is reserved between the upper rod and the lower rod, a tobacco leaf rod for placing tobacco leaves is arranged in the gap, a tension sensor is arranged on the connecting rod, and the humidity sensor, the temperature sensor and the tension sensor are electrically connected with a control module. When the device is used in the baking process, the weight change condition in the whole baking process is automatically recorded, the weight of single-rod fresh tobacco leaves, the weight of single-dry tobacco leaves after baking and the total weight before baking and after baking can be accurately calculated according to the tobacco loading sequence and the tobacco unloading sequence, the fresh-to-dry ratio is accurately calculated, and data support is conveniently provided for selection of baking strategies in a tobacco area.
Owner:WUXI BRANCH CHONGQING CITY COMPANY OF CHINA NAT TOBACCO
Tobacco leaf maturity nondestructive testing method based on multispectral imaging
PendingCN121185943ASpectrum investigationColor/spectral properties measurementsAlgorithmNetwork model
The invention provides a tobacco leaf maturity nondestructive testing method based on multispectral imaging, and belongs to the technical field of tobacco leaf maturity detection.The tobacco leaf maturity nondestructive testing method comprises the steps that six-channel spectral data collection is conducted on three areas of a tobacco leaf tip, a tobacco leaf middle and a tobacco leaf base, a GPU multi-CUDA flow parallel computing architecture is started to operate a shallow feature extraction model and a dynamic spectrum regulation and control model, and the tobacco leaf maturity is obtained; a shallow layer direct output or deep layer optimization processing path is adopted through complexity score judgment, finally, three-region optimization spectral features are fused through a multi-branch deep learning network model, and maturity level probability distribution is output through feature fusion layer splicing, full connection layer integration and Softmax activation. And selecting the category corresponding to the highest probability as a tobacco maturity discrimination result. The method solves the technical problem that it is difficult to discriminate the maturity of tobacco leaves accurately in the prior art.
Owner:TOBACCO RESEARCH INSTITUTE OF CHINESE ACADEMY OF AGRICULTURAL SCIENCES (QINGZHOU TOBACCO RESEARCH INSTITUTE OF CHINA NATIONAL TOBACCO COMPANY)
A three-stage tobacco leaf pre-loose device
ActiveCN116439393BTobacco preparationFinal product manufactureNicotiana tabacumStructural engineering
Owner:CHINA TOBACCO ANHUI IND CO LTD
A method for cigarette formulation design based on numerical control of tobacco calorific value.
This invention discloses a cigarette formulation design method based on calorific value adjustment. The method includes the following steps: S1, collecting calorific value data; S2, constructing a tobacco leaf calorific value prediction model based on near-infrared spectroscopy; S3, extending the model in step S2 to stockpiled tobacco leaves; S4, designing cigarette formulations based on calorific value screening; S5, improving the permeability and aroma of the formulation by selecting alternative formulations with significantly higher calorific values than the original formulation; and improving the smoothness and reducing the irritation of the formulation by selecting alternative formulations with significantly lower calorific values than the original formulation. This invention, without changing the basic components of the existing formulation, including total sugar, reducing sugar, nicotine, chlorine, potassium, total nitrogen, pH, etc., designs cigarette formulations of different styles and qualities by adjusting the calorific value, and achieves rapid detection of tobacco leaf calorific value.
Owner:CHINA TOBACCO ZHEJIANG IND CO LTD
Production quality control method of special fertilizer for Yunnan cigar tobacco leaves
PendingCN120875687AData processing applicationsMicroorganism based treatmentAgricultural scienceMetabolite
The invention relates to the technical field of soil fertility management, in particular to a production quality control method of a special fertilizer for Yunnan cigar tobacco leaves, which comprises the following steps: step 1, preparing a waste-based functional carrier; step 2, signal response type fermentation control: based on a dynamic monitoring result of microbial population sensing signal molecules in a fermentation system, regulating and controlling the injection opportunity of an exogenous inducer and fermentation environment parameters, and directionally synthesizing a targeted antibacterial metabolite; step 3, adaptive packaging in a growing period; and 4, bionic verification and closed-loop optimization: verifying a nutrient release curve through a bionic root system simulation device, and feeding back and adjusting packaging parameters in combination with a field metabolite detection result to form a production-application self-optimization system. The production efficiency and fertilizer efficiency of the cigar tobacco leaf fertilizer are improved through accurate process control, it is ensured that nutrient supply and release of the fertilizer in all growth periods have excellent matching performance, and the effect of the fertilizer can be optimized in practical application.
Owner:YUNNAN AGRICULTURAL UNIVERSITY +1
Yeast saccharomyces cerevisiae and application thereof
The invention provides a strain of saccharomyces cerevisiae and application of the saccharomyces cerevisiae. The preservation number of the Filobasidium magnum is CGMCC (China General Microbiological Culture Collection Center) No.34231, and the Filobasidium magnum secretes lipoxygenase, protease and amylase. Compared with a control group fermented by sterile water, the saccharomyces cerevisiae fermentation group has the advantages that when the saccharomyces cerevisiae fermentation group is applied to the enhanced fermentation of the tobacco leaves, the contents of carotenoid degradation products, cembrane degradation products, Maillard reaction products, chlorophyll degradation products, terpenoid substances and the like of the tobacco leaves can be remarkably increased, the potassium-chlorine ratio can be increased by 50.1%, and the yield of the tobacco leaves can be increased by 50.1%. The total content of aroma components of the tobacco leaves is increased by 37.7%. According to the invention, the aroma amount, aroma richness, maturity, sweetness and combustibility of cigar tobacco leaves can be obviously improved, irritation and offensive odor are reduced, the aroma characteristics of sweet aroma, costustoot, bean aroma and the like are highlighted, and the fermentation period is shortened to 15 days.
Owner:CHINA TOBACCO SICHUAN IND CO LTD
Tobacco harvesting machine navigation method and system based on three-weight dynamic fusion
PendingCN120907551ANavigational calculation instrumentsNavigation by speed/acceleration measurementsConfidence metricEngineering
The invention relates to the technical field of agricultural machinery automation, and discloses a tobacco harvesting machine navigation method and system based on three-weight dynamic fusion, and the method comprises the following steps: firstly collecting multi-source navigation data, and evaluating the quality of the multi-source navigation data in real time to generate a real-time confidence coefficient; and maintaining a navigation risk map based on the historical data to obtain prediction confidence. Then, the two confidence coefficients are jointly used for adaptive state fusion, and optimal state estimation and uncertainty thereof are obtained. And the uncertainty is converted into global confidence so as to determine a hierarchical behavior mode. And finally, a closed-loop control instruction is generated in combination with the optimal state and the behavior mode. According to the method, firstly, real-time multi-dimensional quality evaluation is carried out on each navigation information source, and the measurement noise parameters in the extended Kalman filter are dynamically adjusted based on the evaluation result, so that the navigation system can carry out adaptive fusion according to the data reliability at each moment, and the technical effects of accurate quantification and utilization of different quality information are achieved.
Owner:GUIZHOU UNIV
Tobacco leaf quality feature library-based threshing and redrying digital formula design method and system
The invention discloses a threshing and redrying digital formula design method and system based on a tobacco leaf quality feature library, and the method comprises the steps: building a tobacco leaf quality feature library based on the data of various indexes of tobacco leaf raw materials and tobacco leaf finished products; based on the tobacco leaf quality feature library, establishing a tobacco leaf quality prediction meta-model by adopting an XGBoost model and neural network model integration calibration technology; according to the characteristic data of each tobacco leaf raw material to be proportioned, a linear programming solver is combined with a particle swarm algorithm technology to construct a multi-target mixed optimization formula algorithm model, and the tobacco leaf raw material proportioning proportion is optimized; and based on the tobacco leaf quality prediction meta-model, predicting a tobacco leaf finished product index which can be achieved by predicting the ratio of the tobacco leaf raw materials. A mixed solving method combining a linear programming solver with a swarm intelligence algorithm is adopted, a plurality of raw material tobacco leaf proportioning schemes are solved for multi-target requirements of chemical components, inventory targets, cost targets and the like proposed by users, and the mixed requirements of the users for quality and cost are met.
Owner:YUNNAN KUNMING SHIPBUILDING DESIGN & RESEARCH INSTITUTE
Tobacco leaf curing process optimizing method and system
The invention discloses a tobacco leaf curing process optimization method and system, and the method comprises the steps: building a dynamic process diagram with multi-dimensional nodes according to the historical data of a tobacco leaf curing process, and enabling the dynamic process diagram to represent the state and the processing process of tobacco leaves at any processing moment; the weight of the processing technology at the moment is calculated according to the tobacco leaf shape modal data and the processing technology at any moment in the real-time dynamic technology diagram, and the processing technology at the moment is adjusted in real time; integrating the plurality of modal data of the real-time tobacco leaf shape and establishing a training model, wherein the training model is used for outputting optimal process parameters; searching an optimal process path globally according to the optimal process parameters output by the training model, inhibiting parameter fluctuation, and regulating and controlling the real-time process parameters through fuzzy logic control; and performing feature extraction on the to-be-baked tobacco leaves to match the optimal process parameters and the optimal process path for baking. The process is intelligently and dynamically optimized, the quality is accurately controlled, the consumption is reduced, and browning is efficiently and stably inhibited.
Owner:YUNNAN TOBACCO CORP QUJING BRANCH
Tobacco leaf quality improving method and system based on planting soil management
The invention discloses a tobacco leaf quality improving method and system based on planting soil management. The method comprises the following steps: firstly, acquiring historical soil quality and root growth data of a tobacco plant, and analyzing root growth preferences under different soil conditions by using a clustering algorithm to form soil quality-preference data; combining the soil quality data of the target planting area to construct a root growth probability distribution map, and predicting root distribution according to the planting target; determining the arrangement position of a soil monitoring sensor according to a prediction result, and establishing a monitoring network to realize real-time acquisition of soil substance change; and finally, adjusting and managing nutrient substances in the tobacco planting process according to the monitoring data. According to the method, the adaptability of root systems and soil is improved, nutrient supply is optimized, balanced growth and stable quality of the tobacco leaves are promoted, and therefore tobacco leaf quality improvement and planting benefit optimization are achieved.
Owner:CHINA TOBACCO GUANGXI IND