CN117351292B - Tobacco production facility management method and system based on Internet of things - Google Patents
Tobacco production facility management method and system based on Internet of things Download PDFInfo
- Publication number
- CN117351292B CN117351292B CN202311639266.6A CN202311639266A CN117351292B CN 117351292 B CN117351292 B CN 117351292B CN 202311639266 A CN202311639266 A CN 202311639266A CN 117351292 B CN117351292 B CN 117351292B
- Authority
- CN
- China
- Prior art keywords
- tobacco
- parameters
- processing
- detected
- products
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 657
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 200
- 238000007726 management method Methods 0.000 title claims abstract description 24
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 241000208125 Nicotiana Species 0.000 claims abstract description 656
- 238000012545 processing Methods 0.000 claims abstract description 177
- 235000019505 tobacco product Nutrition 0.000 claims abstract description 172
- 238000004806 packaging method and process Methods 0.000 claims abstract description 49
- 230000001105 regulatory effect Effects 0.000 claims abstract description 22
- 230000001276 controlling effect Effects 0.000 claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 claims description 57
- 230000007547 defect Effects 0.000 claims description 47
- 238000000034 method Methods 0.000 claims description 42
- 238000001514 detection method Methods 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 34
- 238000004422 calculation algorithm Methods 0.000 claims description 31
- 241000607479 Yersinia pestis Species 0.000 claims description 24
- 201000010099 disease Diseases 0.000 claims description 24
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000008439 repair process Effects 0.000 claims description 13
- 230000007704 transition Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000005477 standard model Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 239000002699 waste material Substances 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000012216 screening Methods 0.000 abstract description 3
- 238000012937 correction Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 9
- 241000238631 Hexapoda Species 0.000 description 8
- 238000005457 optimization Methods 0.000 description 8
- 238000000342 Monte Carlo simulation Methods 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 235000019506 cigar Nutrition 0.000 description 2
- 235000019504 cigarettes Nutrition 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 235000001705 insufficient nutrition Nutrition 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses a tobacco production facility management method and system based on the Internet of things, comprising the following steps: analyzing the growth condition of tobacco in a tobacco planting area, regulating and controlling the growth condition of the tobacco, and screening processable tobacco; processing the processable tobacco by using a tobacco production facility to obtain a tobacco processed product; and classifying the tobacco processed products, and packaging the classified tobacco processed products to obtain tobacco products. The invention can analyze the tobacco processed products, manage the tobacco production facilities according to the state of the tobacco processed products, improve the working efficiency of the tobacco production facilities and improve the economic benefit.
Description
Technical Field
The invention relates to the field of tobacco production, in particular to a tobacco production facility management method and system based on the Internet of things.
Background
In today's society, there are a large number of smokers buying tobacco products for consumption, including cigarettes, cigars, etc. Whereas tobacco products need to be manufactured from tobacco raw materials. The tobacco production facility is a machine for processing tobacco raw materials into tobacco products, and the main working steps of the machine comprise baking and mixing of tobacco, cutting, packaging of tobacco products and the like. In the working process of the tobacco production facility, the working parameters are easily influenced by the environment, and abnormal working parameters are produced, so that the tobacco processed product does not meet the standard specification, thereby reducing the processing efficiency and the processing effect of the tobacco, not meeting the economic benefit, and not protecting the environment. The tobacco production facilities are required to be subjected to standard management, the defect parts of the tobacco production facilities are corrected, and the tobacco processing efficiency and the tobacco processing effect are improved.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a tobacco production facility management method and system based on the Internet of things.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides a tobacco production facility management method based on the Internet of things, which comprises the following steps of:
observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
and packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, analyzing the packaging state of the tobacco product, and repairing the defect of the tobacco product based on an analysis result.
Further, in a preferred embodiment of the present invention, the method for observing the growth condition of tobacco in the tobacco planting area and regulating the growth condition of tobacco based on the growth condition of tobacco specifically includes:
Acquiring a real-time image of a tobacco planting area by using a camera, and performing image preprocessing on the real-time image of the tobacco planting area, wherein the image preprocessing comprises gray processing and noise reduction processing on the image to obtain a preprocessed tobacco planting area image;
extracting features of the preprocessed tobacco planting area image to obtain surface feature parameters of each tobacco in the tobacco planting area, constructing a tobacco surface model based on the surface feature parameters of each tobacco in the tobacco planting area, and constructing a tobacco surface standard model based on historical data retrieval;
analyzing the tobacco surface model to obtain the real-time growth condition of tobacco, wherein the real-time growth condition of the tobacco comprises the color, the size and the surface pest and disease damage degree of the tobacco, and obtaining the standard growth condition of the tobacco based on the tobacco surface standard model;
comparing and analyzing the real-time growth condition of the tobacco with the standard growth condition of the tobacco to obtain a tobacco growth deviation value, defining the tobacco with the tobacco growth deviation value within a preset range as processable tobacco, and defining the tobacco with the tobacco growth deviation value outside the preset range as tobacco to be detected;
analyzing the surface disease and pest degree in the real-time growth condition of the tobacco to be detected, dividing the tobacco to be detected with the surface disease and pest degree being greater than the preset degree into non-processable tobacco, and guiding the real-time growth condition of the rest of the tobacco to be detected into a tobacco cultivation control center, wherein the tobacco cultivation control center regulates and controls the growth condition of the tobacco planting area where the rest of the tobacco to be detected is located in real time through the Internet of things.
Further, in a preferred embodiment of the present invention, the tobacco processing step is obtained based on the production element, the tobacco processing facility processes the processable tobacco based on the tobacco processing step, and the real-time processing parameters of the tobacco processing facility are intelligently controlled during the processing process, specifically:
acquiring production elements of tobacco based on big data retrieval, and acquiring a tobacco processing step based on the production elements of tobacco;
placing the processable tobacco in a tobacco production facility, and introducing the tobacco processing step into a control center of the tobacco production facility, wherein the control center of the tobacco production facility generates processing parameters according to the tobacco processing step, and the control center of the tobacco production facility controls the tobacco production facility to process the processable tobacco based on the processing parameters;
real-time monitoring is carried out on the processing parameters, the real-time processing parameters are obtained in a control center, if the real-time processing parameters are not in a preset range, the corresponding real-time processing parameters are defined as abnormal processing parameters, and the running time of the tobacco production parameters under the abnormal processing parameters is obtained and defined as abnormal running time;
Tobacco processed in abnormal operation time is obtained, the tobacco is defined as two types of tobacco to be detected, tobacco quality detection is carried out on the two types of tobacco to be detected, a tobacco quality detection result is generated, and defect position tracing is carried out on tobacco production facilities based on the tobacco quality detection result;
combining the defect positions of the tobacco production facilities with the abnormal processing parameters to obtain processing parameters of each defect position, and introducing the tobacco quality detection result and the processing parameters of each defect position into a convolutional neural network to generate repair processing parameters;
and the tobacco production facility carries out tobacco restoration treatment on the two types of to-be-detected tobacco based on restoration processing parameters to obtain restored tobacco, mixes the restored tobacco with other processable tobacco, and carries out tobacco processing treatment on the mixed tobacco by using the tobacco production facility under standard processing parameters to obtain a tobacco processed product.
Further, in a preferred embodiment of the present invention, the detecting of tobacco quality of the second class of tobacco to be detected generates a tobacco quality detection result, and tracing the defect position of the tobacco production facility based on the tobacco quality detection result, specifically:
Acquiring surface parameters of a class II to-be-detected tobacco, and constructing a class II to-be-detected tobacco three-dimensional model based on the surface parameters of the class II to-be-detected tobacco;
acquiring state parameters of the two types of tobacco to be detected based on the two types of tobacco to be detected three-dimensional model, acquiring preset state parameters of the two types of tobacco to be detected based on big data retrieval, and calculating a deviation value between the state parameters of the two types of tobacco to be detected and the preset state parameters, wherein the deviation value is defined as a state parameter deviation value;
constructing a time sequence, and combining the state parameter deviation value and the abnormal processing parameter to generate a state parameter deviation value and an abnormal processing parameter based on the time sequence;
introducing a Markov chain algorithm, and performing state transition probability calculation on the state parameter deviation value and the abnormal processing parameter based on the time sequence to obtain fault state transition probability values of tobacco production facilities under different time sequences;
based on the fault state transition probability values of the tobacco production facilities under the different time sequences, a fault state probability table is generated, the fault state probability table is analyzed, and the fault state probability table is imported into a Bayesian network for training, so that the defect positions of the tobacco production facilities are obtained.
Further, in a preferred embodiment of the present invention, based on tobacco production order information and quality detection parameters of tobacco processed products, a fuzzy clustering algorithm is used to classify the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product, specifically:
acquiring tobacco production order information, and acquiring the number of different tobacco products based on the tobacco production order information;
based on the tobacco production facility, acquiring quality detection parameters of all tobacco processed products, generating a quality parameter data set, initializing the quality parameter data set, and introducing a fuzzy clustering algorithm to acquire a membership matrix of the quality parameter data set;
carrying out iterative updating on the membership matrix by an iterative algorithm and presetting iterative times;
stopping iteration updating when the iteration times reach a preset value to obtain an initial iteration analysis result, and evaluating the initial iteration analysis result through a fuzzy coefficient in a fuzzy clustering algorithm to generate an evaluation value;
if the evaluation value is not in the range of the preset value, carrying out iteration updating again by using an iteration algorithm, and stopping iteration updating and outputting an optimal iteration analysis result when the Euclidean distance between each quality detection parameter data point in the membership matrix and the center of the membership matrix reaches the preset value;
If the evaluation value is within the range of the preset value, the initial iteration analysis result is used as the optimal iteration analysis output;
introducing the optimal iterative analysis result into a tobacco production facility, classifying tobacco processed products, and obtaining the types of the tobacco processed products required by different tobacco products;
and analyzing the quantity of the different tobacco products and the types of the tobacco processed products required by the different tobacco products to obtain the types and the quantities of the tobacco processed products required by the single tobacco product.
Further, in a preferred embodiment of the present invention, the method for packaging a tobacco processed product by a tobacco production facility to obtain a tobacco product, performing a packaging state analysis on the tobacco product, and repairing a defect of the tobacco product based on the analysis result comprises:
based on the tobacco production order information and the historical data information, obtaining appearance parameters and weight parameters of a single tobacco product, combining the types and the amounts of tobacco processed products required by the single tobacco product, and introducing a convolutional neural network model to perform prediction processing to obtain packaging working parameters;
the tobacco production facility packages the tobacco processed products based on the packaging working parameters to obtain initial tobacco products, and obtains appearance parameters and weight parameters of all the initial tobacco products;
The appearance parameters of the initial tobacco products comprise the package color and the size of the initial tobacco products, the color difference value of the package color of the initial tobacco products and the standard package color is obtained, and when the color difference value is larger than a preset value, the corresponding initial tobacco products are defined as abnormal-color tobacco products;
detecting the humidity of the abnormal color tobacco products by using a humidity sensor, if the humidity parameter of the abnormal color tobacco products is larger than a preset value, baking the corresponding abnormal color tobacco products until the humidity parameter reaches the preset value, and the color difference value between the packaging color and the standard packaging color meets the preset value;
when the humidity parameter of the abnormal color tobacco product is in a preset range, but the color difference value between the packaging color and the standard packaging color is larger than a preset value, defining the corresponding abnormal color tobacco product as a waste tobacco product, and defining all the rest initial tobacco products as tobacco products with weight to be detected;
and analyzing the weight parameters of the weight to-be-detected tobacco products, repackaging the weight to-be-detected tobacco products with the weight parameters not within the preset range, and defining the weight to-be-detected tobacco products with the weight parameters within the preset range as qualified tobacco products.
The second aspect of the present invention also provides a tobacco production facility management system based on the internet of things, the production facility management system includes a memory and a processor, the memory stores a tobacco production facility management method based on the internet of things, and when the tobacco production facility management method based on the internet of things is executed by the processor, the following steps are implemented:
observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
and packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, analyzing the packaging state of the tobacco product, and repairing the defect of the tobacco product based on an analysis result.
The invention solves the technical defects in the background technology, and has the following beneficial effects: analyzing the growth condition of tobacco in a tobacco planting area, regulating and controlling the growth condition of the tobacco, and screening processable tobacco; processing the processable tobacco by using a tobacco production facility to obtain a tobacco processed product; and classifying the tobacco processed products, and packaging the classified tobacco processed products to obtain tobacco products. The invention can analyze the tobacco processed products, manage the tobacco production facilities according to the state of the tobacco processed products, improve the working efficiency of the tobacco production facilities and improve the economic benefit.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a method of tobacco production facility management based on the Internet of things;
FIG. 2 shows a flow chart for intelligent regulation of real-time processing parameters of a tobacco production facility;
fig. 3 shows a view of a tobacco production facility management system based on the internet of things.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a tobacco production facility management method based on the internet of things, comprising the following steps:
s102: observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
s104: acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
S106: classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
s108: and packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, analyzing the packaging state of the tobacco product, and repairing the defect of the tobacco product based on an analysis result.
Further, in a preferred embodiment of the present invention, the method for observing the growth condition of tobacco in the tobacco planting area and regulating the growth condition of tobacco based on the growth condition of tobacco specifically includes:
acquiring a real-time image of a tobacco planting area by using a camera, and performing image preprocessing on the real-time image of the tobacco planting area, wherein the image preprocessing comprises gray processing and noise reduction processing on the image to obtain a preprocessed tobacco planting area image;
extracting features of the preprocessed tobacco planting area image to obtain surface feature parameters of each tobacco in the tobacco planting area, constructing a tobacco surface model based on the surface feature parameters of each tobacco in the tobacco planting area, and constructing a tobacco surface standard model based on historical data retrieval;
Analyzing the tobacco surface model to obtain the real-time growth condition of tobacco, wherein the real-time growth condition of the tobacco comprises the color, the size and the surface pest and disease damage degree of the tobacco, and obtaining the standard growth condition of the tobacco based on the tobacco surface standard model;
comparing and analyzing the real-time growth condition of the tobacco with the standard growth condition of the tobacco to obtain a tobacco growth deviation value, defining the tobacco with the tobacco growth deviation value within a preset range as processable tobacco, and defining the tobacco with the tobacco growth deviation value outside the preset range as tobacco to be detected;
analyzing the surface disease and pest degree in the real-time growth condition of the tobacco to be detected, dividing the tobacco to be detected with the surface disease and pest degree being greater than the preset degree into non-processable tobacco, and guiding the real-time growth condition of the rest of the tobacco to be detected into a tobacco cultivation control center, wherein the tobacco cultivation control center regulates and controls the growth condition of the tobacco planting area where the rest of the tobacco to be detected is located in real time through the Internet of things.
The tobacco has a special planting area, and the purpose of acquiring the image of the tobacco planting area by an image recognition method is to study the growth condition of the tobacco. During the growth process of the tobacco, the tobacco can be influenced by diseases and insect pests, weather and the like, so that necrosis is generated on the surface of the tobacco, or the growth state is abnormal. The purpose of constructing the tobacco surface model is to intuitively acquire the growth state of tobacco through image recognition, and the deviation value acquired by comparing the tobacco surface model with the standard model reflects the difference between the growth state and the normal state of the tobacco. If the surface pest and disease damage degree of the tobacco to be detected is larger than a preset value, the tobacco is proved to be unsuitable for continuous processing and is directly abandoned. The other reasons for the deviation of the tobacco to be detected are possibly insufficient nutrition and moisture, so that the growth condition of the tobacco is abnormal, and the growth condition of the area where the tobacco is positioned is regulated in real time, such as the watering rate is controlled, the fertilizer is applied to the planting land of the tobacco, and the nutrition is increased. According to the invention, the growth condition of tobacco can be judged through the tobacco surface model, and the growth condition of the tobacco planting area is regulated and controlled in real time.
Further, in a preferred embodiment of the present invention, based on tobacco production order information and quality detection parameters of tobacco processed products, a fuzzy clustering algorithm is used to classify the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product, specifically:
acquiring tobacco production order information, and acquiring the number of different tobacco products based on the tobacco production order information;
based on the tobacco production facility, acquiring quality detection parameters of all tobacco processed products, generating a quality parameter data set, initializing the quality parameter data set, and introducing a fuzzy clustering algorithm to acquire a membership matrix of the quality parameter data set;
carrying out iterative updating on the membership matrix by an iterative algorithm and presetting iterative times;
stopping iteration updating when the iteration times reach a preset value to obtain an initial iteration analysis result, and evaluating the initial iteration analysis result through a fuzzy coefficient in a fuzzy clustering algorithm to generate an evaluation value;
if the evaluation value is not in the range of the preset value, carrying out iteration updating again by using an iteration algorithm, and stopping iteration updating and outputting an optimal iteration analysis result when the Euclidean distance between each quality detection parameter data point in the membership matrix and the center of the membership matrix reaches the preset value;
If the evaluation value is within the range of the preset value, the initial iteration analysis result is used as the optimal iteration analysis output;
introducing the optimal iterative analysis result into a tobacco production facility, classifying tobacco processed products, and obtaining the types of the tobacco processed products required by different tobacco products;
and analyzing the quantity of the different tobacco products and the types of the tobacco processed products required by the different tobacco products to obtain the types and the quantities of the tobacco processed products required by the single tobacco product.
The tobacco production order includes the number of tobacco products, and the types of tobacco products are different, and the types and the numbers of tobacco processed products used are also different. Such as cigars, in tobacco products, are used in a greater variety and number of tobacco products than cigarettes. Different kinds of tobacco may be planted in the same tobacco planting area, and the appearance size and the like of the tobacco processed product obtained after processing the tobacco may be the same, but the quality parameters of different tobacco processed products may be different. The quality parameters include the weight of the tobacco processed product in the same volume, the taste of the tobacco processed product, etc. The fuzzy clustering method is used for classifying the tobacco processed products, so that conditions can be provided for tobacco product processing. And calculating a membership matrix of the quality parameter data set by using a fuzzy clustering algorithm, wherein the greater the membership, the more obvious and fine classification effect of the tobacco processed products is proved. The iterative algorithm can reduce the classification errors, so that the classification errors are converged, when the iteration times reach a preset value, the evaluation value of the iterative effect under ideal conditions is in an ideal state, and if the evaluation value of the iterative effect under the current iteration times is not in the preset value range, the current classification effect is poor, and the iterative calculation needs to be continued. In the membership matrix, the center of the membership matrix is a clustering center, the Euclidean distance is the distance between the quality detection parameter data points and the clustering center point, and when the Euclidean distance between the two points is within a preset value, the similarity between the two points is proved to meet the preset value, the iterative computation can be stopped, and the optimal iterative analysis result is output. And obtaining the types of the tobacco processing products required by different tobacco products and the number of the types of the tobacco processing products required by a single tobacco product according to the optimal iterative analysis result. The invention can classify the types of tobacco processed products through a fuzzy clustering algorithm and an iterative algorithm.
Further, in a preferred embodiment of the present invention, the method for packaging a tobacco processed product by a tobacco production facility to obtain a tobacco product, performing a packaging state analysis on the tobacco product, and repairing a defect of the tobacco product based on the analysis result comprises:
based on the tobacco production order information and the historical data information, obtaining appearance parameters and weight parameters of a single tobacco product, combining the types and the amounts of tobacco processed products required by the single tobacco product, and introducing a convolutional neural network model to perform prediction processing to obtain packaging working parameters;
the tobacco production facility packages the tobacco processed products based on the packaging working parameters to obtain initial tobacco products, and obtains appearance parameters and weight parameters of all the initial tobacco products;
the appearance parameters of the initial tobacco products comprise the package color and the size of the initial tobacco products, the color difference value of the package color of the initial tobacco products and the standard package color is obtained, and when the color difference value is larger than a preset value, the corresponding initial tobacco products are defined as abnormal-color tobacco products;
detecting the humidity of the abnormal color tobacco products by using a humidity sensor, if the humidity parameter of the abnormal color tobacco products is larger than a preset value, baking the corresponding abnormal color tobacco products until the humidity parameter reaches the preset value, and the color difference value between the packaging color and the standard packaging color meets the preset value;
When the humidity parameter of the abnormal color tobacco product is in a preset range, but the color difference value between the packaging color and the standard packaging color is larger than a preset value, defining the corresponding abnormal color tobacco product as a waste tobacco product, and defining all the rest initial tobacco products as tobacco products with weight to be detected;
and analyzing the weight parameters of the weight to-be-detected tobacco products, repackaging the weight to-be-detected tobacco products with the weight parameters not within the preset range, and defining the weight to-be-detected tobacco products with the weight parameters within the preset range as qualified tobacco products.
It should be noted that different tobacco products have different appearances and weights, and different types and numbers of tobacco products are required, so that different packaging methods are required for distinguishing different tobacco products. The convolutional neural network is used for predicting various parameters of tobacco products, so that packaging working parameters can be generated, and the tobacco production facility can be controlled to automatically package tobacco processed products by inputting the packaging working parameters to obtain initial tobacco products. If the appearance color of the initial tobacco product is not consistent with the preset value, judging that the initial tobacco product is likely to change color due to moisture, acquiring humidity parameters of the initial tobacco product, and if the humidity parameters are larger than the preset value, proving that the corresponding tobacco product is moist, and performing operations of baking, heating and the like to evaporate the moisture of the tobacco until the humidity parameters are normal. The humidity parameter is normal, the packaging color of the tobacco product in an ideal state should be a normal value, if the initial tobacco product is free from the damp condition and the color is still abnormal, the initial tobacco product is judged to be polluted by the outside, the color is possibly changed due to the pollution of plant diseases and insect pests, or the oil stain of a tobacco production machine affects the color of the initial tobacco product, and the initial tobacco product needs to be abandoned. Because the weight parameters of the tobacco products have specification requirements, the weight parameters of the tobacco products to be detected need to be detected, the tobacco products to be detected, which do not meet the specification, are repackaged, and finally the qualified tobacco products are obtained. The invention can obtain the qualified tobacco product by detecting the appearance and the weight of the packaged initial tobacco product and repairing and optimizing the initial tobacco product which does not meet the requirements.
Fig. 2 shows a flow chart illustrating intelligent regulation of real-time processing parameters of a tobacco production facility, comprising the steps of:
s202: processing tobacco based on the tobacco processing step, and acquiring abnormal operation time of a tobacco production facility;
s204: detecting the tobacco quality of the two types of tobacco to be detected, generating a tobacco quality detection result, and tracing the defect position of the tobacco production facility based on the tobacco quality detection result;
s206: combining the defect position of the tobacco production facility with the abnormal processing parameters, introducing a convolutional neural network to generate repairing processing parameters, and repairing the tobacco by using the tobacco production facility to obtain a tobacco processed product.
Further, in a preferred embodiment of the present invention, the processing of tobacco based on the tobacco processing step and obtaining abnormal operation time of the tobacco production facility specifically includes:
acquiring production elements of tobacco based on big data retrieval, and acquiring a tobacco processing step based on the production elements of tobacco;
placing the processable tobacco in a tobacco production facility, and introducing the tobacco processing step into a control center of the tobacco production facility, wherein the control center of the tobacco production facility generates processing parameters according to the tobacco processing step, and the control center of the tobacco production facility controls the tobacco production facility to process the processable tobacco based on the processing parameters;
Real-time monitoring is carried out on the processing parameters, the real-time processing parameters are obtained in the control center, if the real-time processing parameters are not in the preset range, the corresponding real-time processing parameters are defined as abnormal processing parameters, and the running time of the tobacco production parameters under the abnormal processing parameters is obtained and defined as abnormal running time.
The tobacco is processed after being planted and picked, and a tobacco processed product is obtained. The tobacco is processed by different steps including airing, baking, fermenting, cutting, mixing and the like. According to the tobacco processing steps, the processable tobacco is placed in a tobacco production facility, and the tobacco production facility is controlled by a control center to process the tobacco. During processing, tobacco processing facilities are prone to problems such as reduced cut rates, reduced cut forces, higher or lower baking temperatures, etc. Real-time monitoring is needed to be carried out on the processing parameters to obtain real-time processing parameters, and the real-time processing parameters which are not in a preset range are defined as abnormal processing parameters. Under abnormal processing parameters, the tobacco processing effect of the tobacco production facility is changed, and the abnormal operation time is defined in the period.
Further, in a preferred embodiment of the present invention, the detecting of tobacco quality of the second class of tobacco to be detected generates a tobacco quality detection result, and tracing the defect position of the tobacco production facility based on the tobacco quality detection result, specifically:
acquiring surface parameters of a class II to-be-detected tobacco, and constructing a class II to-be-detected tobacco three-dimensional model based on the surface parameters of the class II to-be-detected tobacco;
acquiring state parameters of the two types of tobacco to be detected based on the two types of tobacco to be detected three-dimensional model, acquiring preset state parameters of the two types of tobacco to be detected based on big data retrieval, and calculating a deviation value between the state parameters of the two types of tobacco to be detected and the preset state parameters, wherein the deviation value is defined as a state parameter deviation value;
constructing a time sequence, and combining the state parameter deviation value and the abnormal processing parameter to generate a state parameter deviation value and an abnormal processing parameter based on the time sequence;
introducing a Markov chain algorithm, and performing state transition probability calculation on the state parameter deviation value and the abnormal processing parameter based on the time sequence to obtain fault state transition probability values of tobacco production facilities under different time sequences;
Based on the fault state transition probability values of the tobacco production facilities under the different time sequences, a fault state probability table is generated, the fault state probability table is analyzed, and the fault state probability table is imported into a Bayesian network for training, so that the defect positions of the tobacco production facilities are obtained.
It should be noted that the second type of tobacco to be detected is tobacco processed under abnormal operation time. The method comprises the steps of analyzing surface parameters of two kinds of tobacco to be detected, obtaining state parameters of the two kinds of tobacco to be detected, and forming various defects of tobacco production facilities, wherein the two kinds of tobacco to be detected possibly have poor processing effect, the two kinds of tobacco to be detected can be formed by various reasons, a Markov chain algorithm can be used for obtaining probability values of the tobacco production facilities, obtaining a fault state probability table, and carrying out fault inversion reasoning by combining a Bayesian network, so that the defect positions of the tobacco production facilities are obtained. The invention can analyze the abnormal working parameters of the tobacco production facility by introducing a Markov chain algorithm and a Bayesian network to acquire the defect position of the tobacco production facility.
In addition, the tobacco production facility management method based on the Internet of things further comprises the following steps:
The tobacco production facility monitors the yield of qualified tobacco products in real time, and if the yield of one batch of qualified tobacco products does not meet a preset value, all the unprocessed tobacco of the same batch of qualified tobacco products are obtained and defined as tobacco to be repaired;
sampling the surface diseases and insect pests of the tobacco to be repaired, analyzing the surface diseases and insect pests to obtain the types and the concentrations of the surface diseases and insect pests of the tobacco to be repaired, and acquiring a surface disease and insect pest treatment method of the tobacco to be repaired according to the types and the concentrations of the surface diseases and insect pests of the tobacco to be repaired by combining with big data retrieval;
after the surface disease and pest treatment method of the tobacco to be repaired is used, judging the surface disease and pest condition of the tobacco to be repaired again, and if the severity of the surface disease and pest condition is still greater than a preset degree, controlling a tobacco production facility to cut and remove the part of the surface of the tobacco to be repaired, wherein the rest tobacco to be repaired is repaired tobacco;
processing and packaging the repaired tobacco to obtain a qualified tobacco product, and if the yield of the qualified tobacco product still does not meet a preset value at the moment, acquiring real-time processing parameters and packaging working parameters of the current tobacco production facility;
The method comprises the steps of importing real-time processing parameters and packaging working parameters of a current tobacco production facility into a big data network to find a parameter optimization scheme, screening to obtain an optimal optimization scheme based on optimization properties, optimization efficiency and optimization effects, and importing the optimal optimization scheme into the tobacco production facility to perform parameter optimization of the real-time processing parameters and the packaging working parameters.
If the yield of the qualified tobacco products in the same batch is not more than the set yield, the tobacco raw materials in the same batch are required to be further processed, the unprocessed tobacco is fully utilized, and the plant diseases and insect pests are repaired according to the requirement, so that the yield of the qualified tobacco products is increased. If the yield of the qualified tobacco products is still smaller, judging that the working efficiency of the tobacco production facility is problematic, and improving the working efficiency of the tobacco production facility is needed, wherein the working efficiency of the tobacco production facility can be improved by searching the optimal optimization scheme in the big data network.
In addition, the tobacco production facility management method based on the Internet of things further comprises the following steps:
acquiring a preset delivery time of the tobacco product based on the tobacco production order information;
Searching all correction schemes of the defect positions of the tobacco production facilities in a big data network, constructing a correction scheme set, and acquiring correction scheme output meeting the highest correction efficiency and the highest correction property in the correction scheme set, wherein the correction scheme output meets the correction property, and the correction scheme is defined as the optimal defect correction scheme of the tobacco production facilities;
performing defect repair on the tobacco production facilities based on the optimal tobacco production facility defect correction scheme, and obtaining defect repair time;
acquiring processing time of processable tobacco and packaging time of tobacco processed products, acquiring environmental parameters around tobacco processing facilities, and generating a data set by combining defect repair time;
introducing a Monte Carlo simulation model, introducing the data set into the Monte Carlo simulation model, generating a large number of sample values, carrying out statistical analysis on all the sample values, and outputting the production time of the tobacco product, wherein the statistical analysis comprises calculating the average value, variance and confidence interval of the samples;
and if the production time of the tobacco product is longer than the preset delivery time of the tobacco product, executing processing steps corresponding to the defect positions by using other good-performance tobacco production facilities during defect repair of the tobacco production facilities.
It should be noted that, the tobacco production order information includes a preset delivery time of the tobacco product, and economic losses are caused by delivering the product outside the preset delivery time of the tobacco product, so that the tobacco product production time needs to be obtained, thereby improving the production and delivery efficiency of the tobacco product. Obtaining the defect repair time after obtaining the optimal defect repair scheme of the tobacco production facility. Because the environment may affect the production of tobacco during the production of tobacco products, such as rainy and humid weather, which may result in a longer curing time of tobacco, it is desirable to combine the environmental parameters surrounding the tobacco processing facility with the processing time of the processable tobacco and the packaging time of the tobacco processed product to generate a data set. The Monte Carlo simulation method can consider the influence of different factors on the production time of the tobacco products, and simulate the distribution of the production time of the tobacco products for a plurality of times by using a random sampling sample method to obtain an estimated value. If the tobacco product production time is greater than the predetermined delivery time for the tobacco product, then other tobacco production facilities are used to perform the corresponding processing steps during the repair of the defective location in order to fulfill the delivery order to the customer during the delivery time. The invention can preset the delivery time and the production time of the tobacco products and can formulate the optimal production scheme.
As shown in fig. 3, the second aspect of the present invention further provides a tobacco production facility management system based on the internet of things, where the production facility management system includes a memory 31 and a processor 32, where the memory 31 stores a tobacco production facility management method based on the internet of things, and when the tobacco production facility management method based on the internet of things is executed by the processor 32, the following steps are implemented:
observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
and packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, analyzing the packaging state of the tobacco product, and repairing the defect of the tobacco product based on an analysis result.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (4)
1. The tobacco production facility management method based on the Internet of things is characterized by comprising the following steps of:
observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, carrying out packaging state analysis on the tobacco product, and carrying out defect repair on the tobacco product based on an analysis result;
The method comprises the steps of observing the growth condition of tobacco in a tobacco planting area, regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco, and specifically comprises the following steps:
acquiring a real-time image of a tobacco planting area by using a camera, and performing image preprocessing on the real-time image of the tobacco planting area, wherein the image preprocessing comprises gray processing and noise reduction processing on the image to obtain a preprocessed tobacco planting area image;
extracting features of the preprocessed tobacco planting area image to obtain surface feature parameters of each tobacco in the tobacco planting area, constructing a tobacco surface model based on the surface feature parameters of each tobacco in the tobacco planting area, and constructing a tobacco surface standard model based on historical data retrieval;
analyzing the tobacco surface model to obtain the real-time growth condition of tobacco, wherein the real-time growth condition of the tobacco comprises the color, the size and the surface pest and disease damage degree of the tobacco, and obtaining the standard growth condition of the tobacco based on the tobacco surface standard model;
comparing and analyzing the real-time growth condition of the tobacco with the standard growth condition of the tobacco to obtain a tobacco growth deviation value, defining the tobacco with the tobacco growth deviation value within a preset range as processable tobacco, and defining the tobacco with the tobacco growth deviation value outside the preset range as tobacco to be detected;
Analyzing the surface pest and disease damage degree in the real-time growth condition of the tobacco to be detected, dividing the tobacco to be detected with the surface pest and disease damage degree larger than the preset degree into non-processable tobacco, and guiding the real-time growth condition of the rest of the tobacco to be detected into a tobacco cultivation control center, wherein the tobacco cultivation control center regulates and controls the growth condition of the tobacco planting area where the rest of the tobacco to be detected is located in real time through the Internet of things;
the tobacco processing step is obtained based on production elements, the tobacco processing facility processes processable tobacco based on the tobacco processing step, and the real-time processing parameters of the tobacco processing facility are intelligently regulated and controlled in the processing process, specifically:
acquiring production elements of tobacco based on big data retrieval, and acquiring a tobacco processing step based on the production elements of tobacco;
placing the processable tobacco in a tobacco production facility, and introducing the tobacco processing step into a control center of the tobacco production facility, wherein the control center of the tobacco production facility generates processing parameters according to the tobacco processing step, and the control center of the tobacco production facility controls the tobacco production facility to process the processable tobacco based on the processing parameters;
Real-time monitoring is carried out on the processing parameters, the real-time processing parameters are obtained in a control center, if the real-time processing parameters are not in a preset range, the corresponding real-time processing parameters are defined as abnormal processing parameters, and the running time of the tobacco production parameters under the abnormal processing parameters is obtained and defined as abnormal running time;
tobacco processed in abnormal operation time is obtained, the tobacco is defined as two types of tobacco to be detected, tobacco quality detection is carried out on the two types of tobacco to be detected, a tobacco quality detection result is generated, and defect position tracing is carried out on tobacco production facilities based on the tobacco quality detection result;
combining the defect positions of the tobacco production facilities with the abnormal processing parameters to obtain processing parameters of each defect position, and introducing the tobacco quality detection result and the processing parameters of each defect position into a convolutional neural network to generate repair processing parameters;
the tobacco production facility carries out tobacco restoration treatment on the two types of tobacco to be detected based on restoration processing parameters to obtain restored tobacco, mixes the restored tobacco with other processable tobacco, and carries out tobacco processing treatment on the mixed tobacco by using the tobacco production facility under standard processing parameters to obtain a tobacco processed product;
The method comprises the steps of detecting the tobacco quality of two types of tobacco to be detected, generating a tobacco quality detection result, and tracing the defect position of a tobacco production facility based on the tobacco quality detection result, wherein the method specifically comprises the following steps:
acquiring surface parameters of a class II to-be-detected tobacco, and constructing a class II to-be-detected tobacco three-dimensional model based on the surface parameters of the class II to-be-detected tobacco;
acquiring state parameters of the two types of tobacco to be detected based on the two types of tobacco to be detected three-dimensional model, acquiring preset state parameters of the two types of tobacco to be detected based on big data retrieval, and calculating a deviation value between the state parameters of the two types of tobacco to be detected and the preset state parameters, wherein the deviation value is defined as a state parameter deviation value;
constructing a time sequence, and combining the state parameter deviation value and the abnormal processing parameter to generate a state parameter deviation value and an abnormal processing parameter based on the time sequence;
introducing a Markov chain algorithm, and performing state transition probability calculation on the state parameter deviation value and the abnormal processing parameter based on the time sequence to obtain fault state transition probability values of tobacco production facilities under different time sequences;
based on the fault state transition probability values of the tobacco production facilities under the different time sequences, a fault state probability table is generated, the fault state probability table is analyzed, and the fault state probability table is imported into a Bayesian network for training, so that the defect positions of the tobacco production facilities are obtained.
2. The method for managing tobacco production facilities based on the internet of things according to claim 1, wherein the tobacco products are classified by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco products, so as to obtain the number of tobacco processing varieties required by a single tobacco product, specifically comprising:
acquiring tobacco production order information, and acquiring the number of different tobacco products based on the tobacco production order information;
based on the tobacco production facility, acquiring quality detection parameters of all tobacco processed products, generating a quality parameter data set, initializing the quality parameter data set, and introducing a fuzzy clustering algorithm to acquire a membership matrix of the quality parameter data set;
carrying out iterative updating on the membership matrix by an iterative algorithm and presetting iterative times;
stopping iteration updating when the iteration times reach a preset value to obtain an initial iteration analysis result, and evaluating the initial iteration analysis result through a fuzzy coefficient in a fuzzy clustering algorithm to generate an evaluation value;
if the evaluation value is not in the range of the preset value, carrying out iteration updating again by using an iteration algorithm, and stopping iteration updating and outputting an optimal iteration analysis result when the Euclidean distance between each quality detection parameter data point in the membership matrix and the center of the membership matrix reaches the preset value;
If the evaluation value is within the range of the preset value, the initial iteration analysis result is used as the optimal iteration analysis output;
introducing the optimal iterative analysis result into a tobacco production facility, classifying tobacco processed products, and obtaining the types of the tobacco processed products required by different tobacco products;
and analyzing the quantity of the different tobacco products and the types of the tobacco processed products required by the different tobacco products to obtain the types and the quantities of the tobacco processed products required by the single tobacco product.
3. The method for managing a tobacco production facility based on the internet of things according to claim 1, wherein the method for packaging a tobacco processed product by a tobacco production facility to obtain a tobacco product, performing a packaging state analysis on the tobacco product, and performing defect repair on the tobacco product based on an analysis result comprises the following steps:
based on the tobacco production order information and the historical data information, obtaining appearance parameters and weight parameters of a single tobacco product, combining the types and the amounts of tobacco processed products required by the single tobacco product, and introducing a convolutional neural network model to perform prediction processing to obtain packaging working parameters;
the tobacco production facility packages the tobacco processed products based on the packaging working parameters to obtain initial tobacco products, and obtains appearance parameters and weight parameters of all the initial tobacco products;
The appearance parameters of the initial tobacco products comprise the package color and the size of the initial tobacco products, the color difference value of the package color of the initial tobacco products and the standard package color is obtained, and when the color difference value is larger than a preset value, the corresponding initial tobacco products are defined as abnormal-color tobacco products;
detecting the humidity of the abnormal color tobacco products by using a humidity sensor, if the humidity parameter of the abnormal color tobacco products is larger than a preset value, baking the corresponding abnormal color tobacco products until the humidity parameter reaches the preset value, and the color difference value between the packaging color and the standard packaging color meets the preset value;
when the humidity parameter of the abnormal color tobacco product is in a preset range, but the color difference value between the packaging color and the standard packaging color is larger than a preset value, defining the corresponding abnormal color tobacco product as a waste tobacco product, and defining all the rest initial tobacco products as tobacco products with weight to be detected;
and analyzing the weight parameters of the weight to-be-detected tobacco products, repackaging the weight to-be-detected tobacco products with the weight parameters not within the preset range, and defining the weight to-be-detected tobacco products with the weight parameters within the preset range as qualified tobacco products.
4. The tobacco production facility management system based on the Internet of things is characterized by comprising a memory and a processor, wherein the memory stores a tobacco production facility management method based on the Internet of things, and when the tobacco production facility management method based on the Internet of things is executed by the processor, the following steps are realized:
observing the growth condition of tobacco in the tobacco planting area, and regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco;
acquiring a tobacco processing step based on production elements, processing processable tobacco by a tobacco production facility based on the tobacco processing step, and intelligently regulating and controlling real-time processing parameters of the tobacco production facility in the processing process;
classifying the tobacco processed products by using a fuzzy clustering algorithm based on tobacco production order information and quality detection parameters of the tobacco processed products to obtain the number of tobacco processed varieties required by a single tobacco product;
packaging the tobacco processed product through a tobacco production facility to obtain a tobacco product, carrying out packaging state analysis on the tobacco product, and carrying out defect repair on the tobacco product based on an analysis result;
The method comprises the steps of observing the growth condition of tobacco in a tobacco planting area, regulating and controlling the growth condition of the tobacco based on the growth condition of the tobacco, and specifically comprises the following steps:
acquiring a real-time image of a tobacco planting area by using a camera, and performing image preprocessing on the real-time image of the tobacco planting area, wherein the image preprocessing comprises gray processing and noise reduction processing on the image to obtain a preprocessed tobacco planting area image;
extracting features of the preprocessed tobacco planting area image to obtain surface feature parameters of each tobacco in the tobacco planting area, constructing a tobacco surface model based on the surface feature parameters of each tobacco in the tobacco planting area, and constructing a tobacco surface standard model based on historical data retrieval;
analyzing the tobacco surface model to obtain the real-time growth condition of tobacco, wherein the real-time growth condition of the tobacco comprises the color, the size and the surface pest and disease damage degree of the tobacco, and obtaining the standard growth condition of the tobacco based on the tobacco surface standard model;
comparing and analyzing the real-time growth condition of the tobacco with the standard growth condition of the tobacco to obtain a tobacco growth deviation value, defining the tobacco with the tobacco growth deviation value within a preset range as processable tobacco, and defining the tobacco with the tobacco growth deviation value outside the preset range as tobacco to be detected;
Analyzing the surface pest and disease damage degree in the real-time growth condition of the tobacco to be detected, dividing the tobacco to be detected with the surface pest and disease damage degree larger than the preset degree into non-processable tobacco, and guiding the real-time growth condition of the rest of the tobacco to be detected into a tobacco cultivation control center, wherein the tobacco cultivation control center regulates and controls the growth condition of the tobacco planting area where the rest of the tobacco to be detected is located in real time through the Internet of things;
the tobacco processing step is obtained based on production elements, the tobacco processing facility processes processable tobacco based on the tobacco processing step, and the real-time processing parameters of the tobacco processing facility are intelligently regulated and controlled in the processing process, specifically:
acquiring production elements of tobacco based on big data retrieval, and acquiring a tobacco processing step based on the production elements of tobacco;
placing the processable tobacco in a tobacco production facility, and introducing the tobacco processing step into a control center of the tobacco production facility, wherein the control center of the tobacco production facility generates processing parameters according to the tobacco processing step, and the control center of the tobacco production facility controls the tobacco production facility to process the processable tobacco based on the processing parameters;
Real-time monitoring is carried out on the processing parameters, the real-time processing parameters are obtained in a control center, if the real-time processing parameters are not in a preset range, the corresponding real-time processing parameters are defined as abnormal processing parameters, and the running time of the tobacco production parameters under the abnormal processing parameters is obtained and defined as abnormal running time;
tobacco processed in abnormal operation time is obtained, the tobacco is defined as two types of tobacco to be detected, tobacco quality detection is carried out on the two types of tobacco to be detected, a tobacco quality detection result is generated, and defect position tracing is carried out on tobacco production facilities based on the tobacco quality detection result;
combining the defect positions of the tobacco production facilities with the abnormal processing parameters to obtain processing parameters of each defect position, and introducing the tobacco quality detection result and the processing parameters of each defect position into a convolutional neural network to generate repair processing parameters;
the tobacco production facility carries out tobacco restoration treatment on the two types of tobacco to be detected based on restoration processing parameters to obtain restored tobacco, mixes the restored tobacco with other processable tobacco, and carries out tobacco processing treatment on the mixed tobacco by using the tobacco production facility under standard processing parameters to obtain a tobacco processed product;
The method comprises the steps of detecting the tobacco quality of two types of tobacco to be detected, generating a tobacco quality detection result, and tracing the defect position of a tobacco production facility based on the tobacco quality detection result, wherein the method specifically comprises the following steps:
acquiring surface parameters of a class II to-be-detected tobacco, and constructing a class II to-be-detected tobacco three-dimensional model based on the surface parameters of the class II to-be-detected tobacco;
acquiring state parameters of the two types of tobacco to be detected based on the two types of tobacco to be detected three-dimensional model, acquiring preset state parameters of the two types of tobacco to be detected based on big data retrieval, and calculating a deviation value between the state parameters of the two types of tobacco to be detected and the preset state parameters, wherein the deviation value is defined as a state parameter deviation value;
constructing a time sequence, and combining the state parameter deviation value and the abnormal processing parameter to generate a state parameter deviation value and an abnormal processing parameter based on the time sequence;
introducing a Markov chain algorithm, and performing state transition probability calculation on the state parameter deviation value and the abnormal processing parameter based on the time sequence to obtain fault state transition probability values of tobacco production facilities under different time sequences;
based on the fault state transition probability values of the tobacco production facilities under the different time sequences, a fault state probability table is generated, the fault state probability table is analyzed, and the fault state probability table is imported into a Bayesian network for training, so that the defect positions of the tobacco production facilities are obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311639266.6A CN117351292B (en) | 2023-12-04 | 2023-12-04 | Tobacco production facility management method and system based on Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311639266.6A CN117351292B (en) | 2023-12-04 | 2023-12-04 | Tobacco production facility management method and system based on Internet of things |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117351292A CN117351292A (en) | 2024-01-05 |
CN117351292B true CN117351292B (en) | 2024-03-08 |
Family
ID=89371362
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311639266.6A Active CN117351292B (en) | 2023-12-04 | 2023-12-04 | Tobacco production facility management method and system based on Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117351292B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101690451A (en) * | 2009-09-18 | 2010-04-07 | 安徽省农业科学院烟草研究所 | Ralstonia solanacearum disease resistance high density identification method in field |
CN103955834A (en) * | 2013-12-24 | 2014-07-30 | 南宁眸博科技有限公司 | Agricultural-product source tracing device based on Internet of Things |
CN105516663A (en) * | 2015-12-11 | 2016-04-20 | 卢志文 | Plant wall growth situation monitoring system |
CN107133860A (en) * | 2017-06-08 | 2017-09-05 | 武汉轻工大学 | Green and healthy consumption system of tracing to the source based on Internet of Things |
CN108958330A (en) * | 2018-05-24 | 2018-12-07 | 山东百家兴农业科技股份有限公司 | One kind being used for greenhouse corps growth of seedling monitoring device |
CN109242248A (en) * | 2018-08-02 | 2019-01-18 | 山东中烟工业有限责任公司 | Cigarette machine multidimensional data comprehensive analysis platform and method |
CN111652756A (en) * | 2020-07-03 | 2020-09-11 | 张玉红 | Green wisdom green house planting environment monitoring management system |
CN111721719A (en) * | 2020-06-30 | 2020-09-29 | 詹晨 | Give birth to bright commodity safety intellectual detection system management system based on big data |
CN112579807A (en) * | 2020-12-18 | 2021-03-30 | 杭州宣迅电子科技有限公司 | Smart agriculture full-period planting data cloud sharing platform based on cloud computing and big data analysis |
CN112749627A (en) * | 2020-12-09 | 2021-05-04 | 北京星衡科技有限公司 | Method and device for dynamically monitoring tobacco based on multi-source remote sensing image |
CN112801246A (en) * | 2021-01-26 | 2021-05-14 | 厦门海晟融创信息技术有限公司 | Tobacco big data tracking platform under internet of things connection |
JP2021143865A (en) * | 2020-03-10 | 2021-09-24 | 信越ポリマー株式会社 | Quality determination method for packaging roll body |
CN113589772A (en) * | 2021-08-02 | 2021-11-02 | 武汉胜凯图文设计有限公司 | Intelligent operation regulation and control management system for packaging bag image-text printing production line |
CN113610851A (en) * | 2021-10-09 | 2021-11-05 | 武汉平桥兄弟包装材料有限公司 | Packaging decoration quality inspection method based on machine vision |
JP2022065917A (en) * | 2020-10-16 | 2022-04-28 | 元博 大塚 | Cigarette and tobacco package |
CN114609025A (en) * | 2022-03-11 | 2022-06-10 | 云南中烟工业有限责任公司 | Method for detecting color fastness to light of cigarette packaging paper |
CN116797601A (en) * | 2023-08-24 | 2023-09-22 | 西南林业大学 | Image recognition-based Huashansong growth dynamic monitoring method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170098137A1 (en) * | 2012-08-08 | 2017-04-06 | Scanadu Incorporated | Method, apparatus and system for detecting and determining compromised reagent pads by quantifying color changes induced by exposure to a hostile environment |
-
2023
- 2023-12-04 CN CN202311639266.6A patent/CN117351292B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101690451A (en) * | 2009-09-18 | 2010-04-07 | 安徽省农业科学院烟草研究所 | Ralstonia solanacearum disease resistance high density identification method in field |
CN103955834A (en) * | 2013-12-24 | 2014-07-30 | 南宁眸博科技有限公司 | Agricultural-product source tracing device based on Internet of Things |
CN105516663A (en) * | 2015-12-11 | 2016-04-20 | 卢志文 | Plant wall growth situation monitoring system |
CN107133860A (en) * | 2017-06-08 | 2017-09-05 | 武汉轻工大学 | Green and healthy consumption system of tracing to the source based on Internet of Things |
CN108958330A (en) * | 2018-05-24 | 2018-12-07 | 山东百家兴农业科技股份有限公司 | One kind being used for greenhouse corps growth of seedling monitoring device |
CN109242248A (en) * | 2018-08-02 | 2019-01-18 | 山东中烟工业有限责任公司 | Cigarette machine multidimensional data comprehensive analysis platform and method |
JP2021143865A (en) * | 2020-03-10 | 2021-09-24 | 信越ポリマー株式会社 | Quality determination method for packaging roll body |
CN111721719A (en) * | 2020-06-30 | 2020-09-29 | 詹晨 | Give birth to bright commodity safety intellectual detection system management system based on big data |
CN111652756A (en) * | 2020-07-03 | 2020-09-11 | 张玉红 | Green wisdom green house planting environment monitoring management system |
JP2022065917A (en) * | 2020-10-16 | 2022-04-28 | 元博 大塚 | Cigarette and tobacco package |
CN112749627A (en) * | 2020-12-09 | 2021-05-04 | 北京星衡科技有限公司 | Method and device for dynamically monitoring tobacco based on multi-source remote sensing image |
CN112579807A (en) * | 2020-12-18 | 2021-03-30 | 杭州宣迅电子科技有限公司 | Smart agriculture full-period planting data cloud sharing platform based on cloud computing and big data analysis |
CN112801246A (en) * | 2021-01-26 | 2021-05-14 | 厦门海晟融创信息技术有限公司 | Tobacco big data tracking platform under internet of things connection |
CN113589772A (en) * | 2021-08-02 | 2021-11-02 | 武汉胜凯图文设计有限公司 | Intelligent operation regulation and control management system for packaging bag image-text printing production line |
CN113610851A (en) * | 2021-10-09 | 2021-11-05 | 武汉平桥兄弟包装材料有限公司 | Packaging decoration quality inspection method based on machine vision |
CN114609025A (en) * | 2022-03-11 | 2022-06-10 | 云南中烟工业有限责任公司 | Method for detecting color fastness to light of cigarette packaging paper |
CN116797601A (en) * | 2023-08-24 | 2023-09-22 | 西南林业大学 | Image recognition-based Huashansong growth dynamic monitoring method and system |
Non-Patent Citations (2)
Title |
---|
吴陈等.《模式识别》.机械工业出版社,2020,第231-236页. * |
基于智能传感器技术的卷烟包装质量在线检测***设计;高春芳;《装备制造技术》(第7期);第227-229、237页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117351292A (en) | 2024-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108090628A (en) | A kind of grain feelings security detection and analysis method based on PSO-LSSVM algorithms | |
CN111950795A (en) | Random forest based method for predicting water adding proportion of loosening and conditioning | |
CN105334738B (en) | A kind of method of evaluating performance suitable for tobacco processing course pid control circuit | |
CN115860581A (en) | Method, device, equipment and storage medium for evaluating suitability of crop variety | |
CN110308111B (en) | Method for rapidly predicting time for smoldering yellow tea by using near infrared spectrum technology | |
CN117351292B (en) | Tobacco production facility management method and system based on Internet of things | |
CN112352523A (en) | Tea garden water and fertilizer irrigation control method and system based on intelligent decision | |
CN111985728A (en) | Method for establishing organic sorghum yield prediction model | |
CN117033810A (en) | Agricultural data analysis management system and method based on big data | |
CN117296538B (en) | Green plant maintenance method, device and system based on vegetation soil component detection | |
CN111950166B (en) | Cost optimization method for household paper making machine based on data mining | |
CN116523149B (en) | Method and device for predicting appropriate period for preventing and controlling tiny pests, electronic equipment and storage medium | |
CN117455062A (en) | Crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
CN117575094A (en) | Crop yield prediction and optimization method and device based on digital twin | |
CN116228454A (en) | Big data-based planting management control method, system and readable storage medium | |
CN110320174B (en) | Method for rapidly predicting time for smoldering yellow tea by applying polynomial net structure artificial neural network | |
Yadav et al. | Crop disease prediction and solution | |
CN113029984A (en) | Soil monitoring method and device based on multi-channel spectral sensor | |
Jackson et al. | Robust Ensemble Machine Learning for Precision Agriculture | |
CN112633107A (en) | Intelligent forestry monitoring method, device, equipment and storage medium | |
CN117689489A (en) | Intelligent grape planting control system based on multidimensional monitoring | |
KR102575549B1 (en) | A Method for the Development of the optimal Crop Cultivation Recipe to Improve the Productivity of Smart Farms | |
CN112580703B (en) | Method for predicting morbidity of panax notoginseng in high-incidence stage | |
CN117295210B (en) | Intelligent power supply control method, system and storage medium based on agricultural illumination | |
CN110308110B (en) | Nondestructive prediction method for long-distance safe yellow tea yellow-smoldering time based on least square support vector machine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |