CN110009191A - A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm - Google Patents
A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm Download PDFInfo
- Publication number
- CN110009191A CN110009191A CN201910161363.6A CN201910161363A CN110009191A CN 110009191 A CN110009191 A CN 110009191A CN 201910161363 A CN201910161363 A CN 201910161363A CN 110009191 A CN110009191 A CN 110009191A
- Authority
- CN
- China
- Prior art keywords
- flue
- cured tobacco
- quality
- data
- decision
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a kind of, and the flue-cured tobacco based on genetic algorithm cultivates decision-making technique and system, the beneficial effects of the practice of the present invention is, the relevant data of flue-cured tobacco cultivation are obtained first from database, and the data got are pre-processed, and reject the abnormal data and Outlier Data in data；Then it is modeled using yield and quality of the artificial neural network to flue-cured tobacco, establishes flue-cured tobacco quality evaluation model；It finally uses genetic algorithm to establish using flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation as constraint condition, using the flue-cured tobacco quality evaluation model of foundation as fitness function, establishes using flue cured tobacco quality and yield as the Optimized model of target；The flue-cured tobacco that climatic environment, soil environment and expectation by giving flue-cured tobacco growing district reach cultivates target, and the yield and quality that cultivation step parameter is calculated and can achieve provides effective decision support for tobacco grower.
Description
Technical field
The present invention relates to flue-cured tobaccos to cultivate field, cultivates decision more specifically to a kind of flue-cured tobacco based on genetic algorithm
Method and system.
Background technique
Flue-cured tobacco is an important agricultural product in China industrial crops, has the characteristics that small investment and profit are high, in agricultural
It is occupied an important position in economy, international trade and fiscal revenues.Flue-cured tobacco is the crop that quality is laid equal stress on, and quality is by baking
Tobacco kind, ecological environment and the coefficient result of cultivation.Basis of the flue-cured tobacco cultivars as leaf tobacco production, by cultivating
The kind of merit can fundamentally improve the quality and benifit of tobacco leaf, but when breed of variety or quite long improvement needs
Between.Ecological environment includes climatic environment and soil environment, belongs to the intrinsic condition of cigarette district, is difficult to change in a short time.No
Be same as flue-cured tobacco cultivars and producing region ecological environment, the cultivation of flue-cured tobacco be it is flexibly controllable, can from planting density, leaves remained,
The various aspects such as dose are controlled to improve the quality and benifit of flue-cured tobacco.
Traditional flue-cured tobacco cultivates decision and tends to rely on the long-term cultivation experience of tobacco grower.But due to different cultivars flue-cured tobacco and
The difference of each department ecological condition causes tobacco grower to have biggish subjectivity in the decision of flue-cured tobacco cultivation and do not know
Property, so that flue-cured tobacco is unable to reach optimal comprehensive productive target in yield and quality.DSS can pass through model
It calculates, enumerate the modes such as possible scheme, provide help for the manager of agricultural production, at present the relevant DSS of flue-cured tobacco
The scheme of middle use is typically all to be calculated by model and compared with practical situation, provides feasible cultivation measure.This patent
Decision problem is cultivated for flue-cured tobacco, a kind of flue-cured tobacco based on genetic algorithm is proposed and cultivates DSS, which can be with
More reasonable flue-cured tobacco cultivating scheme is provided, for instructing cured tobacco production.
Summary of the invention
The technical problem to be solved in the present invention is that for maximize improve flue-cured tobacco cultivate quality, auxiliary tobacco grower into
The decision that row flue-cured tobacco is cultivated provides a kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm.
The technical solution adopted by the present invention to solve the technical problems is: constructing a kind of flue-cured tobacco cultivation based on genetic algorithm
Decision-making technique, specifically includes the following steps:
S1, the data that flue-cured tobacco cultivation is obtained from database；
S2, the data got are pre-processed, rejects the abnormal data and Outlier Data in data；
S3, using the pretreated data of step S2, built using yield and quality of the artificial neural network to flue-cured tobacco
Mould establishes yield of flue-cured tobacco, Environmental Evaluation Model respectively；
S4, genetic algorithm is used to establish using flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation as constraint condition, with step
The flue-cured tobacco quality evaluation model established in S3 is established as fitness function using flue cured tobacco quality and yield as the optimization of target
Model；By the Optimized model of foundation, the result that the flue-cured tobacco in best productive target cultivates decision support is acquired.
Further, the data that will acquire in step S1 are divided into influence factor data set I and quality and benifit evaluation index
Data set O；It wherein, include several influence factor indexs, the quality and benifit evaluation index in the influence factor data set I
It include several evaluation indexes in data set O.
Further, it is pre-processed, is rejected different in data using data of the DBSCAN algorithm to acquisition in step S2
Regular data and Outlier Data.
Further, in step S3, using with index and method, for each quality evaluation index data, flue cured tobacco quality is commented
Valence model is the stack combinations of every Environmental Evaluation Model；Wherein, the expression formula of index and method are as follows:
Wherein, YiIndicate the evaluation result of i-th of quality evaluation index, AiIndicate weight shared by i-th of evaluation index, Y
Indicate quality overall evaluation result；
The Yield evaluation model of flue-cured tobacco is Z=YN+1；Wherein, YN+1For the Yield evaluation result of flue-cured tobacco.
Further, solving the step of flue-cured tobacco cultivates decision support result by genetic algorithm in step S4 includes:
S41, the flue-cured tobacco cultivars to decision, the weather conditions X in flue-cured tobacco cultivation are obtained1, edaphic condition X2And it is expected
Cultivate target；The expected target of cultivating includes expected flue cured tobacco quality YtargetWith flue-cured tobacco per mu yield Ztarget。
S42, according to flue-cured tobacco quality evaluation model, establish flue cured tobacco quality fitness function f respectivelyYIt is suitable with yield of flue-cured tobacco
Response function fZ；
S43, according to the flue-cured tobacco cultivars to decision of acquisition, weather conditions X1, edaphic condition X2And expected cultivation target,
Data in database are screened, finds out and meets expected cultivate in historical data under the same ecological environment of current flue-cured tobacco cultivars
The cultivation measure of target, and establish population M primary0；
S44, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, to first
For population M0Individual carry out Fitness analysis, calculate separately and obtain population M primary0In each individual prospective quality and expection
Yield；
S45, it is expected cultivation target according to what is inputted in step S41, using genetic algorithm to population M primary0Selected,
After variation, calculated crosswise, formed and population M primary0Corresponding filial generation M1；
S46, step S44-S45 is repeated, and the number of iterations is defined as n times；After iteration n times, filial generation M is finally obtainedn；
S47, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, antithetical phrase
For MnCarry out Fitness analysis, and the population M primary being calculated in conjunction with step S440In each individual prospective quality and expection
Yield is found out under the basis for meeting target, filial generation MnMiddle prospective quality or the maximum individual of expected volume；By the individual
Final result as flue-cured tobacco cultivation decision support of cultivation parameter and expected flue-cured tobacco matter, yield.
Further, in population M primary0In the middle insufficient situation of individual amount, with flue-cured tobacco cultivars, weather conditions X1, soil
Condition X2With expected target of cultivating as edge-restraint condition；According to the edge-restraint condition, several individuals are generated at random,
Expand population M primary0Scale.
Further, the process of new population is calculated in step S45 using genetic algorithm are as follows: firstly, utilizing wheel disc
Gambling method is from population M primary0Middle selection constitutes several pairs of parents and female generation close to the expected individual for cultivating target；Secondly, passing through friendship
Fork probability coefficent successively intersects each pair of parent and female generation, obtain with each pair of parent and mother for it is corresponding it is several each and every one
Body；Finally, carrying out mutation operation to each of generation individual is intersected according to mutation probability coefficient, filial generation M is obtained1。
A kind of flue-cured tobacco based on genetic algorithm provided by the invention cultivates decision system, specifically includes:
Database module cultivates data for storing flue-cured tobacco, flue-cured tobacco cultivates evaluation model, flue-cured tobacco cultivates the result of decision；
Data acquisition module, for obtaining the relevant data of flue-cured tobacco cultivation from database module；
Data preprocessing module, for being pre-processed to the data got, reject abnormal data in data and from
Group's data；
Server background module for being packaged to module included by its inside, and utilizes computer programming language
Dynamic link library is written as to realize function that all modules for including inside it have；
Front-end interface module, for showing the data from server background module calls on the display device.
Further, server background module further includes that flue-cured tobacco quality modeling module and flue-cured tobacco cultivate decision-making module,
In:
Flue-cured tobacco quality modeling module is built for being modeled using yield and quality of the artificial neural network to flue-cured tobacco
Vertical flue-cured tobacco quality evaluation model；
Flue-cured tobacco cultivates decision-making module, for using genetic algorithm to establish with flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation
For constraint condition, using flue cured tobacco quality and yield as the Optimized model of target；Acquire the flue-cured tobacco training in best productive target
Plant the result of decision support.
Further, the more new function for periodically automatically updating model is also provided in server background module；Using roasting
When cigarette cultivates decision making function, the flue-cured tobacco evaluation model in flue-cured tobacco quality modeling module is called directly；Server background module
In, dynamic link library is write using C# language.
Cultivated in decision-making technique in a kind of flue-cured tobacco based on genetic algorithm of the present invention, use genetic algorithm to establish with
Flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation are constraint condition, using flue cured tobacco quality and yield as the Optimized model of target；It is logical
The flue-cured tobacco cultivation target that climatic environment, soil environment and the expectation of given flue-cured tobacco growing district reach is crossed, cultivation step ginseng is calculated
Number and the yield and quality that can achieve, provide effective decision support for tobacco grower.
Implement a kind of flue-cured tobacco based on genetic algorithm of the invention and cultivate decision-making technique and system, has below beneficial to effect
Fruit:
1, it is pre-processed by cultivating data to the flue-cured tobacco of acquisition, rejecting abnormalities data, establishes complete flue-cured tobacco and cultivate
The evaluation indexes database such as influence factor and yield and quality；
2, yield of flue-cured tobacco and Environmental Evaluation Model are designed, establishes model library according to the data in case library.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the method flow diagram that the flue-cured tobacco based on genetic algorithm cultivates decision；
Fig. 2 is the system construction drawing that the flue-cured tobacco based on genetic algorithm cultivates decision.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing is described in detail
A specific embodiment of the invention.
Referring to FIG. 1, its method flow diagram for cultivating decision for the flue-cured tobacco based on genetic algorithm, specifically includes following step
It is rapid:
S1, the data that flue-cured tobacco cultivation is obtained from database；Wherein, the data that will acquire in step S1 are divided into shadow
Ring factor data collection I and quality and benifit evaluation index data set O；In the influence factor data set I include several influence because
Plain index includes several evaluation indexes in the quality and benifit evaluation index data set O.
The data got are pre-processed using DBSCAN algorithm in S2, the present embodiment, reject the exception in data
Data and Outlier Data.
S3, using the pretreated data of step S2, built using yield and quality of the artificial neural network to flue-cured tobacco
Mould establishes yield of flue-cured tobacco, Environmental Evaluation Model respectively；In the present embodiment, using index and method, for each quality evaluation index
Data, quality evaluation of flue-cured tobacco model are the stack combinations of every Environmental Evaluation Model；Wherein, the expression formula of index and method are as follows:
Wherein, YiIndicate the evaluation result of i-th of quality evaluation index, AiIndicate weight shared by i-th of evaluation index, Y
Indicate quality overall evaluation result；
The Yield evaluation model of flue-cured tobacco is Z=YN+1；Wherein, YN+1For the Yield evaluation result of flue-cured tobacco.
In the present embodiment, for different quality evaluation index, weight setting are as follows:
Table 1
The evaluation model finally established can indicate are as follows:
Wherein, parameter X1、X2And X3Represent the influence of three flue-cured tobacco cultivation mesoclimate, soil and cultivation step parts
Factor value, f1() represents the relationship between flue-cured tobacco cultivation process influence factor and flue cured tobacco quality, f2() represents flue-cured tobacco cultivation mistake
Relationship between journey influence factor and yield of flue-cured tobacco.
S4, the evaluation model established according to step S42, in the present embodiment, decision support problem is converted are as follows: given flue-cured tobacco
The weather X in producing region1With soil environment X2, by flue-cured tobacco prospective quality Y value be 85, as 85 points；Using genetic algorithm, work as flue-cured tobacco
When prospective quality Y is close to 85, so that the expected volume Z of flue-cured tobacco reaches maximum value；Specific steps include are as follows:
S41, the flue-cured tobacco cultivars to decision, the weather conditions X in flue-cured tobacco cultivation are obtained1, edaphic condition X2And it is expected
Cultivate target；The expected target of cultivating includes expected flue cured tobacco quality YtargetWith flue-cured tobacco per mu yield Ztarget；It will in the present embodiment
It is expected that flue cured tobacco quality YtargetValue is 80；
S42, according to flue-cured tobacco quality evaluation model, establish flue cured tobacco quality fitness function f respectivelyYIt is suitable with yield of flue-cured tobacco
Response function fZ；
S43, according to the flue-cured tobacco cultivars to decision of acquisition, weather conditions X1, edaphic condition X2And expected cultivation target,
Data in database are screened, flue-cured tobacco prospective quality under the same ecological environment of current flue-cured tobacco cultivars is found out in historical data
The cultivation measure of about 85 timesharing, and establish population M primary0；Wherein, in population the information of individual record be flue-cured tobacco cultivation
Measure parameter X3；
If population M primary0Middle individual amount is insufficient, in the present embodiment, with flue-cured tobacco cultivars, weather conditions X1, edaphic condition X2
With expected target of cultivating as edge-restraint condition；According to the edge-restraint condition, several individuals are generated at random, further
Expand population M primary0Scale；
S44, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, to first
For population M0Individual carry out Fitness analysis, calculate separately and obtain population M primary0In each individual prospective quality and expection
Yield；
S45, according to the expection flue cured tobacco quality Y inputted in step S41target, in population M primary0In preferentially select expected matter
Measure the individual close to 80；Wherein, the process of individual is selected are as follows:
Firstly, considering that individual of the prospective quality between [80*0.95,80*1.05] utilizes roulette on this basis
Method selects M0Individual, constitute parent and female generation.If prospective quality between [80*0.95,80*1.05] individual quantity compared with
It is small, it will lead to selected parent and female generation repetition ratio be big, therefore when the less area Shi Zaijiang of individual amount for meeting above-mentioned section
Between be extended to [80*0.9,80*1.1]；Population M primary0Middle individual amount be m (m is even number, in the present embodiment m value be 60),
Then it may be constructed according to this methodTo the set of parent and female generation；
Secondly, successively being intersected to each pair of parent and female generation according to crossover probability coefficient, two filial generations are generated, finally may be used
To generate m individual；
Finally, mutation operation is carried out to each individual according to mutation probability coefficient, it is final to generate the filial generation with m individual
M1；In general, crossover probability is optional but is not limited to 0.8, and mutation probability is optional but is not limited to 0.05, and mutation probability is much smaller than handing over
Pitch probability.
S46, step S44-S45 is repeated, and the number of iterations is defined as n times；After iteration n times, filial generation M is finally obtainedn；
S47, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, antithetical phrase
For MnCarry out Fitness analysis, and the population M primary being calculated in conjunction with step S440In each individual prospective quality and expection
Yield is found out under the basis for meeting target, filial generation MnMiddle prospective quality or the maximum individual of expected volume；By the individual
Final result as flue-cured tobacco cultivation decision support of cultivation parameter and expected flue-cured tobacco matter, yield.
Referring to FIG. 2, its system construction drawing for cultivating decision for the flue-cured tobacco provided by the invention based on genetic algorithm, described
It includes database module L1, data acquisition module L2, data preprocessing module L3, server background mould that flue-cured tobacco, which cultivates decision system,
Block L4, front-end interface module L5；It wherein, further include flue-cured tobacco quality modeling module L41 and flue-cured tobacco in server background module L4
Decision-making module L42 is cultivated, the function of each module is illustrated below:
The database module L1 is used to store flue-cured tobacco cultivation data, flue-cured tobacco cultivates evaluation model, flue-cured tobacco cultivates decision
As a result；
The data acquisition module L2 is used to obtain the relevant data of flue-cured tobacco cultivation from database module；
The data preprocessing module L3 rejects the abnormal data in data for pre-processing to the data got
And Outlier Data；
The server background module L4 utilizes use for being packaged to module included by its inside in this implementation
C# language is written as dynamic link library to realize function that all modules for including inside it have；Wherein, flue-cured tobacco quality
Modeling module L41 establishes the evaluation of flue-cured tobacco quality for modeling using yield and quality of the artificial neural network to flue-cured tobacco
Model；Flue-cured tobacco cultivates decision-making module L42 for using genetic algorithm to establish with flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation
For constraint condition, using flue cured tobacco quality and yield as the Optimized model of target；Acquire the flue-cured tobacco training in best productive target
Plant the result of decision support；
The front-end interface module L5 is used to show the data from server background module calls on the display device.
It is last complete to each functional module successively design interface program after the exploitation for completing above-mentioned each functional module
At the integration of system.
During user operates in front-end interface, when needing that flue-cured tobacco is called to cultivate decision-making module, in server background
Flue-cured tobacco quality modeling module L41 and flue-cured tobacco cultivate the data in decision-making module L42 calling database module, are calculated
Result on the one hand be saved in database module, on the other hand by front-end interface completion calculated result echo.
By test, as shown in following table (flue-cured tobacco product are omitted here in the resulting result of decision of system that flue-cured tobacco cultivates decision
Parameters, the cultivation measures such as kind, flue-cured tobacco growing district climate and soil conditions only consider planting density, leaves remained and amount of nitrogen):
Table 2
Table 3
Wherein, after table 2 is cultivates decision system using flue-cured tobacco, in the case where inputting expected flue-cured tobacco cultivation target, system
The cultivation step and plantation provided is as a result, table 3 is the practical cultivation step and plantation result that expected flue-cured tobacco cultivates target；By system
After result and the actual result comparison obtained, it can be seen that the flue-cured tobacco, which cultivates decision, can cultivate target guaranteeing expected flue-cured tobacco
Meanwhile in the reasonable cultivation step that implementation system provides, the yield and quality of flue-cured tobacco can be further increased.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of flue-cured tobacco based on genetic algorithm cultivates decision-making technique, which is characterized in that specifically includes the following steps:
S1, the data that flue-cured tobacco cultivation is obtained from database；
S2, the data got are pre-processed, rejects the abnormal data and Outlier Data in data；
S3, using the pretreated data of step S2, modeled using yield and quality of the artificial neural network to flue-cured tobacco, point
Yield of flue-cured tobacco, Environmental Evaluation Model are not established；
S4, genetic algorithm is used to establish using flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation as constraint condition, in step S3
The flue-cured tobacco quality evaluation model of foundation is established as fitness function using flue cured tobacco quality and yield as the Optimized model of target；
By the Optimized model of foundation, the result that the flue-cured tobacco in best productive target cultivates decision support is acquired.
2. flue-cured tobacco according to claim 1 cultivates decision-making technique, which is characterized in that the data that will acquire in step S1 point
For influence factor data set I and quality and benifit evaluation index data set O；It wherein, include several in the influence factor data set I
Influence factor index includes several evaluation indexes in the quality and benifit evaluation index data set O.
3. flue-cured tobacco according to claim 1 cultivates decision-making technique, which is characterized in that utilize DBSCAN algorithm pair in step S2
The data of acquisition are pre-processed, and abnormal data and Outlier Data in data are rejected.
4. flue-cured tobacco according to claim 1 cultivates decision-making technique, which is characterized in that in step S3, using with index and method,
For each quality evaluation index data, quality evaluation of flue-cured tobacco model is the stack combinations of every Environmental Evaluation Model；Wherein, refer to
Several and method expression formula are as follows:
Wherein, YiIndicate the evaluation result of i-th of quality evaluation index, AiIndicate weight shared by i-th of evaluation index, Y is indicated
Quality overall evaluation result；
The Yield evaluation model of flue-cured tobacco is Z=YN+1；Wherein, YN+1For the Yield evaluation result of flue-cured tobacco.
5. flue-cured tobacco according to claim 1 cultivates decision-making technique, which is characterized in that solved in step S4 by genetic algorithm
Flue-cured tobacco cultivate decision support result the step of include:
S41, the flue-cured tobacco cultivars to decision, the weather conditions X in flue-cured tobacco cultivation are obtained1, edaphic condition X2And expected cultivation
Target；The expected target of cultivating includes expected flue cured tobacco quality YtargetWith flue-cured tobacco per mu yield Ztarget。
S42, according to flue-cured tobacco quality evaluation model, establish flue cured tobacco quality fitness function f respectivelyYWith yield of flue-cured tobacco fitness letter
Number fZ；
S43, according to the flue-cured tobacco cultivars to decision of acquisition, weather conditions X1, edaphic condition X2And expected cultivation target, logarithm
It is screened according to the data in library, finds out and meet expected cultivation target in historical data under the same ecological environment of current flue-cured tobacco cultivars
Cultivation measure, and establish population M primary0；
S44, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, to primary kind
Group M0Individual carry out Fitness analysis, calculate separately and obtain population M primary0In each individual prospective quality and expected volume；
S45, it is expected cultivation target according to what is inputted in step S41, using genetic algorithm to population M primary0Selected, made a variation,
After calculated crosswise, formed and population M primary0Corresponding filial generation M1；
S46, step S44-S45 is repeated, and the number of iterations is defined as n times；After iteration n times, filial generation M is finally obtainedn；
S47, the flue cured tobacco quality fitness function f established in step S42 is utilizedYWith yield of flue-cured tobacco fitness function fZ, to filial generation Mn
Carry out Fitness analysis, and the population M primary being calculated in conjunction with step S440In each individual prospective quality and expected produce
Amount, finds out under the basis for meeting target, filial generation MnMiddle prospective quality or the maximum individual of expected volume；By the individual
It cultivates parameter and expected flue-cured tobacco matter, yield cultivates the final result of decision support as flue-cured tobacco.
6. flue-cured tobacco according to claim 5 cultivates decision-making technique, which is characterized in that in population M primary0Middle individual amount is not
In the case where foot, with flue-cured tobacco cultivars, weather conditions X1, edaphic condition X2With expected target of cultivating as edge-restraint condition；According to
The edge-restraint condition generates several individuals at random, expands population M primary0Scale.
7. flue-cured tobacco according to claim 5 cultivates decision-making technique, which is characterized in that use genetic algorithm meter in step S45
Calculation obtains the process of new population are as follows: firstly, using roulette method from population M primary0The middle close expected cultivation target of selection
Individual constitutes several pairs of parents and female generation；Secondly, successively each pair of parent and female generation are intersected by crossover probability coefficient,
It obtains with each pair of parent and mother for several corresponding individuals；Each of finally, intersection is generated according to mutation probability coefficient
Individual carries out mutation operation, obtains filial generation M1。
8. a kind of flue-cured tobacco based on genetic algorithm cultivates decision system, which is characterized in that the flue-cured tobacco cultivates decision system and includes:
Database module cultivates data for storing flue-cured tobacco, flue-cured tobacco cultivates evaluation model, flue-cured tobacco cultivates the result of decision；
Data acquisition module, for obtaining the relevant data of flue-cured tobacco cultivation from database module；
Data preprocessing module rejects the abnormal data in data and the number that peels off for pre-processing to the data got
According to；
Server background module for being packaged to module included by its inside, and is write using computer programming language
The function that all modules for including inside it have is realized at dynamic link library；
Front-end interface module, for showing the data from server background module calls on the display device.
9. flue-cured tobacco according to claim 8 cultivates decision system, which is characterized in that server background module further includes flue-cured tobacco
Quality modeling module and flue-cured tobacco cultivate decision-making module, in which:
Flue-cured tobacco quality modeling module is established roasting for being modeled using yield and quality of the artificial neural network to flue-cured tobacco
Cigarette quality evaluation model；
Flue-cured tobacco cultivates decision-making module, is about for using genetic algorithm to establish with flue-cured tobacco growing district ecological condition and flue-cured tobacco cultivation
Beam condition, using flue cured tobacco quality and yield as the Optimized model of target；The flue-cured tobacco cultivation in best productive target is acquired to determine
The result that plan is supported.
10. flue-cured tobacco according to claim 9 cultivates decision system, which is characterized in that also set up in server background module
Periodically automatically update the more new function of model；When cultivating decision making function using flue-cured tobacco, the modeling of flue-cured tobacco quality is called directly
Flue-cured tobacco evaluation model in module；In server background module, dynamic link library is write using C# language.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910161363.6A CN110009191A (en) | 2019-03-04 | 2019-03-04 | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910161363.6A CN110009191A (en) | 2019-03-04 | 2019-03-04 | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110009191A true CN110009191A (en) | 2019-07-12 |
Family
ID=67166457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910161363.6A Pending CN110009191A (en) | 2019-03-04 | 2019-03-04 | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009191A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799741A (en) * | 2012-07-30 | 2012-11-28 | 中国海洋大学 | Initially baked tobacco formula threshing optimized design method based on genetic algorithm |
| CN105303252A (en) * | 2015-10-12 | 2016-02-03 | 国家计算机网络与信息安全管理中心 | Multi-stage nerve network model training method based on genetic algorithm |
| CN106529584A (en) * | 2016-10-25 | 2017-03-22 | 福建农林大学 | Flue-cured tobacco aroma type and quality judgment intelligent evaluation method |
| US20170116525A1 (en) * | 2015-02-03 | 2017-04-27 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN106717412A (en) * | 2016-12-01 | 2017-05-31 | 攀枝花学院 | High-quality tobacco produces the determination method of fertilizer applications |
| CN106919979A (en) * | 2015-12-25 | 2017-07-04 | 济南大学 | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control |
-
2019
- 2019-03-04 CN CN201910161363.6A patent/CN110009191A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799741A (en) * | 2012-07-30 | 2012-11-28 | 中国海洋大学 | Initially baked tobacco formula threshing optimized design method based on genetic algorithm |
| US20170116525A1 (en) * | 2015-02-03 | 2017-04-27 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN105303252A (en) * | 2015-10-12 | 2016-02-03 | 国家计算机网络与信息安全管理中心 | Multi-stage nerve network model training method based on genetic algorithm |
| CN106919979A (en) * | 2015-12-25 | 2017-07-04 | 济南大学 | A kind of method that utilization improved adaptive GA-IAGA realizes cotton processing Based Intelligent Control |
| CN106529584A (en) * | 2016-10-25 | 2017-03-22 | 福建农林大学 | Flue-cured tobacco aroma type and quality judgment intelligent evaluation method |
| CN106717412A (en) * | 2016-12-01 | 2017-05-31 | 攀枝花学院 | High-quality tobacco produces the determination method of fertilizer applications |
Non-Patent Citations (4)
| Title |
|---|
| HUI-LI GONG 等: "Genetic algorithm for optimization of tobacco-group formulas design", 《IMACS MULTICONFERENCE ON "COMPUTATIONAL ENGINEERING IN SYSTEMS APPLICATIONS"(CESA)》 * |
| 庄嘉祥: "精英策略遗传算法改进及在作物模型参数优化的应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李红梅: "基于线性回归和SVM的烟叶质量分析及等级预测模型", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 陈伟，周浩，潘文杰，等: "基于人工神经网络的烤烟评吸质量评估模型及实现", 《湖北农业科学》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fountas et al. | A model of decision-making and information flows for information-intensive agriculture | |
| Lopez et al. | Integrating simulation of architectural development and source–sink behaviour of peach trees by incorporating Markov chains and physiological organ function submodels into L-PEACH | |
| Bossel et al. | Simulation of multi-species tropical forest dynamics using a vertically and horizontally structured model | |
| CN109978234A (en) | Soil moisture content prediction, irrigation decision method and apparatus | |
| Mason | Decision-support systems for establishing radiata pine plantations in the Central North Island of New Zealand | |
| CN110837926A (en) | Tobacco main pest and disease damage prediction method based on big data | |
| CN106373022A (en) | BP-GA-based greenhouse crop plantation efficiency condition optimization method and system | |
| CN107680000A (en) | Area crops plant system of selection | |
| König et al. | Tree regeneration in models of forest dynamics–Suitability to assess climate change impacts on European forests | |
| Yan et al. | A quantitative knowledge-based model for designing suitable growth dynamics in rice | |
| Caldwell et al. | Simulation of multiple cropping systems with CropSys | |
| CN109858180A (en) | A kind of area crops water consumption spatial framework optimum design method | |
| Avigal et al. | Learning seed placements and automation policies for polyculture farming with companion plants | |
| Wang et al. | A decision support system for tobacco cultivation measures based on BPNN and GA | |
| Suarez et al. | Identifying smart strategies for effective agriculture solution using data mining techniques | |
| CN106372740A (en) | Calculation method and system of pasturing area water-land-pasture-livestock balance model | |
| CN105654242A (en) | Fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model, establishment method and application thereof | |
| CN110009191A (en) | A kind of flue-cured tobacco cultivation decision-making technique and system based on genetic algorithm | |
| Li et al. | Simulation-optimization based real-time irrigation scheduling: A human-machine interactive method enhanced by data assimilation | |
| Mishoe et al. | Using crop and pest models for management applications | |
| Yin | Central characteristics of reform: Measures of the effects of improved property rights, a stable policy environment, and environmental protection | |
| Ruiz-Ramos et al. | ALAMEDA, a structural–functional model for faba bean crops: morphological parameterization and verification | |
| CN109614763A (en) | A kind of area crops yield estimation method correcting crop modeling based on multi-source information substep | |
| Geetha et al. | A time-series based yield forecasting model using stacked lstm to predict the yield of paddy in cauvery delta zone in tamilnadu | |
| Khin et al. | Crop Yield Prediction Enhancement Utilizing Deep Learning and Ensemble Algorithms |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190712 |
|
| WD01 | Invention patent application deemed withdrawn after publication |